Quick Info

Research Interests

Reinforcement Learning; Task and Motion Planning; Riemannian Manifolds

Studies

M.Sc. Information Technology, University of Stuttgart (2019 - 2021) B.Eng. Electrical Engineering and Information Technology, Frankfurt University of Applied Sciences (2016 - 2019)

Links

Google Scholar LinkedIn

Contact Information

work(lab) +49-171-944-0393

An Thai Le joined the Intelligent Autonomous Systems group as an external Ph.D. student in collaboration with the Bosch Center for Artificial Intelligence (BCAI), working on Task and Motion Planning & Learning for robotics manipulations.

Before starting his Ph.D., he did a research internship at BCAI, where he developed a Learning from Demonstration approach to encode multi-modal demonstrations, consisting of pose trajectories and force & torque readings, conditioned operation scene. This work enables fast skill learning while capturing skill dynamics for compliance, which is important in industrial processes such as assembly.

Then, he joined the Human to Robot Motion lab at the University of Stuttgart in November 2020, where he worked on the Logic-Geometric Programming methods to tackle the problem of human-robot coordination in sequences of manipulation tasks. Planning methods for understanding human intention are the small steps towards natural interactions between humans and robots in the near future.

During his MSc research, An worked under the supervision of Dr. Jim Mainprice, and Dr. Meng Guo focusing particularly on Robot Skill Learning and Task & Motion Planning. His research goal is to contribute to the physical "intelligence" of the robotics system.

Key references

  • "An T. Le, et al. Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations." IROS (2021). Submitted.
  • "An T. Le, et al. Hierarchical Human-Motion Prediction and Logic-Geometric Programming for Minimal Interference Human-Robot Tasks." RO-MAN (2021). Submitted.

Other Activities

  

zum Seitenanfang