Uncertainty-aware learning of optimal controllers for human-robot collaboration

Check the IROS'19 paper Uncertainty-aware imitation learning using kernelized movement primitives for details.

Towards Safe and efficient controllers for human-robot interaction

From the paper An Uncertainty-Aware Minimal Intervention Control Strategy Learned from Demonstrations (IROS'18).

Probabilistic Learning of torque controllers

From the paper Probabilistic Learning of Torque Controllers from Kinematic and Force Constraints (IROS'18). See Publications.

Priority Learning for loco-manipulation

For details check the pre-print Learning Task Priorities from Demonstrations in the Publications section.

Learning Dual-arm priorities

For details check the pre-print Learning Task Priorities from Demonstrations in the Publications section.

cocktail-making humanoid robot

For details check the pre-print Learning Task Priorities from Demonstrations in the Publications section.

Bimanual sweeping

This work has been presented at IROS'15 (see the paper Learning bimanual end-effector poses from demonstrations using task-parameterized dynamical systems)