Interactive Dynamic Walking: Learning Gait Switching Policies With Generalization Guarantees
In this letter, we consider the problem of adapting a dynamically walking bipedal robot to follow a leading co-worker based on physical interaction. Our approach relies on switching among a family of Dynamic Movement Primitives (DMPs) as governed by a supervisor. We train the supervisor to orchestra...
Saved in:
Published in | IEEE robotics and automation letters Vol. 7; no. 2; pp. 4149 - 4156 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | In this letter, we consider the problem of adapting a dynamically walking bipedal robot to follow a leading co-worker based on physical interaction. Our approach relies on switching among a family of Dynamic Movement Primitives (DMPs) as governed by a supervisor. We train the supervisor to orchestrate the switching among the DMPs in order to adapt to the leader's intentions, which are only implicitly available in the form of interaction forces. The primary contribution of our approach is that it furnishes certificates of generalization to novel leader intentions for the trained supervisor. This is achieved by leveraging the Probably Approximately Correct (PAC)-Bayes bounds from generalization theory. We demonstrate the efficacy of our approach by training a neural-network supervisor to adapt the gait of a dynamically walking biped to a leading collaborator whose intended trajectory is not known explicitly. |
---|---|
ISSN: | 2377-3766 2377-3766 |
DOI: | 10.1109/LRA.2022.3147006 |