An Thai Le

An Thai Le joined the Intelligent Autonomous System lab on November 1st, 2021, as a Ph.D. student. He is currently working on applying Optimal Transport methods for the correspondence problem of imitation learning and also for motion generation problems.

Before his Ph.D., An Thai Le has worked on motion optimization and reactive motion generation methods applied in robotics manipulation and human-robot collaboration settings. His thesis entitled Learning Task-Parameterized Riemannian Motion Policies ( Code link) was written under the supervision of Dr. Jim Mainprice from Universitaet Stuttgart and Dr. Meng Guo from BCAI. The thesis aims to learn movement primitives that are context-dependent for adaptation under different task conditions and composable with other behavior skills such as collision avoidance.

Key References

Learning for Motion Planning

1. Urain, J.; Le, A.T.; Lambert, A.; Chalvatzaki, G.; Boots, B.; Peters, J. (2022). Learning Implicit Priors for Motion Optimization, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   Download Article [PDF]   BibTeX Reference [BibTex] Website

Forceful Imitation Learning

1. Le, A.T.; Guo M.; Duijkeren, N.; Rozo, L.; Krug, R.; Kupcsik, A.G.; Bürger M. (2021). Learning forceful manipulation skills from multi-modal human demonstrations, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   Download Article [PDF]   BibTeX Reference [BibTex] Video

Human-Robot Collaboration

1. Le, A.T.; Kratzer, P.; Hagenmayer, S.; Toussaint, M.; Mainprice, J. (2021). Hierarchical Human-Motion Prediction and Logic-Geometric Programming for Minimal Interference Human-Robot Tasks, 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN).   Download Article [PDF]   BibTeX Reference [BibTex] Video