Past Talks in the Oberseminar - Intelligent Autonomous Systems

Up to 15-5-2020

DatePresenterTopicRoom
13.05.202014:00-14:30Christoph Zelch (SIM-TUDa), Invited Talk: Learning Control Policies from Optimal TrajectoriesSIM Zoom (https://tu-darmstadt.zoom.us/j/93879973107)
14.05.202014:00-14:30Tim Dorau, M.Sc. Intermediate Presentation: Distributionally Robust Optimization for Optimal Controlhttp://tiny.cc/7askoz
 14:30-15:00Markus Semmler, M.Sc. Intermediate Presentation: Bayesian Optimal Experimental Design for Dynamical Systemshttp://tiny.cc/7askoz
 16:30-17:00Fabian Scharf, B.Sc. Thesis Defense: Proximal Policy Optimization with Explicit Intrinsic MotivationKE-Oberseminar
30.04.202014:30-14:45Len Williamson, M.Sc. Thesis Defense: Learning Nonlinear Dynamical Systems with the Koopman OperatorS02|02 E202
30.04.202014:00-14:30Jascha Hellwig, B.Sc. Thesis Defense: Comparison of Methods for Human Feedback as a Reward-Signal in Reinforcement LearningS02|02 E202
30.04.202011:00-12:00Jean Kaddour (ICL), Invited Talk: Active Meta-LearningS0202-A102
28.04.202014:00-16:30Integrated Project: Final PresentationsS02|02 E202
16.04.202014:00-14:20Alexander Klein, M.Sc. Intermediate Presentation: Learning Robot Grasping of Industrial Work Pieces using Dense Object DescriptorsS02|02 E202
26.03.202015:10-15:40Alexy Georgos, M.Sc. Thesis Defense: Robotics under Partial Observability: A Survey of POMDP ApplicationsS02|02 E202
26.03.202014:30-15:10Sahil Sharma, M.Sc. Thesis Defense: Building and Continuous Control of a Differential Drive RobotS02|02 E202
12.03.202014:00-14:30Carlo D'Eramo, Research Talk: Sharing knowledge in Multi-Task RLE202
10.03.202011:30-12:15Niklas Funk (ETH Zürich), Invited Talk: Learning event-triggered control — leveraging hierarchical reinforcement learning algorithms to obtain resource-aware controllersS02|02 E202
5.03.202014:00-14:30Jakob Weimar, M.Sc. Thesis Defense: Exploring Intrinsic Motivation for Quanser Reinforcement Learning Benchmark SystemsS2|02 E202
27.02.202014:30-14:45Jascha Hellwig, B.Sc. Intermediate Presentation: Comparison of Methods for Human Feedback as a Reward-Signal in Reinforcement LearningS02|02 E202
27.02.202014:00-14:30Vignesh Prasad, Research Talk: Learning Human-like Handshaking BehavioursS2|02 E202
20.02.202014:00-14:30Jonas Stadtmüller, B.Sc. Thesis Defense: Dimensionality Reduction of Movement Primitives in Parameter SpaceS2|02 E202
13.02.202014:30-15:00Lejla Nukovic, B.Sc. Thesis Defense: Evaluation of the Handshake Turing Test for anthropomorphic RobotsS02|02 E202
13.02.202014:00-14:30Kai Ploeger, M.Sc. Thesis Defense: Robot JugglingS2|02 E202
12.02.202016:00-17:30Peter Dayan (MPI Cybernetics), Invited Talk: Replay and Preplay in Human PlanninS101/A4, Karo5
11.02.202017:00-19:00Dorothea Koert, Ph.D. Thesis Defense: Interactive Machine Learning for Assistive RobotsS2|02 C110
11.02.202011:00-12:00Heni Ben Amor (ASU), Invited Talk: Towards Robots that Hug and HelpS1|03 07
6.02.202014:30-15:00Pratik Borhade, M.Sc. Thesis Defense: Multi-agent reinforcement learning for autonomous drivingS02|02 E202
6.02.202014:00-14:30Vini Marconie Tengang, M.Sc. Intermediate Presentation: 3D-Pose Estimation for Robot MikadoE202
30.01.202014:00-14:30Tekam Feudjo, M.Sc. Intermediate Presentation: Off-Policy Policy Gradient Estimation via Mixture of ExpertsS02|02 E202
29.01.202010:30-11:30Maren Bennewitz (Uni Bonn), Invited Talk: Robot Navigation in Human EnvironmentsS202/C205
23.01.202015:00-17:00Oliver Brock (TU Berlin), Invited Talk: How Concepts of Computation Complicate Conquering IntelligenceS3|06, 052.
23.01.202014:00-14:30Axel Patzwahl, Honor Thesis Defense: Robot CatchingS02|02 E202
16.01.202014:00-15:00Oleg Arenz, Research Talk: Non-Adversarial Deep Imitation LearningE202
15.01.202014:00-16:30IP Intermediate PresentationsE202
9.01.202014:00-14:30Maximilian Kirschner, B.Sc. Thesis Defense: Integration of LIDAR S LAM for an Autonomous VehicleE202
6.01.202015:00-16:00Dimitar Ho (Caltech), Invited Talk: Robust Learning and Control without Prior KnowledgeS02|02 E202
19.12.201915:30-17:30Simone Parisi, Ph.D. Thesis Defense: Reinforcement Learning with Sparse and Multiple RewardsA102
19.12.201911:00-12:00Joschka Boedecker (Uni Freiburg), Invited Talk: Combining Long- and Short-term Predictions in Q-learningA102
18.12.201916:00-17:00Carlos Zednik (Uni Magdeburg), Invited Talk: Toward a Cognitive Science of AI - Aims, Norms, and MethodsS1 01 | A4
17.12.201916:00-18:30Dieter Büchler, Ph.D. Thesis Defense: Learning Control and High Speed Robotics on Muscular SystemsS02|02 E202
16.12.201915:30-17:30Sebastian Gomez-Gonzalez, Ph.D. Thesis Defense: Adaptation and Robust Learning of Probabilistic Movement PrimitivesS02|02 E202
16.12.201911:00-12:00Petar Komurshev (ICL), Invited Talk: Practical Robot Skill Learning for Manipulation and LocomotionS2|02 A102
12.12.201915:30-16:00Melvin Laux, M.Sc. Thesis Defense: Deep Adversarial Reinforcement Learning for Object DisentanglingS02|02 E202
12.12.201915:00-15:30Peter Nickl, M.Sc. Thesis Defense: Bayesian Inference for Regression Models using Nonparametric Infinite MixturesE202
12.12.201914:30-15:00Maximilian Kircher, M.Sc. Thesis Defense: Learning from Human Feedback: a Comparison of Interactive Reinforcement Learning AlgorithmsS02|02 E202
12.12.201914:00-14:30Moritz Knaust, M.Sc. Thesis Defense: Intuitive Imitation Learning for One-Handed and Bimanual Tasks Using ProMPsE202
5.12.201914:35-15:05Leon Keller, B.Sc. Thesis Defense: Application of state-of-the-art RL algorithms to robotics simulatorsS02|02 E202
5.12.201914:15-14:35Aron Eiermann, B.Sc. Thesis Defense: Automatic optimization of synthetic-biological systems with the help of a robotic platformE202
5.12.201914:00-14:10Jakob Weimar, M.Sc. Intermediate Presentation: Exploring Intrinsic Motivation for Quanser Reinforcement Learning Benchmark SystemsE202
4.12.201916:15-17:15Jozsef Fiser (Central European University), Invited Talk: Integrated view on perceptual and statistical learning in visionS101/A4, Karo5
29.11.201911:00-12:00Nicolai Lynnerup (DTI), Invited Talk: Tools for Reproducible Research on Learning RobotsA213
28.11.201915:00-15:10Len Williamson, M.Sc. Intermediate Presentation: Learning Nonlinear Dynamical Systems with the Koopman OperatorE202
28.11.201914:30-15:00Simon Kohaut, B.Sc. Thesis Defense: Simultaneous Map Correction and Auto Calibration for Hybrid LocalizationE202
28.11.201914:00-14:30Alexy Georgos, M.Sc. Intermediate Presentation: Robotics under Partial ObservabilityE202
28.11.201913:30-14:00Pascal Klink, Research Talk: Curriculum Learning for RLE202
21.11.201914:15-14:45Stefan Hübecker, M.Sc. Thesis Defense: Curiosity Driven Reinforcement Learning for Autonomous DrivingE202
21.11.201914:00-14:15Kai Ploeger, M.Sc. Intermediate Presentation: Robot JugglingE202
21.11.201911:00-12:00Hamid Eghbal-Zadeh (Johannes Kepler University), Invited Talk: Representation Learning under Incomplete and Imprecise Information ConditionsS02-02, Room A102
14.11.201915:30-16:00Ijlal Baig, B.Sc. Thesis Defense: Deep End-to-End CalibrationA126
14.11.201915:00-15:30Andreas Look (BCAI), Invited Talk: Deep Learning with Stochastic Differential EquationsA126
14.11.201914:00-15:00Melih Kandemir (BCAI), Invited Talk: Bayesian Neural Net Inference without SamplingA126
7.11.201915:30-16:00Michele Ginesi (Uni Verona), Invited Talk: Inference of Surgical GesturesA313
31.10.201916:15-17:15Deniz Gunduz (ICL), Invited Talk: Learn to Communicate – Communicate to LearnFraunhofer IGD, Hörsaal 074, Fraunhoferstraße 5, 64283 Darmstadt
31.10.201916:00-16:30Maximilian Hensel, B.Sc. Thesis Defense: Correlated Exploration for Robot Reinforcement LearningA313
31.10.201915:30-16:00Maximilian Kirschner, B.Sc. Intermediate Presentation: Integration of LIDAR SLAM for an Autonomous VehicleA313
24.10.201916:00-17:30Johannes Buchmann, Lecture: AbschiedsvorlesungS02|02 E202
24.10.201915:30-16:00Felix Divo, B.Sc. Thesis Defense: Trajectory Based Upper Body Gesture Recognition for an Assistive RobotA213
24.10.201915:00-15:30Matthias Lang, B.Sc. Thesis Defense: Imitation Learning for Highlevel Robot behavior in the context of elderly assistanceA213
24.10.201914:30-15:00Moritz Knaust, M.Sc. Intermediate Presentation: Intuitive Imitation Learning for One-Handed and Bimanual Tasks Using ProMPsA213
17.10.201914:30-15:00Aron Eiermann, B.Sc. Intermediate Presentation: Automatic optimization of synthetic-biological systems with the help of a robotic platformA213
17.10.201914:00-14:30Jasper Süß, B.Sc. Thesis Defense: Robust Control for Model LearningA213
16.10.201914:00-15:00IP Introduction TalkA213
10.10.201915:30-16:00Robin Menzenbach, B.Sc. Thesis Defense: Benchmarking Sim-to-Real Algorithms on Real-World PlatformsA102
10.10.201915:00-15:30Christian Weiland, B.Sc. Thesis Defense: Deep Model-based Reinforcement Learning by Propagating RewardsA102
10.10.201914:30-15:00Kai Cui, M.Sc. Thesis Defense: A Study on TD-Regularized Actor-Critic MethodsA102
26.09.201915:00-16:00Michael Lutter, I.P. Conclusion: Final Project PresentationA213
26.09.201914:30-15:00Christian Eilers, B.Sc. Thesis Defense: Bayesian Optimization for Learning from Randomized SimulationA213
26.09.201914:00-14:30Marcus Ebner von Eschenbach, M.Sc. Thesis Defense: Metric-based Imitation LearningA213
19.09.201915:30-15:45Kay Hansel, Janosch Moos, I.P. Conclusion: Foundations of Robust Adverserial Reinforcement LearningS02|02 E202
19.09.201915:00-15:15Tomas Pinto, I.P. Conclusion: Development and Implementation of an Approach for Multi-Object Tracking in the Context of Autonomous DrivingS02|02 E202
19.09.201914:30-15:00Florian Szymanski, M.Sc. Thesis Defense: Humanlike Bipedal Hopping with Reflex Based ControlA213
19.09.201914:00-14:30Joao Carvalho, M.Sc. Thesis Defense: Nonparametric Off-Policy Policy GradientS02|02 E202
12.09.201914:30-15:00Stephan Weigand, M.Sc. Thesis Defense: Guided Reinforcement Learning Under Partial ObservabilityA213
12.09.201914:00-14:30Maximilian Hensel, B.Sc. Intermediate Presentation: Correlated ExplorationA213
10.09.201910:00-11:00Satoshi Tadokoro (Tohoku University), Invited Talk: ImPACT Tough Robotics Challenge - Results of a national project of disaster roboticsS202 C110
5.09.201914:30-15:00Joe Watson, Research Talk: Input Inference as Stochastic Optimal ControlA213
5.09.201914:00-14:15Maximilian Kircher, M.Sc. Intermediate Presentation: Learning from Human Feedback: A Comparison of Interactive Reinforcement Learning AlgorithmsA213
29.08.201915:30-16:00Jasper Suess, B.Sc. Intermediate Presentation: Robust Control for Model LearningA213
29.08.201915:00-15:30Marcel Hussing, Honor Thesis Defense: Online Adaptation, Exploration through Forgetting in Stochastic Recurrent NetworksA213
29.08.201914:30-15:00</td><td align='right'>Saoud Hussam, M.Sc. Thesis Defense: Improving Sample-Efficiency with a Model-Based Deterministic Policy GradientA213
29.08.201914:00-14:15Felix Divo, B.Sc. Intermediate Presentation: Trajectory Based Upper Body Gesture Recognition for an Assistive RobotA213
22.08.201914:30-15:00Suman Pal, M.Sc. Thesis Defense: Deep Robot Reinforcement Learning for Assisting a HumanS02|02 E202
22.08.201914:00-14:30Peter Nickl, M.Sc. Intermediate Presentation: Bayesian Inference for Regression Models using Nonparametric Infinite MixturesS02|02 E202
15.08.201916:00-16:15Augustin Wilberg, M.Sc. Thesis Defense: An Exploration of Interacting Machine Learning Methods for Agent NavigationA213
15.08.201915:30-16:00Shuo Zhang, M.Sc. Thesis Defense: Integration of self-imitation and model-based learning to actor-critic algorithmsA213
15.08.201915:00-15:15Patrick Lutz, B.Sc. Thesis Defense: Automatic Segmentation and Labeling for Robot Table Tennis Time SeriesA213
7.08.201918:00-19:00Jan strikes back!S02|02 E202
1.08.201915:00-15:30Quentin Delfosse, M.Sc. Intermediate Presentation: Grasping Objects Using a Goal-Discovering Architecture for Intrinsically-Motivated LearningA213
1.08.201914:50-15:00Tomas Pinto, I.P. Intermediate Presentation: Development and Implementation of an Approach for Multi-Object Tracking in the Context of Autonomous DrivingA213
1.08.201914:40-15:15Artur Yanhua, I.P. Intermediate Presentation: Improving Intention Aware ProMPsA213
1.08.201914:30-14:40Sebastian Sztwiertnia, I.P. Intermediate Presentation: Simulation-based Haptic Feedback for Delayed Telerobotic Arm OperationsA213
1.08.201914:00-14:20Robin Menzenbach, B.Sc. Intermediate Presentation: Benchmerking Sim-2-Real AlgorithmsA213
25.07.201915:20-15:50Nils Huegelmann, M.Sc. Thesis Defense: The applications of probabilistic movement primitives to generate adaptable and re-usable robot movements in the context of the Moley Robotic KitchenS02|02 E202
25.07.201914:50-15:20Shuo Zhang, M.Sc. Intermediate Presentation: Integration of self-imitation and model-based learning to actor-critic algorithmsS02|02 E202
25.07.201914:20-14:50Lina Jukonyte, M.Sc. Thesis Defense: Probabilistic Motion and Intention Prediction for Autonomous VehiclesS02|02 E202
25.07.201914:00-14:20Matthias Lang, B.Sc. Intermediate Presentation: Imitation Learning for Highlevel Robot behavior in the context of elderly assistanceS202 A213
19.07.201914:00-15:00Andre Platzer (CMU), Invited Talk: Differential Equation AxiomatizationC205
18.07.201914:30-15:30Philip Becker-Ehmck, Research Talk: Switching Linear Dynamics for Variational Bayes FilteringS02|02 E202
18.07.201914:00-14:30Matthias Schulteis, M.Sc. Thesis Defense: Bayesian Reinforcement Learning for System IdentificationS02|02 E202
15.07.201914:30-19:00Marco Ewerton, Ph.D. Thesis Defense: Bidirectional Human-Robot Learning: Imitation and Skill ImprovementS02|02 A102
11.07.201915:30-16:00Suman Pal, M.Sc. Intermediate Presentation: Deep Robot Reinforcement Learning for Assisting a HumanS02|02 E202
11.07.201915:00-15:30Kai Kui, M.Sc. Intermediate Presentation: TD-Regularized AlgorithmsS02|02 E202
11.07.201914:30-15:00Alexander Woelker, M.Sc. Thesis Defense: Local Pixel Manipulation Detection with Deep Neural NetworksS02|02 E202
11.07.201914:00-14:30Simon Leischnig, M.Sc. Thesis Defense: Robot Grasping for any HandS02|02 E202
4.07.201914:00-14:15Stefan Hübecker, M.Sc. Intermediate Presentation: Curiosity Driven Reinforcement Learning for Autonomous DrivingS02|02 E202
27.06.201915:30-15:45Ijlal Baig, M.Sc Intermediate Presentation: DETECT - a Deep End-To -End Calibration ThesisS02|02 E202
27.06.201915:00-15:15Leon Keller, B.Sc. Intermediate Presentation: Application of state -of-the-art RL algorithms to robotics simulatorsS02|02 E202
27.06.201914:20-15:00Samuele Tosatto, Research Talk: Non-Parametric Off-Policy Policy GradientS02|02 E202
27.06.201914:00-14:20Joao Carvalho, M.Sc. Intermediate Presentation: Non-Parametric Off -Policy Policy GradientS02|02 E202
21.06.201914:30-15:30Azalia Mirhoseini (Google Brain), Dept. Talk: Machine Learning for SystemsMornewegstrasse 30, 64293 Darmstadt – room 5.3.01
21.06.201911:00-12:00Roberto Lampariello (DLR), Research Talk: Trajectory-based semi-autonomous grasping of a non-cooperative tumbling satellite with a free-floating robotS02-09 Room 007 next to Informatik Labore
13.06.201915:00-15:15Augustin Wilberg, M.Sc. Intermediate Presentation: Can RL, SL and UL interact in agent navigation inspired by the brain?S02|02 E202
6.06.201916:00-16:30David Hoffmann, M.Sc. Final Presentation: Pedestrian Detection, Tracking and Intention Prediction in the Context of autonomous DrivingS02|02 E202
6.06.201915:30-16:00Stephan Weigand, M.Sc. Intermediate Presentation: Guided Reinforcement Learning Under Partial ObservabilityS02|02 E202
6.06.201915:00-15:30Riad Akrour, Research Talk: Projections for Approximate Policy Iteration AlgorithmsS02|02 E202
6.06.201914:00-15:00Jia-Jie Zhu (MPI-IS), Invited Talk: Why is optimal control still challenging and how can learning help?S02|02 E202
23.05.201914:00-15:00Julen Urain, Research Talk: Study of force-impendance primitives in a human-humanoid coworking environmentS02|02 E202
16.05.201914:00-15:00Davide Tateo, Research Talk: Model-free Inverse Reinforcement LearningS02|02 E202
9.05.201915:00-15:30Florian Szymanski, M.Sc. Intermediate Presentation: Humanlike Bipedal Hopping with Reflex Based ControlS02|02 E202
9.05.201914:30-15:00David Rother, Seminar Thesis Final Presentation: Bio-inspired Components for long-term learning of internal models for robot motor skillsS02|02 E202
9.05.201914:10-14:40Matej Zecevic, Seminar Thesis Final Presentation: S-PILCO: An Effort of Developing a Safe Reinforcement Learning Method based on PILCOS02|02 E202
9.05.201914:00-14:10Alexander Klein: RL Seminar presentation, "Challanges of Model Predicitve Control in a Black Box Environment"S02|02 E202
2.05.201915:00-15:45João André (University of Minho), Research Talk: Construction of a Library of Skill Memories for Movement AdaptationS02|02 E202
2.05.201914:30-15:00Frederik Bous, M.Sc. Thesis Final Presentation: Generating Spectral Envelopes for Singing Synthesis Using Neural NetworksS02|02 E202
2.05.201914:00-14:30Anton Ziese, M.Sc. Final Presentation: Fast Multi-Objective Redundancy Resolution for Highly-Redundant Mobile RobotsS02|02 E202
30.04.201911:00-12:00Alexander Spröwitz (MPI-IS), LL Talk: How can Bio-robotics Help Understand Legged Locomotion?S1/15 Room 29 (Red Saloon)
25.04.201914:00-14:30Albert Schotschneider, Seminar Thesis Final Presentation: Learning Human Intentions from Motion DataS02|02 E202
18.04.201914:05-14:35Volker Hartmann, Final M.Sc. Thesis Presentation: Deep reinforcement learning with optimality tightened bootstrapped DQNS02|02 E202
18.04.201914:00-14:05Seminar: Igor Braun, Dual vs PrimalS02|02 E202
11.04.201914:00-15:00Zinan Liu, M Sc Final PresentationS02|02 E202
9.04.201911:00-12:00Frank Sup (U.Mass. Amherst), LL Talk: Optimizing the Design of Assistive Devices with Predictive Gait SimulationsS1/18 PC-Pool (Hinterhaus, 2. OG)
4.04.201915:00-16:00Daniel Tanneberg, Ph.D. Proposal: From Cognition and Abstract Strategies to Adaptive Movements: Neural Networks for Intelligent Autonomous AgentsS02|02 E202
4.04.201914:30-15:00Nils Huegelmann, M.Sc. Intermediate Presentation: The applications of probabilistic movement primitives to generate adaptable and re-usable robot movements in the context of the Moley Robotic KitchenS02|02 E202
4.04.201914:00-14:15Matthias Schultheis, Inter. M.Sc.: Approximate Bayesian Reinforcement Learning for Sys-IDS02|02 E202
2.04.201911:00-12:00Christian Leukel (U. Freiburg), LL Talk: Resolving Functions of Motor Cortex Circuits for Movement ControlS1/18 Seminarraum (Hinterhaus, EG)
28.03.201915:30-16:00Deepak Singh Mohan, Final M.Sc. Thesis Presentation: Learning hand adjustments for haptic interactionsS02|02 E202
28.03.201914:30-15:30Patrick Klose (Uni Fra), Research Talk: Using Reinforcement Learning for Simulated Autonomous DrivingS02|02 E202
28.03.201914:15-14:30Pascal Klink, M.Sc. Final Presentation: Generalization and Transferability in RLS02|02 E202
28.03.201914:00-14:05RL Class Seminar PresentationS02|02 E202
26.03.201911:00-12:00Leif Johannsen (RWTH Aachen), LL Talk: Controlling Body Balance with Light Interpersonal Tactile SupportS1/18 Seminarraum (Hinterhaus, EG)
25.03.201911:00-12:00Nicholas Stergiou (UNE), LL Talk: Harenssing Movement Variability to Treat and Prevent Motor Related DisordersS1/18 Seminarraum (Hinterhaus, EG)
22.03.201913:00-13:30Ge Li, Research Talk: "Enabling RL for Tennis-Table a Gym-like environment"S02|02 E202
21.03.201913:30-13:45IP2 PresentationsS02|02 E202
21.03.201913:00-13:30Philipp Becker, Final MS Thesis Presentation: Using the I-Projection for Mixture Density EstimationS02|02 E202
7.03.201914:30-14:45Hussam Saoud, Intermediate Master Thesis Presentation: Improving sample efficiency with a model-based deterministic policy gradientS02|02 E202
7.03.201914:00-14:30Alymbek Sadybakasov, Final MS Thesis Presentation: Learning tactile skills for architectural assemblyS02|02 E202
28.02.201915:30-16:00Volker Hartmann, Intermediate M.Sc. Thesis Presentation: Deep reinforcement learning with optimality tightened bootstrapped DQNS02|02 E202
28.02.201915:00-15:30David Hoffmann, Intermediate MSc : Pedestrian Detection, Tracking and Intention Prediction in the Context of Autonomous DrivingS02|02 E202
28.02.201914:30-15:00Alexander Wölker, MSc Thesis Intermediate Talk: Local Pixel Manipulation Detection with Deep Neural NetworksS02|02 E202
28.02.201914:00-14:30Josef Kinold, Final BSc Thesis presentation: Development of a Simulation Model for an Autonomous VehicleS02|02 E202
21.02.201914:45-15:15Pascal Klink, RobCom2.0, TutorialS02|02 E202
21.02.201914:25-14:45Lennart Ebeling, Final BS Thesis presentation: Experimental validation of an MPC-POMDP model of ball catchingS02|02 E202
21.02.201914:00-14:10RL seminar presentationsS02|02 E202
19.02.201912:00-13:00Adam Kosiorek (Oxford), Invited Talk: Generative Modelling & Tracking of Moving Objects with Attention MechanismsA102, S2|02
14.02.201914:00-15:30Simone Parisi, Ph.D. Proposal: Regularised Reinforcement Learning: Towards More Scalable and Autonomous AlgorithmsS02|02 E202
14.02.201913:30-14:00Felix Kaiser, Final BSc Thesis presentation: Towards a Robot Skill Library Using Hierarchy, Composition and AdaptationS02|02 E202
7.02.201914:00-16:00Dieter Büchler, Ph.D. Proposal: Learning Control and High Speed Robotics on Muscular SystemsS02|02 E202
31.01.201914:00-15:00Tim Landgraf (FU Berlin), Invited Talk: Reinforcement Learning for Biomimetic Robot SwarmsS02|02 E202
24.01.201914:00-15:30Oleg Arenz, Ph.D. Proposal: Trust-Region I-Projections for Variational Inference and Inverse Reinforcement LearningS02|02 E202
17.01.201917:00-19:00Gregor Gebhardt, Ph.D. Thesis Defense: Using Mean Embeddings for State Estimation and Reinforcement LearningS202 A126
17.01.201914:00-14:45Anton Ziese, M.Sc. Intermediate Presentation: Fast Multi-Objective Redundancy Resolution for Highly-Redundant Mobile RobotsS02|02 E202
14.01.201916:00-18:00Simon Guist (MPI/Uni Heidelberg), Research Talk: Reinforcement Learning for High-Speed Robotics with Muscular ActuationS1|03 Hochschulstr. 1 - 07
10.01.201914:30-15:00Intermediate IP PresentationsS02|02 E202
10.01.201914:00-14:30David Nass, M.Sc. Thesis Final Presentation: Risk-sensitive policy searchS02|02 E202
8.01.201917:00-18:00Torsten Hoefler (ETH), Research Talk: A systems guy's view of quantum computingS02|02 E202
13.12.201814:30-15:00Philipp Becker, M.Sc. Intermediate Presentation: Using the I-projection to learn GMMs and Mixture of ExpertsS02|02 E202
13.12.201814:00-14:30Onur Celik, M.Sc. Final Presentation: Chance Constraints for Stochastic Optimal Control and OptimizationS02|02 E202
11.12.201811:00-12:00Charlotte Le Mouel (MPI Intelligent Systems), Research Talk: The role of postural adjustments in motor coordination in humansMeeting Room (Magdalenenstraße 27, S1/17, 1. OG)
26.11.201816:30-17:30Saso Dzerosk, Research Talk: Mining Big and Complex DataS2/02 C205
22.11.201814:00-14:30Rong Zhi, Final M.Sc. Thesis Presentation: Deep reinforcement learning for autonomous driving under uncertaintyS02|02 E202
19.11.201816:00-17:00Dana Ballard, Research Talk: In large scale movements with a common goal humans use common posturesC110
15.11.201814:30-15:00Christian Ritter, Final MS Thesis Presentation: Deep Model LearningS02|02 E202
15.11.201814:00-14:20Alymbek Sadybakasov, Intermediate MS Talk: Learning tactile skills for architectural assemblyS02|02 E202
8.11.201814:00-14:30Lennart Ebeling, Intermediate BSc Talk: Experimental validation of an MPC-POMDP model of ball catchingS02|02 E202
26.10.201813:00-13:30Samuel Clarke (CMU), Invited Talk: Audio Feedback in Robotic ManipulationE203
25.10.201816:00-17:00Volker Tresp, Research Talk: Deep X: Deep Learning with Deep KnowledgeS3|20 Room 111
25.10.201814:30-15:00Tim Schneider, Final B.Sc. Presentation: Guided Policy Search for In-Hand ManipulationS02|02 E202
25.10.201814:00-14:15Fabio CoRL Test TalkS02|02 E202
24.10.201818:00-19:00Debora Clever (ABB), Research Talk: Autonome Systeme in der ProduktionGebäude L1|01 (Otto-Berndt-Straße 2), Raum K24
24.10.201813:00-14:30Okan Koc, Ph.D. Thesis Defense: Control and Learning for Robot Table TennisA102
24.10.201810:30-11:30Sethu Vijayakumar (U. Edinburgh), Invited Talk: Shared Autonomy - The Future of Interactive RoboticsS202/C120
22.10.201816:30-18:00Filipe Veiga, Ph.D. Thesis Defense: Tactile Manipulation: Sensing\ , Control and LearningA102
22.10.201811:00-12:00Veronica Santos (UCLA), Invited Talk: Artificial haptic intelligence for human-machine systemsA102
11.10.201813:30-14:45Sebastian Trimpe (MPI-IS), Invited TalkS02|02 E202
4.10.201814:00-14:30Marius Vieth, Master's Thesis Final PresentationS02|02 E202
1.10.201815:00-17:00Rudolf Lioutikov, Ph.D. Thesis Defense: Parsing Motion and Composing Behavior for Semi-Autonomous ManipulationS02|02 A102
1.10.201813:30-14:30Ken Goldberg (UC Berkeley), Research Talk: The New Wave in Robot GraspingS02|02 E202
27.09.201815:00-15:30Ana Borg, Final Bsc. Thesis Presentation: Infinite Mixture Policies for Reinforcement LearningS02|02 E202
27.09.201814:30-15:00Dominik Dienlin - Final MS Thesis Talk: Generative Adverserial Learning for Autonomous DrivingS02|02 E202
27.09.201814:00-14:30David Bug, Final MS Thesis Presentation: Comparison and evaluation of Concepts for SLAM in the Context of Autonomous DrivingS02|02 E202
20.09.201814:00-14:30Zhizhen Wang, Final M.Sc. Thesis Presentation: Representation Learning for Tactile ManipulationS02|02 E202
13.09.201815:30-16:00Christian Ritter, Intermediate Master ThesisS02|02 E202
13.09.201815:00-15:30Felix Kaiser, Intermediate BSc. Thesis Presentation: Towards a Robot Skill Library Using Hierarchy, Composition and AdaptationS02|02 E202
13.09.201814:30-15:00Kim Berninger, Intermediate MS Thesis Presentation: Learning Conditional Embeddings for Structured Movement using a Recursive AutoencoderS02|02 E202
13.09.201814:00-14:15David Nass, Intermediate MS Thesis Presentation: Learning risk-sensitive movement primitives for robot badmintonS02|02 E202
6.09.201814:00-14:30Zlatko Kolev, B.Sc. Final Presentation: Joint Learning of Human and RobotsS02|02 E202
31.08.201810:00-11:00Jan H. Reimann (Uni Delaware), Research Talk: How to walk on two legs: neural control of balance during walking in humans?Red Saloon (S1/15, Alexanderstrasse 10, Room 29)
30.08.201814:00-14:30Pascal Klink - Intermediate MS Thesis Talk: Generalizing Optimal Controllers to Novel GoalsS02|02 E202
23.08.201815:00-15:30Onur Celik, MSc. Intermediate Talk: Chance Constraints in Optimal ControlS02|02 E202
23.08.201814:30-15:00Ana Borg, BSc. Intermediate: Infinite-Mixture Policies in RLS202/E202
23.08.201814:00-14:30Nourhan Khaled, BSc. Benchmarking Reinforcement Learning Algorithms for Robot TetherballS202/E202
17.08.201814:00-14:30Olga Holet, Research TalkS02|02 E202
17.08.201811:00-12:00Koh Hosoda (U.Osaka), Invited Talk: Soft Humanoid RoboticsAlexanderstr. 10, R29
16.08.201814:00-14:30Yunlong Song, M.Sc. Thesis Defense: Minimax and entropic proximal policy optimizationS02|02 E202
2.08.201814:00-14:30Zlatko Kolev, B.Sc. Intermediate Presentation: Joint Learning of Human and RobotsS02|02 E202
26.07.201815:00-16:00Yassine Nemmour (MPI), Research TalkS02|02 E202
19.07.201814:00-15:00Dominik Dienlin, M.Sc. Intermediate Presentation: Generative Adverserial Imitation Learning for Autonomous DrivingS02|02 E202
18.07.201815:00-16:00Haitham Bou Ammar (Prowler.io), Invited Talk: Data-Efficient Reinforcement LearningRoom 07, S1|03, Hochschulstraße 1, 64289 Darmstadt, Germany
13.07.201810:00-12:00Seungmoon Song (Stanford), Invited Talk: Modeling human locomotion control and its applicationsS02|02 E202
12.07.201814:00-14:30Tim Schneider, B.Sc. Intermediate Presentation: Guided Policy Search for In-Hand ManipulationS02|02 E202
5.07.201815:00-16:00Prof. Masaki Takahashi, Research Talk: How to fuse machine learning and control theoryS02|02 E202
5.07.201814:00-15:00Zhang-Wei Hong (NTHU, Taiwan), Research Talk: Deep Reinforcement Learning for RoboticsS02|02 E202
28.06.201814:00-15:00Boris Belousov, Research Talk: Geometry, probability, and controlS02|02 E202
21.06.201815:00-15:30Florian Brandherm, M.Sc. Final Presentation: Learning Replanning Policies with Direct Policy SearchS02|02 E202
21.06.201814:00-15:00Rudolf Lioutikov, Research Talk: The Imitation Learning Pipeline - from unlabeled demonstrations to intuitive movement grammarsS02|02 E202
14.06.201815:00-15:30Felix Treede, M.Sc. Final Presentation: Learning Robust Control Policies from Perturbed SimulationsS02|02 E202
14.06.201814:00-15:00Oleg Arenz: Research Talk, Sampling High-Dimensional Multi-Modal Distributions via Varitional InferenceS02|02 E202
12.06.201810:00-11:00Krzysztof Dembczyński (TU Poznan)Tree-based algorithms for extreme multi-label classificationS1|A02
7.06.201814:30-15:30Marco Ewerton, Research Talk: Human-Robot Joint Motor Skill LearningS02|02 E202
7.06.201814:00-14:30Rong Zhi, M.Sc. Intermediate Presentation: Deep Reinforcement Learning under Uncertainty for Autonomous DrivingS02|02 E202
6.06.201811:00-12:00Wenzhen Yuan (MIT), Research Talk: Making Sense of the Physical World with High-resolution Tactile SensingS02|02 E202
24.05.201814:30-15:00Onur Celik, Msc. Intermediate: Chance Constrained OptimizationS02|02 E202
24.05.201814:00-14:30Pascal Klink: Online Dynamic Model LearningS02|02 E202
17.05.201814:00-15:00Fabio Muratore, Research Talk: Domain Randomization for Policy SearchS02|02 E202
14.05.201814:30-16:00Shie Mannor (Technion), Invited Talk: Risk in Reinforcement Learning: Nothing ventured nothing gainedS02|02 E202
8.05.20189:50-11:30Amazon: Introduction to Deep Learning with Apache MxNet GluonS202/C205
7.05.201816:30-17:30Debora Clever (ABB), Research Talk: Autonome Systeme in der ProduktionS 3|20 – Rundeturmstraße 10; Raum 18
3.05.201814:00-14:30Zhizhen Wang, Msc. Intermediate Presentation: "Representation Learning for Tactile Manipulation"S02|02 E202
19.04.201815:00-15:30Carlo D'Eramo, visiting PhD, Politecnico di Milano: Mushroom - Python RL LibraryS02|02 E202
19.04.201814:30-15:00Jeremy Tschirner, B.Sc. Final Presetation: Boosted DQNS02|02 E202
19.04.201814:00-14:30Yunlong Song, MSc. Intermediate Presentation: f-divergence penalized policy optimizationS02|02 E202
12.04.201814:00-15:00Samuele Tosatto, Research Talk: An Optimistic Perspective in Reinforcement LearningS02|02 E202
6.04.201811:00-12:00Masashi Sugiyama (U.Tokyo & RIKEN), Invited Talk: Machine Learning from Weak Supervision ---Towards Accurate Classification with Low Labeling CostsS02-02 C120
5.04.201814:30-15:30Sebastian Gomez, Research Talk: Adaptation and Robust Learning of Probabilistic Movement PrimitivesS02|02 E202
5.04.201814:00-14:30Albert Schotschneider, B.Sc. Final Presentation: Collision Avoidance in Uncertain Environments for Autonomous Vehicles using POMDPsS02|02 E202
29.03.201815:30-16:10Carlo D'Eramo, Research Talk: Estimating the Maximum Expected Value through Gaussian ApproximationS02|02 E202
29.03.201815:00-15:30Idris Nematpur, B. Sc. Final Presentation: Jointly Learning from Demonstrations and Human Preferences on Non-Linear systemsS02|02 E202
29.03.201814:00-15:00Michael Lutter, Research Talk: Robot Skill LearningS02|02 E202
19.03.201813:30-14:00IP Final Presentation: CobotsS02|02 E202
15.03.201814:00-14:30Sebastian Rinder, B.Sc. Final Presentation: Trajectory Kernel for Bayesian OptimizationS02|02 E202
1.03.201815:00-15:15Invited Talk: Tobias Hammerschmidt - Recursion and A* for the Hamster ProblemS02|02 E202
1.03.201814:00-15:00Research Talk: Robotics at ABB Corporate ResearchS02|02 E202
28.02.201811:00-12:00Stefan Löckel, Porsche AG: Estimation, Optimization & Control -- and a Ph.D. OutlookS02-02 A213
22.02.201814:00-14:15Felix Treede, M. Sc. Intermediate Presentation, Reinforcement Learning from Perturbed Physics SimulationsS02|02 E202
1.02.201814:30-15:00Kianoosh Soltani Naveh, Research Talk: Learning Traction Conditions via POMDPsS02|02 E202
1.02.201814:00-14:30Hong Linh Thai, M. Sc. Final Presentation: Deep Reinforcement Learning for POMDPsS02|02 E202
26.01.201814:00-15:00Roberto Calandra, Research Talk: Learning to Grasp from Vision and TouchA313
25.01.201815:00-15:30Robin Hesse, B.Sc. Final Presentation: Development and Evaluation of 3D Autoencoders for Feature ExtractionS02|02 E202
25.01.201814:30-14:50Jeremy Tschirner, B. Sc. Intermediate Presentation: Boosted Deep Q NetworkS02|02 E202
25.01.201814:00-14:10Devron Williams: IP intermediate, Building a Grasping TestbedS02|02 E202
23.01.201818:00-19:00Daniel Blackman (STRIDE/FSU), Invited Talk: Design and Control of Minitaur, a Direct-drive Quadrupedal RobotS1 18 (PC-Pool, Dachgeschoss)
22.01.201811:00-12:00Gerhard Kurz (KIT), Research Talk: Estimation Based on Directional Statistics for Robotic Beating Heart Surgery with Automatic Motion CompensationA313
18.01.201815:00-16:00Gagan Narula (INI), Research Talk: Songbird song learning through the lens of reinforcement learningS02|02 E202
18.01.201814:00-15:00Simone Parisi, Research Talk: Status Update - What I Did at RIKENS02|02 E202
18.01.201813:30-14:00Tobias Dollinger (TUDA), Research Talk: Quadcopter experiencing extreme disturbancesS02|02 E202
11.01.201813:30-14:00Danny Dittmar, M. Sc. Final Presentation: Distributed Reinforcement Learning with Neural Networks for RoboticsS02|02 E202
10.01.201816:30-18:00Rainer Goebel (Maastricht University), Invited Talk: Cracking representational codes in the human brain: From basic research to clinical fMRI applicationsS01-03,Room 283
4.01.201815:30-16:00Bastian Wibranek (Architecture Department, Digital Design Unit), Invited Talk: Reconfigurable architectures through the use of robotsA213
21.12.201713:30-14:30Amir Ghalamzan (University of Birmingham), Invited Talk: Robot learning in a dynamic environment and grasping under post-grasp objectivesS02|02 E202
21.12.201710:00-11:00Desmond Elliot (U. Edinburgh), Invited Talk: Multilingual and Multimodal Natural Language ProcessingS2|02 A102
19.12.201716:00-17:00Aude Billard (EPFL), Research Talk: Machine Learning for Estimating Robust Control LawsC110
19.12.201711:30-13:30Simon Manschitz, Ph.D. Thesis Defense: Learning Sequential Skills for Robot Manipulation TasksA103
18.12.201717:00-18:00Jens Kober (TU Delft), Invited Talk: Learning Complex Robot-Environment InteractionsS01-03, Room 7 (Basement)
14.12.201714:30-15:00Okan Koc (Max-Planck Institute of Intelligent Systems), Research TalkS02|02 E202
14.12.201714:00-14:30Albert Schotschneider, B.Sc. Intermediate Presentation: Collision Avoidance in Uncertain Environments for Autonomous Vehicles using POMDPsS02|02 E202
14.12.201713:30-14:00Yannik Frisch, B.Sc. final Presentation: The effect of intrinsic motivation signals on reinforcement learning strategiesS02|02 E202
7.12.201713:30-14:00Davis Manh Truong, Finn Gundlach, Johannes Heilmann, Timo Martin , Praktikum Talk, Online Gaming Framework for Brain-Computer-InterfacesS02|02 E202
6.12.201716:30-18:00Felix Wichmann (Uni Tübingen), CCS Talk: Comparing deep neural networks against humans: Object recognition with weak signalsS01-03,Room 283
30.11.201714:00-14:30Nick Heppert, B.Sc. Final Presentation: Can we predict grasp forces from photos?S02|02 E202
30.11.201713:30-14:00David Rother, B.Sc. Final Presentation: Transferring Insights on Biological Sleep to Robot Motor Skill LearningS02|02 E202
29.11.201715:30-17:00Julia Vinogradska, Ph.D. Defense: Gaussian Processes in Reinforcement Learning: Stability Analysis and Efficient Value PropagationS02-02 | A102
29.11.201713:30-14:30Carl Rasmussen (Cambridge Univ.), Invited Talk: Variational Inference in Gaussian Processes for Non-Linear Time SeriesS1-03 (Altes Hauptgebäude), Room 23
23.11.201713:30-14:00Matej Zecevic, B.Sc. Final Presentation: Matching Bundles of Axons Using Feature GraphsS02|02 E202
22.11.201713:30-14:30Simone Frintrop (Uni Hamburg), Invited Talk: Vision for Mobile Systems: From Saliency to Object DiscoveryS02|02 E202
16.11.201713:30-14:00Sebastian Rinder, B.Sc. Intermediate Presentation: Trajectory Kernel for Bayesian OptimizationS02|02 E202
9.11.201713:30-14:00Karl-Heinz Fiebig, IP final talk, Spatio-spectral Transfer Learning for Motor Performance EstimationS02|02 E202
2.11.201713:30-14:30Joni Pajarinen, Research Talk: Compatible Policy SearchS202 E202
26.10.201715:00-15:30Sebastian Szelag, B.Sc. Final Presentation: Transferring Insights on Mental Training to Robot Motor Skill LearningA126
26.10.201714:30-15:00Markus Semmler, B.Sc. Final Presentation: Exploration in Deep Reinforcement LearningA126
26.10.201714:00-14:30Viktor Pfanschilling, B.Sc. Thesis Final Presentation: Genetic Programming with HaskellA126
26.10.201713:30-13:45Philipp Becker, IP PresentationA126
19.10.201713:30-14:00Pavan Gadiya, M.Sc. Final Presentation: Large Scale Real-Time Data Analytics Platform for Energy ExchangeE 302
18.10.201716:30-18:00Patrick van der Smagt (VW), CCS Talk: Machine Learning: from probability densities to roboticsS01-03,Room 283
17.10.201714:00-15:00Bernt Schiele (MPI), Research Talk: Beyond Deep Learning: Multi-Person Pose Estimation and Multi-People TrackingC110
12.10.201713:30-14:00Nadine Weibrecht, Master Thesis Final Presentation: Auswertung von Sensordaten mit Machine Learning AlgorithmenS02|02 E202
5.10.201714:00-14:30Lukas Beckmann, M.Sc. Defense: Lane estimation with deep neural networksS02|02 E202
28.09.201714:00-14:30Simon-Konstantin Thiem, B.Sc. Final Presentation: Simulation of the underactuated Sake Robotics Gripper in V-REP and ROSS02|02 E202
28.09.201713:30-14:00Parvez Ahmad, M.Sc. Thesis Defense: Analysis of Financial Big Data using Machine Learning and Graph ProcessingS02|02 E202
21.09.201714:00-14:30Markus Semmler, B. Sc. Intermediate Presentation: Exploration In Deep Reinforcement LearningS02|02 E202
21.09.201713:30-14:00Claudia Lölkes, B. Sc. Final Presentation: Incremental Imitation Learning with Estimation of UncertaintyS02|02 E202
21.09.201713:00-13:30Janine Hölscher, M.Sc. Final Presentation: Interactive Planning Under UncertaintyS02|02 E202
14.09.201713:30-14:00Danny Dittmar, M. Sc. Intermediate Presentation: Distributed Reinforcement Learning with Neural Networks for RoboticsS02|02 E202
7.09.201713:00-14:00Oleg Arenz, Tutorial: An introduction to the iiwa platformS02|02 E202
4.09.201715:00-16:00Philip Becker-Ehmck, Research Talk: Variational Model-based EmpowermentS02|02 E202
31.08.201713:30-14:00Yannik Frisch: B.Sc. Intermediate PresentationS02|02 E202
24.08.201714:00-15:30Michael Lutter, Tutorial: Optimization for Deep LearningS02|02 E202
24.08.201713:30-14:00Okan Koc (Max-Planck Institute of Intelligent Systems), Research Talk: Online optimal trajectory generation for robot table tennisS02|02 E202
24.08.201713:00-13:30Robert Pinsler, M.Sc. Final Presentation: Data Efficient Learning of Robotics Grasps from PreferencesS02|02 E202
22.08.201714:00-15:00Sebastian Nowozin (MSR), Research Talk: Probabilistic Deep LearningS02-02, C110
17.08.201714:00-15:00Pascal Klink, Tutorial: RobcomS02|02 E202
17.08.201713:30-14:00Paavo Parmas (Okinawa Institute of Science and Technology Graduate University), Research Talk: Some discussion on policy search with differentiable modelsS02|02 E202
16.08.201713:00-13:45Jérôme Kirchhoff (SIM), Ph.D. Defense: Towards Dependability of Ultra Lightweight Tendon Driven Series Elastic RobotsS1-03, Room 07
15.08.201714:00-16:00Maziar Sharbafi (LL), Ph.D. Defense: Bioinspired template-based control of legged locomotionAlexanderstr. 10, Room 29
10.08.201715:00-16:00Eric Eaton (University of Pennsylvania), Research Talk: Efficient Lifelong Machine Learning: an Online Multi-Task Learning PerspectiveE302 or C110 if we are too many
10.08.201714:30-15:00Sebastian Szelag, B. Sc. Intermediate Presentation: Transferring Insights on Mental Training to Robot Motor Skill LearningS02|02 E202
4.08.201714:00-14:30Manuel Bied, M.Sc. Final Presentation: Learning Sequential Skills for Bi-manual Manipulation TasksE202
3.08.201714:00-15:00Rudolf Lioutikov, Tutorial: Introduction to Formal Grammars with details on using PCFGs for Movement Primitive sequencingS02|02 E202
3.08.201713:30-14:00Riad Akrour, Research Talk: Local Bayesian Optimization of Motor SkillsS02|02 E202
20.07.201714:30-15:00Parvez Ahmad, M.Sc. Intermediate Presentation: Analysis of Financial Big Data using Machine Learning and Graph ProcessingS02|02 E202
20.07.201714:00-14:30David Rother, B.Sc. Intermediate Presentation: Transferring Insights on Biological Sleep to Robot Motor Skill LearningS02|02 E202
20.07.201713:30-14:00Christian Weiland, B.Sc. Intermediate Presentation: Deep Reinforcement Learning by Propagating RewardsS02|02 E202
13.07.201714:30-15:30Guilherme Maeda, Research Talk: Active Incremental Learning of Robot MovementsS02|02 E202
13.07.201713:30-14:30Carlos Celemin (Univ. Chile), Research Talk: Interactive Learning of Continuous Actions from Corrective Advice Communicated by HumansS02|02 E202
7.07.201714:00-15:00Diego Agudelo-Espana (MPI-IS), Research Talk: Definition and Composition of Motor Primitives using Latent Force Models and Hidden Markov Models.E202
6.07.201714:00-14:30Nadine Weibrecht, M.Sc. Intermediate Presentation: Auswertung von Sensordaten mit Machine Learning AlgorithmenS02|02 E202
6.07.201713:30-14:00Claudia Lölkes, B. Sc. Intermediate Presentation: Incremental Imitation Learning with Estimation of UncertaintyS02|02 E202
29.06.201714:00-14:30Kaushik Gondaliya, M.Sc. Final Presentation: Learning to Categorize Issues in Distributed Bug Tracker SystemsS02|02 E202
27.06.201715:00-15:45Gerhard Neumann (Lincoln University), Research Talk: Information-Geometric Policy Search for Learning Versatile, Reusable SkillsGebäude S4|14, Raum 5.3.01, Mornewegstraße 32, 64293 Darmstadt
26.06.201716:30-18:30Alexandros Paraschos, Ph.D. Defense: Robot Skill Representation, Learning and Control with Probabilistic Movement PrimitivesC110
26.06.201714:00-15:30Sylvain Calinon (IDIAP), Research Talk: Robot learning from few demonstrations by exploiting the structure and geometry of dataS202 A103
22.06.201714:30-15:00Dorothea Koert, Research Talk: Trust Region Expectation Maximization for Efficient Learning of Forward and Inverse ModelsS02|02 E202
22.06.201714:00-14:30Lukas Beckmann, M.Sc. Intermediate Presentation: Lane estimation with deep neural networksS02|02 E202
22.06.201713:00-14:00Mikko Lauri (University of Hamburg), Research Talk: Active information gathering for mobile robotsS02|02 E202
21.06.201710:00-12:00Christian Wirth, Ph.D. Thesis Defense: Preference-based Reinforcement LearningA102
12.06.201714:00-15:00Miltos Allamanis (MSR), Research Talk: Learning from Big CodeS2|02 A126
1.06.201715:30-16:00Jiading Fang (UIUC), Research Talk: InfoGAN for Robotics?S02|02 E202
1.06.201715:00-15:30Simon Ramstedt, IP Final Presentation: Bayesian Deep Reinforcement LearningS02|02 E202
1.06.201714:00-15:00Samuele Tosatto, Research Talk: Boosted fitted Q-iterationS02|02 E202
1.06.201713:30-14:00Pavan Gadiya, M.Sc. Intermediate Presentation: Large Scale Real-Time Data Analytics Platform for Energy ExchangeS02|02 E202
31.05.201714:15-15:15Mauricio A. Alvarez (University of Sheffield), Research Talk: Sequential latent force models for segmenting motor primitivesS0202 A126
29.05.201715:00-16:00Armin Biess (Ben Gurion University): Space, time and human motion: Riemannian geometric approach to human arm dynamics, optimization and invarianceA313
23.05.201713:30-14:30Martin Riedmiller (Google Deepmind), Research Talk: Deep Reinforcement Learning for Learning MachinesS202 C205
18.05.201713:30-14:30Heinz Köppl (EE@TU Darmstadt), Research Talk: Learning from demonstrations, intentional and sub-intentional Bayesian methodsS02|02 E202
11.05.201713:30-14:30Filipe Veiga, Research Talk: Towards Dexterous Robotic In-Hand Manipulation through Tactile SensingS02|02 E202
4.05.201716:30-17:00Matej Zecevic,Bilal Hanun,Felix Kosterhon,Robin Hesse, BP Final Presentation, 3D Object Modelling and Recognition using a RGB-D cameraA102
27.04.201712:00-13:00Senka Krivic (Uni Innsbruck), Research Talk: Towards Adaptive Mobile ManipulationsA102
27.04.201711:30-12:00Daniel Tanneberg, Research Talk: Online Motion Planning and Learning with Stochastic Recurrent Neural NetworksA102
27.04.201711:00-11:30Hong Linh Thai, M.Sc. Intermediate Presentation: Guided Deep Learning for POMDPsA102
27.04.201710:30-11:00Sanket Shinde, M.Sc. Final Presentation: POMDPs with discrete and continuous observations for roboticsA102
20.04.201714:30-15:00Manuel Bied, B.Sc. Intermediate Presentation: Learning Sequential Skills for Bi-Manual Manipulation TasksS02|02 E202
20.04.201714:00-14:30Svenja Stark, Research Talk: Metrics for Skill ComparisonS02|02 E202
13.04.201713:30-14:30Boris Belousov, Research Talk: f-Divergence Constrained Policy SearchS02|02 E202
6.04.201714:00-15:00Marco Ewerton, Research Talk: Assisting the practice of motor skills by humans with a probability distribution over trajectoriesS202 E302
6.04.201713:30-14:00Idris Nematpur, B.Sc. Intermediate Presentation: Jointly Learning from Demonstrations and Preferences on Non-Linear SystemsS02|02 E202
5.04.201711:00-11:45Abbas Abdolmaleki, Research Talk: Robot learning with stochastic search -- challenges and solutionsS02|02 E202
30.03.201713:00-13:15Tobias Hammerschmidt, Schülerpraktikum Report: Controlling Sphero Robot with JavaScriptS02|02 E202
28.03.201711:00-12:00Wataru Takano (U. Tokyo), Research Talk: Motion Control and Language Generation from Stochastic SymbolsS02-02 A213
27.03.201713:30-17:00IP Final PresentationS202-A313
23.03.201715:30-16:00Yunsheng Huang, Research Talk: Linear Quadratic Tracking for Unknown Systems and Passivity Based ControlS02|02 E202
23.03.201715:00-15:30Moritz Nakatenus, M.Sc. Honors Thesis Progress Report: LSTM Networks for movement planning in humanoidsS02|02 E202
23.03.201714:30-15:00Simon Thiem, B.Sc. Intermediate Presentation: Deep Neural Networks for Controlling HumanoidsS02|02 E202
22.03.201711:00-12:00Moritz Grosse-Wentrup (MPI-IS), Research Talk: Neural Engineering : Restoring, Replacing, and Extending CognitionS02|02 E202
16.03.201713:30-14:00Harun Polat, B.Sc. Final Presentation: Wachsende Neuronale Netz zur BewegungskoordinationS02|02 E202
16.03.201713:00-13:30Janine Hölscher, M.Sc. Intermediate Presentation: Interactive Planning under UncertaintyS02|02 E202
3.03.201713:30-14:30Takayuki Osa, Research Talk: Robot learning for manipulation: Imitation, interaction, and reinforcement learningS02|02 E202
2.03.201713:30-14:00Julian Gao, M.Sc. Thesis Progress Report: Stochastic Optimal Control of Humanoid Robots in multi-contact environmentsS02|02 E202
2.03.201713:00-13:30Alexander Gabriel, M.Sc. Final Presentation: Empowered SkillsS02|02 E202
23.02.201713:30-14:00Kaushik Gondaliya, M.Sc. Intermediate Presentation: Learning to Categorize Issues in Distributed Bug Tracker SystemsS02|02 E202
23.02.201713:00-13:30Robert Pinsler, M.Sc. Intermediate Presentation: Data-Efficient Learning of Robotic Grasps from Human PreferencesS02|02 E202
21.02.201713:15-14:00Mohammad Shahbazi (IIT), Research Talk: Control of Dynamic Legged Locomotion Based on Spring-Mass ModelsRoom 29, Alexanderstraße 10 (S1/15)
14.02.201714:00-15:00Wolfram Burgard (Uni Freiburg), Research Talk: Deep Learning for Robot Navigation and PerceptionC120
2.02.201714:00-14:45Mohsen Kaboli (TU München), Research Talk: Whole Body Tactile Exploration with a Baby RobotS02|02 E202
2.02.201713:30-14:00Lena Plage, B.Sc. Final Presentation: Reinforcement Learning for tactile-based finger gaitingS02|02 E202
31.01.20179:30-10:30Juliane Euler (SIM), Ph.D. Defense: Optimal Cooperative Control of UAVs for Dynamic Data-Driven Monitoring TasksA102
27.01.201711:00-12:00Andreas Hock (Uni Toronto), Research Talk: Learning for Multi-Agent Systems - Distributed Iterative Learning ControlA313
26.01.201713:30-14:00Gregor Gebhardt, Research Talk: The Kernel Kalman RuleS02|02 E202
26.01.201713:00-13:30David Sharma, M.Sc. Final Presentation: Adaptive Training Strategies for BCIS02|02 E202
19.01.201713:30-14:30Jochen Triesch (FIAS), Research Talk: Self-calibrating Vision through Active Efficient CodingS02|02 E202
10.01.201714:00-15:00Angela Schöllig (U. Toronto), Research Talk: Safe Learning Control for Mobile RobotsS0202-E202
22.12.201614:30-15:00Felix Friske, M.Sc. Final Presentation: Learning to SampleS02|02 E202
22.12.201614:00-14:30Dorothea Koert, Research Talk: Towards Learning, Prediction and Control for Dexterous SkillsS02|02 E202
22.12.201613:30-14:00Daniel Tanneberg, Research Talk: Deep Spiking Networks for Model-based Planning in HumanoidsS02|02 E202
15.12.201614:30-15:00Lena Plage, B.Sc. Intermediate Presentation: Reinforcement Learning for tactile-based finger gaitingS02|02 E202
15.12.201614:00-14:30Sonja Hanek, B.Sc. Intermediate Presentation: Multi-Scale Latent Modelling of the HuMoD databaseS02|02 E202
15.12.201613:00-14:00Simone Parisi, Research Talk: Recent Advances on Multi-objective R LS02|02 E202
2.12.201615:00-16:00Steffen Leonhardt (RWTH Aachen), Research Talk: Closed-Loop Medical SystemsS3|06/052
1.12.201614:00-14:30Blank/Fiebig/Friess/Schultheis/Sharma/Viernickel, Cybathlon Project, BCI PipelineS202 E302
24.11.201614:30-15:00Daniel Palenicek, B.Sc. Final Presentation: Reinforcement Learning for Mobile Missile LaunchingS02|02 E202
24.11.201614:00-14:30Rene Schuster, M.Sc. Final Presentation: 3D Object Proposals from Stereo and Optical FlowB002
24.11.201613:00-14:00Oleg Arenz, Research Talk: Learning to Predict Grasp Quality from Human InteractionsS02|02 E202
17.11.201613:00-14:00Joni Pajarinen, Research Talk: Hybrid control trajectory optimization under uncertaintyS02|02 E202
10.11.201614:30-15:00Pascal Klink B.Sc Final Presentation: Model Learning with Probabilistic Movement PrimitivesS02|02 E202
10.11.201614:00-14:30Sanket Shinde, M.Sc. Intermediate Presentation: POMDPs with discrete and continuous observations for roboticsS02|02 E202
3.11.201613:15-13:45Karl-Heinz Fiebig, B.Sc. Final Presentation: Multi-Task Logistic Regression in Brain-Computer InterfacesS02|02 E202
3.11.201612:50-13:20Matthias Schultheis, B.Sc. Final Presentation: Learning Priors for Error-related Decoding in EEG data for Brain-Computer InterfacingS202 E302
3.11.201612:20-12:50Thomas Hesse, M.Sc. Final Presentation: Learning a Filter for Noise Attenuation in EEG Data for Brain-Computer InterfacesS02|02 E202
3.11.201612:00-12:20Mehmedovic/Lode/Speh/Haddoudi/Reuter (Cybathlon Project): BCI VisualizerS02|02 E202
1.11.201615:00-18:00Herke van Hoof, Ph.D. Thesis Defense: Exploration and Learning in Perception-rich RoboticsS202 A102
1.11.201610:30-11:30Prof. Marc Toussaint (Stuttgart University): Machine Learning and Modern AI Approaches to Robotics -- Learning and Reasoning in Logic, Geometric and Uncertain DomainsS0202-C120
27.10.201613:00-13:30Emmanuel Stapf, M.Sc. Thesis Final Presentation: Predicting Traffic Flows for Traffic Engineering in Software-Defined NetworksE 302
20.10.201613:00-13:30Philipp Becker, B.Sc. Thesis Final Presentation: Learning Deep Feature Spaces for Nonparametric InferenceS02|02 E202
6.10.201613:00-13:30Danny Driess (U. Stuttgart), Research Talk: Constrained Bayesian Optimization of Combined Interaction Force/Task Space Controllers for ManipulationsS02|02 E202
29.09.201613:00-15:00Integrated Project Final PresentationE302
22.09.201613:00-14:00Simon Manschitz, Research Talk: Probabilistic Decomposition of Sequential Force Interaction TasksS02|02 E202
8.09.201613:00-13:30Matthias Schultheis, B.Sc Intermediate Presentation: Learning Priors for Error-related Decoding in EEG data for Brain-Computer InterfacingS202 E302
29.08.201611:00-12:00Michael Lutter (Technische Universitaet Muenchen), Research Talk: Distance measures for view-invariant dynamic texture recognitionE302
25.08.201613:30-14:00Maximilian Hüttenrauch, M.Sc. Final Presentation: Guided Deep Reinforcement Learning for Robot SwarmsS02|02 E202
25.08.201613:00-13:30Valerian Marg, B.Sc Final Presentation: Reinforcement Learning for Manipulation TasksS02|02 E202
18.08.201615:30-16:30Roberto Calandra, Research Talk: Robust Multi-Objective OptimizationS02|02 E202
18.08.201615:00-15:30Lars Fritsche, Honor's Thesis Final Presentation: Learning to Walk on Rough TerrainS02|02 E202
11.08.201615:00-15:30Lukas Grossberger, B.Sc. Final Presentation: Towards a low-cost cognitive Brain-Computer Interface for Patients with Amyotrophic Lateral SclerosisS02|02 E202
11.08.201614:00-15:00Marco Ewerton, Research Talk: Bidirectional Human-Robot Learning: Imitation and Skill ImprovementS202 E302
11.08.201613:00-14:00Takayuki Osa, Research Talk: Learning Multiple Grasping Strategies and Its Application to Nuclear Sort and SegregationS02|02 E202
4.08.201615:30-16:00Rene Schuster, M.Sc. Intermediate Presentation: 3D Object Proposals from Stereo and Optical FlowB002
4.08.201615:00-15:30Thomas Hesse, M.Sc. Intermediate Presentation: Learning a Filter for Noise Attenuation in EEG Data for Brain-Computer InterfacesB002
4.08.201611:00-12:00Michael A Osborne (Oxford), Research Talk: Probabilistic numerics: treating numerical computation as learning, or; it's Bayes all the way downS02|02 E202
3.08.201615:00-18:00Roberto Calandra, Thesis Defense: Bayesian modeling for optimization and control in roboticsC110
28.07.201613:30-14:00Pascal Klink B.Sc Thesis Progress Report: Model Learning with Probabilistic Movement PrimitivesS02|02 E202
28.07.201613:00-13:30Daniel Wilbers, M.Sc. Final Presentation: Context-Driven Movement Primitive AdaptationS202 E302
27.07.201616:00-17:00Alexander Sproewitz (MPI-IS), Research Talk: Agile and Robust Legged Robot Locomotion using Bioinspired Design and Control PrimitivesS118/202 (Magdalenenstr)
21.07.201614:00-14:30Emmanuel Stapf, M.Sc. Thesis Progress Report: Learning to predict in sofware-defined networks (SDNs)S02|02 E202
21.07.201613:30-14:00Philipp Becker, B.Sc. Thesis Progress Report: Learning Deep Feature Spaces for Nonparametric InferenceS02|02 E202
7.07.201613:00-14:30Integrated Project Status UpdatesS02|02 E202
24.06.201616:00-17:00Kevin Luck, M.Sc. Final Presentation: Multi-Group Factor Extension of the GrouPS algorithm and Real-World Robot LearningS02|02 E202
23.06.201613:30-14:00Dorothea Koert, DGR Days Test Talk: Using Human Demonstrations and Trajectory Optimization for Generalizable Human-like Robot MotionsS02|02 E202
23.06.201613:00-13:30Max Hüttenrauch, M.Sc. Intermediate Presentation: Deep Reinforcement Learning for Robot SwarmsS02|02 E202
16.06.20169:30-10:30Klettersteig (50 + 20)S02|02 E202
9.06.201614:30-15:30Peter Englert (U Stuttgart), Research Talk: Combined Optimization and Reinforcement Learning for Manipulations SkillsS02|02 E202
9.06.201614:00-14:30Harun Polat, B.Sc Thesis Progress Report: Wachsende Neuronale Netz zur BewegungskoordinationS02|02 E202
9.06.201613:30-14:00David Sharma M.Sc. Thesis Progress Report: Adaptive Training Strategies for BCIS02|02 E202
2.06.201613:30-1:00Boris+Hany: Hannover Messe in 5min!S02|02 E202
25.05.201617:00-18:00Maurizio Filippone (Eurecom), Research Talk: Unbiased computations for tractable and scalable learning of Gaussian processesS02|02 E202
25.05.201616:30-17:00Viktor Pfanschilling, Honor's Thesis Intermediate Presentation: Genetic Programming with HaskellS02|02 E202
24.05.201611:00-12:00Jerry Lin (Taiwan Tech), Research Talk: Development of Intelligent and Autonomous Robots and SystemsS02|02 E202
23.05.201616:00-17:00Julia Vinogradska, Research Talk: Stability of Controllers for Gaussian Process Forward Models S02|02 E202
19.05.201614:00-14:30Moritz Nakatenus, B.Sc. Final Presentation: Multi-Agent Reinforcement Learning AlgorithmsS02|02 E202
19.05.201613:00-14:00Diego Romeres (Padua University), Research Talk: Analysis of Bayesian SI: point estimators, confidence sets, semi-parametric models and online settingS02|02 E202
12.05.201614:00-15:00Guilherme Maeda, Research Talk: Programming Robots using Human ObservationsS02|02 E202
12.05.201613:30-14:00Jannick Abbenseth, M.Sc. Final Presentation: Hierarchical Cooperative Path Planning for Service RobotsS02|02 E202
12.05.201613:00-13:30Valerian Marg, B.Sc. Intermediate Presentation: Reinforcement learning for manipulationS02|02 E202
28.04.201613:00-13:30Simon Ramstedt, B.Sc. Final Presentation: Deep Reinforcement Learning with Continuous ActionsS02|02 E202
25.04.201611:00-12:00Quan Zhou (Aalto University), Research Talk: Small robotic systems and microassemblyS02|02 E202
22.04.201614:00-17:00Chris Daniel, Thesis Defense: Learning Hierarchical Policies from Human RatingsC120
22.04.201611:00-12:00Chris Watkins (Royal Holloway), Research Talk: Probability models of evolutionS02|02 E202
21.04.201613:30-14:00Dorothea Koert, M.Sc. Final Presentation: Combining Human Demonstrations and Motion Planning for Movement Primitive OptimizationS02|02 E202
21.04.201613:15-1:00Lukas Grossberger, B.Sc. Intermediate Presentation: Towards a low-cost cognitive Brain-Computer Interface for Patients with Amyotrophic Lateral SclerosisS02|02 E202
21.04.201612:45-13:00Felix Unverzagt, B.Sc. Final Presentation: Modeling Robustness for Multi-Objective OptimizationS02|02 E202
14.04.20168:00-18:30Cognitive Science Workshop, Day 2Alten Hauptgebäude S01|03 R 23 Hochschulstr. 1
13.04.20168:00-23:00Cognitive Science Workshop, Day 1Vortragssaal der ULB S01 | 20 Untergeschoss | Magdalenenstraße 8
7.04.201613:45-14:30Introduction to the Robot Learning ToolboxS02|02 E202
7.04.201613:30-13:45Daniel Kauth and Alexander Hendrich, IP Presentation: Learning to Control a Robot Swarm with a FlashlightS02|02 E202
7.04.201613:00-13:30Moritz Nakatenus, B.Sc. Intermediate Presentation: Multi-Agent Reinforcement Learning AlgorithmsS02|02 E202
30.03.201614:00-14:30Alberto Romay (SIM), Thesis Defense: An Object Template Approach to Manipulation for Semi-Autonomous Avatar RobotsS02|02 E202
24.03.201613:00-13:15Daniel Wilbers, M.Sc. Intermediate Presentation: Context-driven Movement Primitive AdaptationS02|02 E202
17.03.201613:30-13:50Max Maag, IP Final Presentation: IRL of Flocking BehaviorS02|02 E202
17.03.201613:00-13:30Daniel Alte, B.Sc. Final presentation: Control of a robotic arm using a low cost BCIS202 E302
10.03.201613:30-14:00Hany Abdulsamad, M.Sc. Final presentation: Stochastic Optimal Control with Linearized DynamicsS02|02 E202
10.03.201613:00-13:30Riad Akrour, Research Talk: Model-free Trajectory OptimizationS02|02 E202
3.03.201613:30-14:30Voot Tangkaratt (Tokyo University), Research Talk: Sufficient Dimension Reduction for Transition Model EstimationS02|02 E202
3.03.201613:00-13:20Simon Ramstedt, B.Sc. Intermediate Presentation: Deep Reinforcement Learning with Continuous ActionsS02|02 E202
24.02.201614:00-15:00Gerhard Neumann, Current and Future Research Directions, Test TalkA 126
18.02.201614:00-14:30Jannick Abbenseth, M.Sc. Intermediate Presentation: Cooperative Path-Planning for Service RobotsS02|02 E202
18.02.201613:00-14:00Frank Hutter (Uni Freiburg), Research Talk: Advances in hyperparameter optimization of (deep) machine learning pipelinesS02|02 E202
11.02.201613:30-14:00Takayuki Osa, Research Talk: Learning Mutiple Grasp Types by Hierarchical Policy SearchS02|02 E202
11.02.201613:00-13:30Svenja Stark, M.Sc. Final Presentation: Learning Probabilistic Feedforward and Feedback Policies for Stable WalkingS02|02 E202
4.02.201613:00-14:00Vittorio Lippi (Uniklinik Freiburg), Research Talk: Neurorobotics and humanoidsA102
28.01.201614:30-15:30Joni Pajarinen, Research Talk: Planning Under Uncertainty: POMDPs\ , Decentralized POMDPs, Multi-Object ManipulationS02|02 E202
28.01.201614:00-14:30Dorothea Koert, M.Sc. Intermediate Presentation: Towards Natural Human Demonstration in Imitation LearningS202 E302
28.01.201613:00-14:00Danko Nikolić (MPI for Brain Research & FIAS), Research Talk: Strong-AI through AI-KindergartenS02|02 E202
21.01.201614:30-15:00Dieter Büchler, Research Talk: A Lightweight Robotic Arm with Pneumatic Muscles for Robot LearningS02|02 E202
21.01.201614:00-14:30Igor Achieser, M.Sc. Final Presentation: Potential evaluation of eye- and headtracking data as a robust and real-time capable predictor for driver intention detection and integration into an algorithm for maneuver predictionS202 E302
21.01.201613:30-14:00Guilherme Maeda, Research Talk: Learning Primitives from Human Observation - Applications to Comfortable InteractionS202 E302
14.01.201614:00-14:30Gregor Gebhardt, Talk: From Gauß to KalmanS02|02 E202
11.01.201614:30-15:30Hunter Bryant Gilbert (Vanderbilt University), Research Talk: Analysis and Design of Concentric Tube Robots as Needles and ManipulatorsS02|02 E202
7.01.201614:00-15:00Jan Kohlschuetter, M.Sc. Final Presentation: Learning Probabilistic Classifiers from Electromyography Data for Predicting Knee AbnormalitiesS02|02 E202
17.12.201514:00-14:20Hany Abdulsamad, M.Sc. Intermediate Presentation: Information-Theoretic Trajectory OptimizationA213
17.12.201513:40-14:00Alexander Gabriel, M.Sc. Intermediate Presentation: Empowerment for Learning Robot Table TennisA213
17.12.201513:20-13:40Felix Unverzagt, B.Sc. Intermediate Presentation: Modeling Robustness in Multi-Objective OptimizationA213
17.12.201513:00-13:20Igor Achieser, M.Sc. Intermediate Presentation: Potential evaluation of eye- and headtracking data as a robust and real-time capable predictor for driver intention detection and integration into an algorithm for maneuver predictionA213
10.12.201514:00-14:15Daniel Tanneberg, Talk: Towards finger gaiting for tactile-based in-hand manipulationS202 E302
10.12.201513:00-14:00Marco Ewerton, Research Talk: Incremental Imitation LearningS202 E302
20.11.201513:00-14:00Herke van Hoof, Test talk: Exploration in sensory rich environmentsA313
19.11.201513:00-13:30Andreas Wieland, M.Sc. Final Presentation: Probabilistic Methods for Electrical Load PredictionS02|02 E202
9.11.201513:30-15:00Michael Black (MPI Intelligent Systems), Research Talk: On Building Digital HumansS202 C205
5.11.201517:00-18:00Koh Hosoda (U.Osaka), Invited Talk: Understanding human's adaptive bipedal walking by using cadaver feet/ artificial muscular-skeletal hybrid robotAlexanderstr. 10, R29
5.11.201513:30-14:00Michael Novotny, M.Sc. Final Presentation: Autonomous EvasionS02|02 E202
5.11.201513:00-13:30Dominik Notz, Thomas Hesse, IP Final Presentation: Contact Location Navigation using Forward ModelsS02|02 E202
3.11.201514:00-14:30Boris Belousov, M.Sc. Thesis Intermediate PresentationS202 A126
3.11.201511:00-12:00Walter Kellermann (FAU Erlangen), Invited Talk: Recent Advances in Acoustic Signal Processing for Natural Human/Machine InterfacesS202 E302
29.10.201515:00-15:30Guilherme Maeda, Research Talk: Programing Robots for Human-Robot CollaborationS02|02 E202
29.10.201514:30-15:30Daniel Alte, B.Sc. Intermediate Presentation: Control of a robotic arm using a low budget BCIS02|02 E202
29.10.201513:45-14:30Oleg Arenz, Talk: Coolest stuff that I have learned at MLSS!S02|02 E202
22.10.201514:31-15:16Roberto Calandra, Talk: What I did at MicrosoftS02|02 E202
22.10.201514:15-14:30Sebastian Gomez, Self-IntroductionS02|02 E202
22.10.201514:00-14:15Jonas Klesy, IP Talk: Cybathlon 2016 - Status as of September 2015S02|02 E202
22.10.201513:30-14:00Felix End, B.Sc. Final Presentation: Learning Versatile Solutions with Policy SearchS02|02 E202
22.10.201513:00-13:30Felix Friske, M.Sc. Intermediate Presentation: Policy Search for Bayesian SamplingS02|02 E202
15.10.20159:30-10:30Constantin Diez (Opel AG), Talk: Wissensbasierte Robustheitsanalyse in der Strukturmechanik mittels Machine LearningS02|02 E202
15.10.20159:00-9:30Tjark Vandommele, M.Sc. Final Presentation: Development of an algorithm for visual detection of driver fatigueS02|02 E202
15.10.20158:30-9:00Christoph Mayer, B.Sc. Final Presentation, Learning to Sequence Movement Primitives for Rhythmic TasksS02|02 E202
8.10.201511:00-11:30IP Presentation: Johannes Geisler and Emmanuel Stapf, Coupling with Probabilistiic Movement PrimitivesS02|02 E202
29.09.201511:50-12:50BusyS02|02 E202
24.09.201510:30-11:00Christian Daniel, What I did at Microsoft!S02|02 E202
24.09.201510:00-10:30Daniel Tanneberg, M.Sc. Final Presentation: Spiking neural networks solve robot planning problemsS02|02 E202
17.09.201510:00-10:30Alexander Blank, B.Sc. Final Report: Learning a Game Agent's Behaviour based on Object DistributionsS02|02 E202
10.09.201510:30-11:00Kim Berninger, B.Sc. Final Report: Hierarchical Policy Search AlgorithmsS02|02 E202
10.09.201510:00-10:30Andras Kupcsik, Learning Dynamic Human-Robot Object Handover from Human Feedback.S02|02 E202
12.08.201514:00-15:00Filipe Veiga, Test Talk for JapanS02|02 E202
12.08.201513:00-14:00Gregor Gebhardt, Test Talk for JapanS02|02 E202
11.08.201515:00-15:30Rudolf Lioutikov, Research Talk: Learning Skill Libraries through Probabilistic SegmentationS02|02 E202
6.08.201511:00-11:30Oleg Arenz, Research Talk: IRL for Semi-Autonomous ControlS02|02 E202
6.08.201510:00-11:00Simone Parisi, Talk: Coolest stuff that I have learned at MLSS! (Convex Optimization)S02|02 E202
30.07.201510:00-11:00Marco Ewerton, Talk: Coolest stuff that I have learned at MLSS!S02|02 E202
23.07.201511:30-11:45Aayush Maloo. Research Talk: Towards a Predictive Collaborative AssemblyS02|02 E202
23.07.201511:00-11:30Matteo Pirotta. Research Talk: Inverse Reinforcement Learning through Policy Gradient MinimizationS02|02 E202
23.07.201510:15-11:00Alexandros Paraschos, Research Talk: Model-Free ProMPsS02|02 E202
10.07.201511:00-12:00Allan Max Axelrod (Oklahoma State University), Research Talk: Real -time Adaptive Prediction of Time-varying and Obscure RewardsE202
9.07.201510:00-11:00Guilherme Maeda, Research Talk: Addressing the Correspondence Problem with Inverse Kinematics and Motion PlanningS02|02 E202
3.07.201515:00-16:00Presentation ADP Project: Fox-2E302
3.07.201513:00-14:00Konstantinos Karydis (University of Delaware), Research Talk: Probabilistically-Valid Templates for Planning, Navigation, and Control under Uncertainty: Applications to Miniature Legged RobotsS202 A213
2.07.201517:55-18:25Roland Fleming (Justus-Liebig-Universität Gießen ), Invited Talk: Perception of 3D shape from orientation fieldsS1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201517:20-17:50Peter Battaglia (Google DeepMind), Invited TalkS1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201516:45-17:15Frank Jäkel (Universität Osnabrück), Invited Talk: Categorization in Man and MachineS1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201516:00-16:30Moritz Grosse-Wentrup (Max Planck Institute for Intelligent Systems ), Invited TalkS1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201515:25-15:55Jörg Conradt (Technische Universität München), Invited Talk: Computational Neuroscience in Technical ApplicationsS1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201514:50-15:20Kristian Kersting (Technische Universität Dortmund), Invited Talk: Statistical Relational Artificial IntelligenceS1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201514:05-14:35Angelika Lingnau (Royal Holloway), Invited Talk: Acting to understand – or the other way around?S1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201513:30-14:00Rainer Goebel (Maastricht University), Invited Talk: Cracking representational codes in the human brain: From basic research to clinical fMRI applicationsS1|20, Lecture Hall of ULB Campus Stadtmitte
2.07.201511:20-11:40Gregor Gebhardt, Research Talk: The Subspace Conditional OperatorS02|02 E202
2.07.201510:30-11:20Christian Wirth, Riad Akrour, Research Talk: Preference-based Reinforcement LearningS02|02 E202
2.07.201510:00-10:30Felix End, B. Sc. Intermediate Report: Hierarchical Policy Search for Table TennisS02|02 E202
30.06.201515:15-16:15Matt Zucker (Swarthmore College), Research Talk: Multigrid CHOMPS202 A313
25.06.201510:00-10:30Andreas Wieland, M.Sc. Intermediate Presentation: Probabilistic Methods for Forecasting Electronic Load ProfilesS02|02 E202
18.06.201510:30-11:00Alexander Blank, B. Sc. Intermediate Report: Learning a Game Agent 's Behaviour based on Object DistributionsS02|02 E202
18.06.201510:15-10:25Janine Hoelscher, Thomas Arnreich, IP Project Talk: Tactile MappingS02|02 E202
11.06.201515:00-16:00Tobias Springenberg, Research Talk: Towards Deep Representation Learning for ControlS202 A102
11.06.201510:00-11:00Takayuki Osa, Research Talk, Automation of Surgical RobotsS02|02 E202
28.05.201511:00-12:00Tina Liu, Research Talk: Humanoid Walking RobotsS02|02 E202
21.05.201512:00-14:00Oberseminar AuSyE302
21.05.201510:30-11:10Adrian Sosic, Research Talk: Inverse Reinforcement Learning in Swarm Systems.S02|02 E202
15.05.201516:30-17:30Marco Ewerton, Research Talk: Mixture of Interaction Primitives and Phase EstimationS202 E302
15.05.201510:30-11:00Oliver Kroemer, Test Talk: Towards Learning Hierarchical Skills for Multi-Phase Manipulation TasksS02|02 E202
8.05.201515:00-16:30Katharina Mülling, Research Talk: Autonomy Infused Teleoperation with Application to BCI ManipulationS02|02 E202
7.05.201510:30-11:00Tjark Vandommele, M.Sc. Intermediate Presentation: Development of an algorithm for visual detection of driver fatigueS02|02 E202
7.05.201510:00-10:30Simone Parisi, Research Talk: Reinforcement Learning vs Human Programming in Tetherball Robot GamesS02|02 E202
30.04.201511:00-12:00Herke van Hoof, Research Talk: Robot learning from vision and tactile sensingS02|02 E202
30.04.201510:00-11:00Dorothea Koert, Research Talk. Inverse Kinematics for Optimal Human-robot CollaborationS02|02 E202
23.04.201510:15-10:30Elmar Rueckert, Research Talk: Extracting Low-Dimensional Control Variables for Movement PrimitivesS02|02 E202
23.04.201510:00-10:15Daniel Tanneberg, M.Sc. Intermediate Presentation: Spiking Neural Networks Solve Robot Planning ProblemsS02|02 E202
16.04.201510:00-10:30Kai Steinert, M.Sc. Intermediate Presentation: Heteroscedastic Gaussian ProcessesS02|02 E202
9.04.201510:00-10:30Michael Novotny, M.Sc. Intermediate Presentation: Autonomous EvasionS02|02 E202
2.04.201511:15-12:00Matteo Pirotta, Research Talk: Reinforcement Learning - From Theory to AlgorithmsS02|02 E202
2.04.201510:30-11:15Christian Daniel, Research Talk: Learning Options from Action SequencesS02|02 E202
2.04.201510:00-10:30Sergej Alexeev, Demo: Mobile Robot Rocket LaunchingS02|02 E202
27.03.201515:00-16:00Antoine Cully, Research Talk: Practical questions for learning with Bayesian optimization in robotics and damage recoveryS02|02 E202
26.03.201510:45-11:10Christoph Mayer, B.Sc. Intermediate Presentation, Learning to Sequence Movement Primitives for Rhythmic TasksS02|02 E202
26.03.201510:00-10:45Roberto Calandra, Test TalkS02|02 E202
20.03.20159:00-18:00IP Final PresentationsS02|02 E202
19.03.20159:30-10:00Sergej Alexeev, B.Sc. Final Presentation: Mobile Robot Rocket LaunchingS02|02 E202
12.03.201510:30-11:30Tucker Hermans, Research Talk: Visual and Tactile Learning for Robot ManipulationS02|02 E202
5.03.201511:00-13:00Oberseminar AuSysE302
5.03.201510:20-11:00Zengkhun Yi, Research Talk on Tactile SensingS02|02 E202
5.03.201510:00-10:20Jan Kohlschütter, B.Sc. Progress Report: Probabilistic Muscle SynergiesS02|02 E202
19.02.201513:00-14:00Aviv Tamar, Research Talk: Risk sensitive reinforcement learningA102
19.02.201512:40-13:00Svenja Stark, M.Sc. Intermediate Presentation: Learning Probabilistic Models for LocomotionA102
5.02.201513:30-14:00Okan Koc, Research Talk: Optimizing Robot Striking Movement Primitives with Iterative Learning ControlA102
5.02.201513:00-13:30Andreas Schaefer, B.Sc. Final Presentation: Prediction of Finger Flexion from ECoG Data with a Deep Neural NetworkA102
29.01.201513:00-13:30Herke van Hoof, Research Talk: Learning non-parametric control policies with high-dimensional state featuresS02|02 E202
15.01.201513:30-14:00Elmar Ruckert: Hardware DemosS02|02 E202
15.01.201513:00-13:30Julius von Willich, B.Sc. Final Report, Reinforcement Learning for Heroes of NewarthS02|02 E202
8.01.201513:00-13:30Hardware presentation (Optoforce & BCI)S02|02 E202
18.12.201413:30-14:00Oleg Arenz, Msc Final Presentation: Feature Extraction for Inverse Reinforcement LearningS02|02 E202
18.12.201413:00-13:30Marco Ewerton, M.Sc. Final Presentation: Modeling Human-Robot Interaction with Probabilistic Movement RepresentationsS02|02 E202
16.12.201415:00-16:00Oliver Kroemer, Ph.D. Defense: Machine Learning for Robot Grasping and ManipulationS2 02|A102
16.12.201413:00-14:00Oliver Brock, Invited TalkA102
11.12.201413:20-14:00Alexander Stumpf, Introduction to the ROBOTIS THOR-MANGS202 E302
11.12.201413:00-13:10Kim Berninger, B.Sc. Progress Talk: Hierarchical PoliciesS02|02 E202
4.12.201413:00-13:30Janine Hoelscher, B.Sc. Final Thesis Presentation: Tactile Exploration of Material PropertiesS02|02 E202
13.11.201413:00-13:45Andreas Wenz, Research Talk, Prediction of driver’s intension using Motion-Tracking sensorsS02|02 E202
7.11.201413:30-14:15Guido Knips, Research Talk, Robotic Grasping Based on the Dynamic Field TheoryA 313
6.11.201413:20-13:50Guilherme Maeda, Research Talk, Interaction ProMPsS02|02 E202
6.11.201413:00-13:10Sergej Alexeev, B.Sc. Intermediate Presentation: Mobile Robot Rocket LaunchingS02|02 E202
30.10.201414:00-14:15Andreas Schaefer, B.Sc. Intermediate Presentation: Prediction of Finger Flexion from ECoG Data with a Deep Neural NetworkS02|02 E202
30.10.201413:30-13:50Max Mindt, M.Sc. Final Presentation: Probabilistic Inference for Movement Planning in HumanoidsS02|02 E202
30.10.201413:00-13:20Jan Mundo, M.Sc. Final Presentation: Structure Learning with Movement PrimitivesS02|02 E202
23.10.201413:00-13:30Dorothea Koert, Research Talk: Inverse Kinematics for Optimal Human-robot CollaborationS02|02 E202
16.10.201414:10-14:35Annemarie Mattmann, B.Sc. final report: Wie fangen Menschen Bälle?S02|02 E202
16.10.201413:55-14:10Christophe Labar, Research Update: Whole-body Control of iCub Using the Matlab InterfaceS02|02 E202
16.10.201413:30-13:50Marco Ewerton, M.Sc. Progress report: Modeling Human-Robot Interaction with Probabilistic Movement RepresentationsS02|02 E202
16.10.201413:00-13:25Simon Reinhardt, M.Sc. Final Presentation: Machine Learning for Active Gait Support with a Powered Ankle ProsthesisS02|02 E202
8.10.201411:45-12:05Peter Englert (Uni Stuttgart), Research Talk: Inverse KKT Motion OptimizationS02|02 E202
8.10.201411:15-11:45Mike Smyk, B.Sc. final report: Learning Generalizable Models for a Compliant Robot ManipulatorS02|02 E202
8.10.201410:45-11:15Niko Huhnstock, B.Sc. Final Report: Tactile sensing for manipulationS02|02 E202
10.09.201411:55-12:10Oliver Kroemer, IROS Practice Talk: Predicting Object Interactions from Contact DistributionsS02|02 E202
10.09.201411:25-11:55Oliver Kroemer, IROS Practice Talk: Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered EnvironmentsS02|02 E202
10.09.201410:45-11:25Tucker Hermans, IROS Practice Talk: Manipulation in ClutterS02|02 E202
3.09.201411:15-11:45Gregor Gebhardt, M.Sc. Final Report: Spectral Learning of HMMs of Robot ControlS02|02 E202
3.09.201410:30-11:00Melvin Laux, B.Sc. Final Report: Online Feature Learning for Reinforcement LearningS02|02 E202
2.09.201411:00-12:00Debora Clever, Yue Hu & Malin Schemshat, Research talk: Current research in the EU project Koroibot and ORB group in HeidelbergE202
27.08.201411:30-12:00Okan Koc, Learning to track trajectoriesS02|02 E202
27.08.201411:00-11:30Dieter Büchler: Overview past research, outlook PhDS02|02 E202
21.08.201414:00-16:00ICRA Internal Review Talks: Marco, Rudi, Max, Jan, RobertoA126
20.08.201411:15-11:45Janine Holscher B.Sc.: Progress Report: Tactile Exploration of Material PropertiesS02|02 E202
20.08.201410:45-11:15Bernhard Koch, B.Sc. Progress Report: Segmenting and Recognizing Demonstrated Manipulation TasksS02|02 E202
13.08.201411:00-11:30Johannes Ringwald, M.Sc Final Report, Combination of Movement PrimitivesS02|02 E202
13.08.201410:30-11:00Kevin Luck - Test Talk for IROSS02|02 E202
6.08.201411:45-12:00Demo: Playing Tetherball with compliant robotsS202 A016
6.08.201411:15-11:45ADP Final presentation: Playing Tetherball with compliant robotsS02|02 E202
30.07.201411:35-12:20Roberto Calandra, Research talk: Multi-Objective OptimizationS02|02 E202
30.07.201410:45-11:30Filipe Veiga, Research Talk: Learning to Detect Slip with Tactile SensingS02|02 E202
23.07.201411:15-11:45Stefan Zeiss, M.Sc. Final Presentation: Manipulation Skill for Robotic AssemblyS02|02 E202
23.07.201410:45-11:15Christian Merfels, M.Sc. Final Presentation: Large-scale probabilistic feature mapping and tracking for autonomous drivingS02|02 E202
16.07.201410:45-11:30Niko Huhnstock, B.Sc. Progress Report: Tactile sensing for manipulationS02|02 E202
9.07.201412:00-12:25Jan Mundo, M.Sc. Progress Report: Structure Learning for Movement PrimitivesS02|02 E202
9.07.201411:35-12:00Max Mindt, M.Sc. Progress Report: Probabilistic Inference for Movement Planning in HumanoidsS02|02 E202
9.07.201410:45-11:30Tucker Hermans, Ph.D. Research Talk: Learning Models for Sensor Space ControlS02|02 E202
8.07.201415:30-16:30Nathan Ratliff, kth-order Markov Optimization and Dual ExecutionA313
3.07.201416:00-16:30Sandra Amend, B.Sc. final talk: Feature Extraction for Policy SearchA213
2.07.201411:15-12:00Gerhard Neumann, Dr.-Ing. Research Talk, Information Theoretic Policy UpdatesS02|02 E202
2.07.201410:45-11:15Mike Smyk, B.Sc. Progress Report: Learning Generalizable Models for a Compliant Robot ManipulatorS02|02 E202
25.06.201411:30-12:15Simon Manschitz, Research Talk: Learning Attractor Goals from DemonstrationsS02|02 E202
25.06.201410:45-11:30Abbas Abdolmaleki, Research Talk: ZMP-based Policies - Overview and LearningS02|02 E202
18.06.201411:57-12:22Melvin Laux, B.Sc. Progress Report: Deep learning for Reinforcement LearningS02|02 E202
18.06.201411:11-11:56Guilherme Maeda: Creating collaborative and inverse dynamics models with a ProMP-based approachS02|02 E202
18.06.201410:45-11:10Aaron Hochländer, B.Sc. Final Presentation: Deep Learning for Reinforcement Learning in PACMANS02|02 E202
18.06.201410:00-10:45Rico Möckel, Guest Talk: Towards novel distributed smart technologies through inspiration by biologyS02|02 E202
11.06.201410:45-11:45Serena Ivaldi: Multimodal and social learning with a humanoid robotS02|02 E202
4.06.201411:15-11:45Simon Reinhardt, M.Sc. Progress Report: Machine Learning for Active Gait Support with a Powered Ankle ProsthesisS02|02 E202
4.06.201410:45-11:15Oleg Arenz, M.Sc. Progress Report: Learning Features for Inverse R LS02|02 E202
28.05.201413:30-15:00Martin Giese (University of Tübingen): Learning-based representation and analysis of complex body movementsMagdalenenstr. 27
28.05.201411:00-12:00Roberto Calandra, Test Talk: An Experimental Comparison of Bayesian Optimization for Bipedal LocomotionS02|02 E202
21.05.201410:45-11:15Oliver Kroemer, Research Talk: Learning to Predict Phases of Manipulation Tasks as Hidden StatesS02|02 E202
14.05.201411:30-11:45Yannick Schröcker, B.Sc. Final Report: Artificial Curiosity for Motor Skill LearningS02|02 E202
14.05.201410:45-11:45Christian Daniel, Research talk: Reward LearningS02|02 E202
7.05.201411:15-11:45Jean-Baptiste Mouret, Research Talk: Animal-like adaptation in machineS02|02 E202
7.05.201410:30-11:15Johannes Ringwald, M.Sc. Progress Report: Combining Movement PrimitivesS02|02 E202
30.04.201411:15-11:45Sascha Brandl, B.Sc. Final Presentation: Learning to Pour Using Warped FeaturesS02|02 E202
30.04.201410:45-11:15Viktor Kisner and Dimitar Ho. ADP Final Presetation: Trajectory Tracking Controller for a 4-DoF Flexible Joint Robot ArmS02|02 E202
28.04.201416:15-17:45Constantin Rothkopf: Visuomotor behavior in naturalistic tasks -- from receptive fields to value functionsS202 C110
28.04.201411:00-12:00Alberto Romay, Research Talk: An Integrated Concept for Control, Vision Based Learning, and Supervision of Robotic Manipulation TasksA313
23.04.201411:15-12:00Adrià Colomé Figueras, Research Talk: Lower dimensionality representation of movement primitives for learningS02|02 E202
23.04.201410:45-11:15Rudolf Lioutikov, Research Talk: Towards a 3rd Hand!S02|02 E202
16.04.201410:45-11:30Herke van Hoof, Research talk: Kernel embeddings of transition models for reinforcement learningS02|02 E202
9.04.201411:30-12:00Elmar Rueckert, Research Talk: Probabilistic Inference for Movement PlanningS02|02 E202
9.04.201410:45-11:30Christoph Dann, M.Sc. Final Presentation: Value function based reinforcement learning with temporal differencesS202 E302
19.03.201410:45-11:45Manuel Mühlig (Visitor), Research Talk: Receding Horizon Optimization of Robot Motions generated by Hierarchical Movement PrimitivesS02|02 E202
19.03.201410:00-10:45Jan Reubold, M.Sc. Final Presentation: 3D Object Reconstruction from Partial ViewE302
12.03.201411:15-11:45Sascha Brandl, B.Sc. Progress Report: Learning to Pour using Warped FeaturesS02|02 E202
12.03.201410:45-11:15Gregor Gebhardt, M.Sc. Progress Report: Spectral HMMs for Robot ControlS02|02 E202
12.03.201410:15-10:45Julius von Willich, B.Sc. Progress Report: Reinforcement Learning for Heros of NewerthS02|02 E202
10.03.201410:30-12:00Nick Hockings (Visitor), Research Talk: "Mechanisms of the human hand, and how to emulate them" and "Smoothed Particle SLAM for manipulation "S02|02 E202
5.03.201416:00-16:30Hong Linh Thai, B.Sc. Final Presentation: Laplacian Mesh Editing for Interaction LearningS02|02 E202
5.03.201415:30-16:00Kevin Luck, B.Sc. Final Presentation: Latent Space Reinforcement LearningS202 A313
28.02.201418:00-18:45Thomas Hesse, B.Sc. Final Presentation, Spectral Learning of HMMsS02|02 E202
19.02.201410:45-11:15Yevgen Chebotar, M.Sc. Thesis Final Report: Learning Robot Tactile Sensing for Object ManipulationS02|02 E202
12.02.201411:30-12:15Stefan Zeiss, M.Sc. Progress Report: Manipulation Skill for Robotic AssemblyS02|02 E202
12.02.201410:30-11:30Gerhard Neumann, Research TalkS202 E302
5.02.201411:15-12:15Simon Manschitz, M.Sc. Thesis Final Report: Learning sequential skills for robot manipulation tasksS02|02 E202
23.01.201417:00-18:00Bram Vanderborght: From stiff actuators over SEA, VSA to series-parallel elastic actuation: New concepts for compliant actuatorsS2|07/167
22.01.201410:45-11:45Marc Deisenroth, Research TalkS02|02 E202
22.01.201410:45-11:15Annemarie Mattmann, B.Sc. Progress Report: Modeling Human Ball Catching as Optimal ControlS202 E302
20.01.201416:30-17:30Sanket Kamthe, M.Sc. Final Presentation: Multi-modal Inference in Time SeriesS202 A213
15.01.201410:00-10:45Intermediate Projekt-Praktikum PresentationsS02|02 E202
18.12.201311:15-11:45Kevin Luck, B.Sc. Progress Report: Latent Space Reinforcement Learning - A Progess ReportS202 E302
18.12.201310:45-11:15</td><td align='right'>Aaron Hochländer, B.Sc. Progress Report: Reinforcement Learning for PacmanS02|02 E202
11.12.201310:45-11:45Christian Daniel, Research Talk: Learning Reward FunctionsS202 E302
10.12.20139:45-10:45Guilherme Maeda, Research Talk: Overview on Prior ResearchS202 A126
3.12.201310:00-11:00Torsten Felzer (Visitor), Research Talk: How Someone with a Neuromuscular Disease Experiences Operating a PC (and How to Successfully Counteract that)S02|02 E202
28.11.201315:10-17:10Ulf Brefeld, Research Talk: Structured Prediction ModelsD017
27.11.201310:45-11:45Roberto Calandra, Research Talk: Feature LearningS202 E302
20.11.201310:45-11:45Herke van Hoof, Research Talk: Predictive State Representations for RLS202 E302
13.11.201315:30-16:30Prof. Sven Dickinson (University of Toronto): Perceptual Grouping using SuperpixelsRoom 074 Fraunhofer IGD Fraunhofer-strasse 5, S3|05
13.11.201311:45-12:15Simon Manschitz, M.Sc. Thesis Progress Report: Learning sequential skills for robot manipulation tasksS202 E302
13.11.201311:15-11:45Yannick Schroecker, B.Sc. Progress Report: Artificial Curiosity for Motor Skill LearningS202 E302
13.11.201310:45-11:15Hong Linh Thai, B.Sc. Progress Report: Laplacian Mesh Editing for Interaction LearningS202 E302
6.11.201310:45-11:15Sebastian Schoengen, B.Sc. Final Presentation: Visual feature learning for interactive segmentationS202 E302
30.10.201311:15-12:15Filipe Veiga, Research Talk: Robotic Grasp Optimization from Contact Force AnalysisS202 E302
30.10.201310:45-11:15Dominik Notz, B.Sc. Final Presentation: Reinforcement learning for planning in high-dimensional domainsS202 E302
25.10.201311:00-12:00Prof. Martin Jagersand (University of Alberta, Canada): Improving robot arm/hand tele-operation through vision guided semi-autonomy and predictive displayS202 E202
23.10.201311:45-12:15Marco Ewerton, Test talk: Learning Responsive Robot Behavior by ImitationS202 E302
23.10.201311:15-11:45Thomas Hesse, B.Sc. Thesis Progress Report: Spectral Learning of Hidden Markov ModelsS202 E302
23.10.201310:45-11:15Sandra Amend, B.Sc Thesis Progress Report: Learning good Features for RLS202 E302
22.10.201312:00-12:20Rudolf Lioutikov, M.Sc. Final Presentation: Information Theoretic Stochastic Optimal ControlS202 A126
22.10.201311:30-11:50Yevgen Chebotar, M.Sc. Thesis Progress Report: Learning Robot Tactile Sensing for Object ManipulationS202 A126
7.10.201317:00-18:15Herke van Hoof, Test talk: Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered EnvironmentsS202 E302
7.10.201316:30-17:00Felix Schmitt, M.Sc. Final Presentation: Probabilistic Nonlinear Model Predictive Control based on Pontryagin's Minimum PrincipleS202 E302

Fall 2013/2014

DatePresenterTopicChair
7. Okt. at 4:30pmFelix SchmittM.Sc. Final Presentation: Probabilistic Nonlinear Model Predictive Control based on Pontryagin's Minimum Principle 
 Herke van HoofTest talk: Probabilistic Interactive Segmentation for Anthropomorphic Robots in Cluttered Environments 
22. Okt.Yevgen ChebotarM.Sc. Thesis Progress Report: Learning Robot Tactile Sensing for Object Manipulation 
 Rudolf LioutikovM.Sc. Final Presentation: Information-Theoretic Stochastic Optimal Control 
23. Okt.Sandra AmendB.Sc Thesis Progress Report: Learning good Features for RL 
 Thomas HesseB.Sc. Thesis Progress Report: Spectral Learning of Hidden Markov Models 
30. Okt.Dominik NotzB.Sc. Final Presentation: Reinforcement learning for planning in high-dimensional domains 
 Filipe VeigaRobotic Grasp Optimization from Contact Force Analysis 
6. Nov.Sebastian SchoengenB.Sc. Final Presentation: Visual feature learning for interactive segmentation 
13. Nov.Hong Linh ThaiB.Sc. Progress Report: Laplacian Mesh Editing for Interaction Learning 
 Yannick SchroeckerB.Sc. Progress Report: Artificial Curiosity for Motor Skill Learning 
 Simon ManschitzM.Sc. Thesis Progress Report: Learning sequential skills for robot manipulation tasks 
20. Nov.Roberto CalandraFeature Learning 
27. Nov.Herke van HoofPredictive State Representations for RL 
4. Dez.Kevin LuckB.Sc. Progress Report: Latent Space Reinforcement Learning - A Progess Report 
11. Dez.Christian DanielLearning Reward Functions 
18. Dez.   
15. Jan.Annemarie MattmannB.Sc. Progress Report: Modeling Human Ball Catching as Optimal Control 
20. Jan. at 4:30pmSanket KamtheM.Sc. Final Presentation: Multi-modal Inference in Time Series 
22. Jan.Jan ReuboldM.Sc Final Presentation: 3D Object Reconstruction from Partial Views 
29. Jan.Kevin LuckB.Sc. Final Presentation: Latent Space Reinforcement Learning 
29. Jan.AlexandrosParaschosTBA 
5. Feb.Gerhard NeumannTBA 
12. Feb.Christoph DannM.Sc. Final Presentation: Value function based reinforcement learning with temporal differences 

Summer 2013

DatePresenterTopicChair
3.Apr.C.Dann, M.Ackermann, T.PloetzProjektpraktikum Advanced Machine Learning: Final Presentation (Room A213)
 R. LioutikovM.Sc. Thesis Progress Report: Learning Time-Dependent Feedback Policies with Information-Theoretic Policy Search (Room A213)
17.Apr.cancelled due to GeRT Review
24.Apr.Brian PfretzschnerBSc Progress Report: Autonomous Car Driving using a Low-Cost On-Board Computer
 Christoph DannAn Exhaustive Search of Policy Evaluation Methods
 Nooshin HajiGhasemiMSc-Progress-Report: Approximate Inference in GPs with Periodic Kernels
8.Maicancelled due to ICRA 
15.MaiKatharina MuellingModeling Strategies in Table Tennis using Inverse Reinforcement Learning
22.MaiGerhard NeumannInformation Theoretic Stochastic Search
 Kevin Luck, Linh Hong, Rebecca SchierenHand Tracking using a Kinect Camera
29.MaiHeni Ben AmorInteraction PrimitivesChris
 Inna MikhailovaEnergy-based State-Feedback Control of Systems with Mechanical or Virtual Springs     
3. Jun.Dana KulicHuman Motion Analysis for Rehabilitation, Expressive Environments and RoboticsMarc
5. Jun.Oliver KroemerTea TalkAlex
12.Jun.Rudi LioutikovM.Sc. Thesis Progress Report: Learning Time-Dependent Feedback Policies with Information-Theoretic Policy SearchGeri
17.Jun.Nooshin HajiGhasemiMSc Final Presentation: Approximate Inference in GPs with Periodic KernelsHeni
 Felix SchmittMSc Progress Report: Probabilistic Nonlinear Model Predictive Control
19.Jun.Renaud DetryGeneralizing Task Parameters Through ModularizationOli
26.Jun.Sebastian SchoengenBSc Progress Report: Visual feature learning for interactive segmentationHerke
1.Jul.Andrej GamsGeneralization and adaptation of motor primitives for interaction with the environmentJan
3.Jul.Herke van HoofTentative: Bayesian Model Selection
 Oliver KroemerLearning to Grasp Through Experience and Object Generalization
10.Jul.Brian PfretzschnerBSc Final PresentationMarc
 Sanket KamtheMSc Progress Report: Multi-modal Inference in Time Series
 Katharina MuellingPhD Test Defense Presentation 
17.Jul.  Oli
24. Jul.Jan ReuboldMSc Progress Report: 3D Object Reconstruction from Partial ViewsHeni
31.Jul.Alexandros ParaschosProbabilistic Movement Primitives 
 Marco EwertonHMMs for Interaction Learning
7. Aug.Dominik NotzFactored Representations for Model Based Reinforcement Learning
21. Aug.Milind PanditImitation Learning: Goal prediction in Handwriting Completion

Fall 2012/13

DatePresenterTopic
19. Okt. 2012Peter EnglertMSc-Progress-Report: Model-based Behavioral Cloning
26. Okt. 2012Gergely NeuOnline Learning in Partially Non-Stationary Markov Decision Processes
2. Nov. 2012Zhikun WangModeling and Inferring Exogenous Variables for Human Movement Analysis 
9. Nov. 2012Herke van HoofInteractive object modelling and segmentation
16. Nov. 2012Canceled
23. Nov. 2012No Oberseminar due to Departmental Review
30. Nov. 2012Nakul GopalanMSc-Defense: Feeback-Error Learning of Motor Primitives
 David SharmaBSc-Final Report: Combining Feature Extraction and Reinforcement Learning
7. Dez. 2012Andras KupcsikData-Efficient Contextual Policy Search for Robot Movement Skills
14. Dez. 2012Heni Ben AmorTowards Algorithms for Learning Human-Robot Interaction by Imitation
21. Dez. 2012Timm MeyerBCI-based Rehabilitation
11. Jan. 2013Alexandros ParaschosProbabilistic Movement Primitives
18. Jan. 2013Bruno StrahStair climbing of a wheeled double inverted pendulum
25. Jan. 2013Oliver KroemerIntro to Humanoid Robot
1. Feb. 2013Philipp BeckerleModel-based Fault Diagnosis
8. Feb. 2013Roberto CalandraBayesian Optimization for Gait Optimization
15. Feb. 2013Peter EnglertFinal Presentation (MSc Thesis)

Summer 2012

DatePresenterTopic
13. Apr. 2012Nakul GopalanMSc-Progress-Report: Feeback-Error Learning of Motor Primitives
20. Apr. 2012Jens KoberPh.D. Thesis Defense Dry Run
27. Apr. 2012Gerhard NeumannInverse Relative Entropy Reinforcement Learning
 Martin DistlerBSc thesis defense (Abschlussvortrag): Koennen Lernalgorithmen interagieren wie im Gehirn?
4. Mai 2012Oliver KroemerA Kernel-based Approach to Direct Action Perception
 Andreas ZimpferBSc thesis defense (Abschlussvortrag): Learning to Shoot Rockets
11. Mai 2012Christian DanielMSc theses defense: Hierarchical Relative Entropy Policy Search - Robots playing Tetherball
 Roberto CalandraLearning from Generated Samples: Towards an Incremental Learning Approach for Deep Belief Networks
18. Mai 2012Alexandros ParaschosModel-Driven Behavior Specification for Robotic Teams
25. Mai 2012Philipp BeckerleA design methodology and basic technologies for user-friendly, active lower limb prostheses
1. Jun. 2012Paul HenschBSc thesis defense (Abschlussvortrag):
  Comparing Reinforcement Learning Algorithms on Tic-Tac-Toe
8. Jun. 2012Timm Meyercanceled
10. June 2012Michael Johanson, U. AlbertaAchieving Professional-Level Strength in Computer Poker
 David SharmaBSc-Progress Report
15. Jun. 2012Herke van HoofScene exploration using Maximally Informative Interactive Learning
22. Jun. 2012Andre SeyfarthBiomechanics and Neuromechanics of Legged Locomotion
 Marco EwertonScanning objects with the Kinect
26. June 2012Chris Watkins, Royal HollowaySex as Gibbs Sampling
29. Jun. 2012Gregory AthertonLearning Rhythmic Movements with Relative Entropy Policy Search
6. Jul. 2012Jackie SheltonSelect and Sample - A model of efficient neural inference and learning
13. Jul. 2012Philipp Hennigprobabilistic quasi-Newton methods
20. Jul. 2012Soeren HessBSc thesis defense (Abschlussvortrag): Levitation Sphere
20. July 2012Aaron DollarUnderstanding Human Hand Use to Motivate the Design of Low-Dimensional Mechanical Hands
27. Jul. 2012Michael GiengerRobot imitation learning of object movement skills
 Igor Mordatch (University of Washington)Discovery of Complex Behaviors through Contact-Invariant Optimization
10. Aug. 2012Marc DeisenrothExpectation Propagation in Dynamical Systems slides
16. Aug. 2012Zhou Jo Ziyun and Grayson BartletIREP Final presentation: Learning Models and Walking Gaits for a Compass Walker
  Behavioral Cloning for Video Games

Fall 2011/2012

DatePresenterTopic
26. Okt. 2011Herke van HoofAdaptive Visual Face Tracking for an Autonomous Robot
2. Nov. 2011Gerhard NeumannOn Movement Skill Learning and Movement Representations for Robotics Δ
9. Nov. 2011Christian DanielMSc-Progress-Report: Hierarchical Relative Entropy Policy Search - Robots playing Tetherball
16. Nov. 2011Abdeslam BoulariasLearning Robot Grasping with Structured Prediction Techniques
23. Nov. 2011Philipp HennigInformation Efficient Global Optimization
30. Nov. 2011Oliver KroemerA Non-Parametric Approach to Dynamic Programming
 Soeren HessBSc-Progress-Report: Levitation Sphere
7. Dez. 2011Zhikun WangLearning Anticipation Policies and Opponent Models in Motor Games
 Andreas ZimpferProgress-Report: Learning to Shoot Rockets
14. Dez. 2011Paolo Robuffo GiordanoBilateral Teleoperation of Multi-Robot Systems: Passivity,
Decentralization, and Connectivity Maintenance
21. Dez. 2011Heni Ben AmorLearning Motor- and Interaction Skills in Low-Dimensional Spaces
11. Jan. 2012Jens KoberReinforcement Learning of Motor Primitives for Robotics
 Martin DistlerBSc-Progress-Report: Koennen Lernalgorithmen interagieren wie im Gehirn?
18. Jan. 2012Moritz Grosse-WentrupBCIs and Robotics
 Sven ArnoldBSc-Progress-Report: Simulation of a Humanoid Robot
25. Jan. 2012Katharina MuellingBiomimetic and Learning Approaches to Robot Table Tennis
1. Feb. 2012Nikita KhakkamBSc-Progress-Report: Wie fangen Menschen Baelle?
 Paul HenschBSc-Progress-Report: Comparing Reinforcement Learning Algorithms on Tic-Tac-Toe
8. Feb. 2012Ruimin ZouMSc-Progress-Report (extern): Freiraumbestimmung auf Basis von Occupancy-Gridmaps
 Yanshu JiangResearch on Neural Networks Sliding Mode Control in the Robot Manipulators,
  Adverse Effects of Modern PWM Adjustable Speed Drive System
  and the Associated Countermeasures