Conference: | Humanoids 2014 |
Location: | Madrid, Spain |
Date: | November 18th, 2014 |
Organizers: | Johannes Kulick, Herke van Hoof, Marc Toussaint, Jan Peters |
Robotics has achieved tremendous results: Robots can drive cars, precisely build goods at industrial scale, and perform surgery. The design of agents that can learn such complex skills by themselves is still in its infancy. One bottleneck is the lack of labeled data. Datasets are often limited in size and coverage, since they need experiments on robots or expensive simulations. Thus an important capability of every robot in complex environments is to gather new data.
To do this efficiently, intelligent robots need to be able to identify which task-relevant information is still missing. Only this ability enables agents to actively work towards a better understanding of the environment, the agent's state, and the task at hand, which will eventually lead to better performance.
Active learning is an approach to gain this ability. Within this paradigm the agent chooses the next datapoint to achieve the best learning result with as few data points as possible. Such strategies can shorten the process of data gathering significantly and also lead to the important information more quickly. In robotics, active learning approaches can be applied on various levels, from low-level tasks such as motor control learning to higher level reasoning tasks.
In this workshop, we want to discuss the state of the art of active learning in robotics, but also address important questions that are still open. The topics discussed in this workshop include (but are not limited to):
The workshop is intended for all scientists conducting research in robotics or machine learning facing the problem of little data in robotics and those interested in exploration strategies for robots in novel situations.
We are happy to announce the following speakers have confirmed their participation in the workshop:
The following contributed posters were accepted:
The tentative workshop schedule is as follows:
09:00 - 09:10 | Opening |
09:10 - 09:45 | Jivko Sinapov: Grounding Object Concepts in Exploratory Behaviors |
09:45 - 10:15 | Contributed paper spotlights |
10:15 - 10:50 | Clement Moulin-Frier: Exploration strategies in Developmental Robotics: a unified framework |
10:50 - 11:15 | Interactive session |
11:15 - 11:40 | Coffee break |
11:40 - 12:15 | Ruben Martinez-Cantin: Bayesian optimization for active policy search |
12:15 - 12:50 | Andreas Krause: Active learning for decision making |
12:50 - 13:00 | Conclusion |
The workshop receives funding from the DFG (German Science Foundation) within the priority programm "Autonomous Learning" (SPP 1527). The workshop organizers acknowledge support from the European Community’s Seventh Framework Programmes (FP7-ICT-2013-10) under grant agreement 610878 (3rdHand), 610967 (TACMAN), and 270327 (CompLACS).