TEAM

TEAM: A Parameter-Free Algorithm to Teach Collaborative Robots Motions from User Demonstrations

INFORMATION

Authors: Lorenzo Panchetti, Jianhao Zheng, Mohamed Bouri, Malcolm Mielle

Published in: Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics (ICINCO)

PDF, DOI, Code, cite

Learning from demonstrations (LfD) enables humans to easily teach collaborative robots (cobots) new motions that can be generalized to new task configurations without retraining. However, state-of-the-art LfD methods require manually tuning intrinsic parameters and have rarely been used in industrial contexts without experts.

Method

We propose a parameter-free LfD method based on probabilistic movement primitives, where parameters are determined using Jensen-Shannon divergence and Bayesian optimization, and users do not have to perform manual parameter tuning.

The cobot’s precision in reproducing learned motions, and its ease of teaching and use by non-expert users were evaluated in two field tests:

1. In the first field test, the cobot works on elevator door maintenance.
2. In the second test, three factory workers teach the cobot tasks useful for their daily workflow.

Results

Errors between the cobot and target joint angles are insignificant — at worst 0.28° — and the motion is accurately reproduced (GMCC score of 1).

Questionnaires completed by the workers highlighted the method’s ease of use and the accuracy of the reproduced motion.

What’s next

• Teaching by demonstration only scratches the surface of human-robot interaction in maintenance — see the Patents that came out of this line of work.
• Robustness to out-of-distribution gestures remains an open issue — the direction we took in UAC with uncertainty-aware calibration.