Learning-based Robust Motion Planning With Guaranteed Stability: A Contraction Theory Approach
- Creators
-
Tsukamoto, Hiroyasu
-
Chung, Soon-Jo
Abstract
This letter presents Learning-based Autonomous Guidance with RObustness and Stability guarantees (LAG-ROS), which provides machine learning-based nonlinear motion planners with formal robustness and stability guarantees, by designing a differential Lyapunov function using contraction theory. LAG-ROS utilizes a neural network to model a robust tracking controller independently of a target trajectory, for which we show that the Euclidean distance between the target and controlled trajectories is exponentially bounded linearly in the learning error, even under the existence of bounded external disturbances. We also present a convex optimization approach that minimizes the steady-state bound of the tracking error to construct the robust control law for neural network training. In numerical simulations, it is demonstrated that the proposed method indeed possesses superior properties of robustness and nonlinear stability resulting from contraction theory, whilst retaining the computational efficiency of existing learning-based motion planners.
Additional Information
© 2021 IEEE. Manuscript received February 24, 2021; accepted June 1, 2021. Date of publication June 21, 2021; date of current version July 6, 2021. This letter was recommended for publication by Associate Editor L. Peternel and Editor D. Kulic upon evaluation of the reviewers' comments. This work was supported by the Jet Propulsion Laboratory, California Institute of Technology, and benefited from discussions with J. Castillo-Rogez, M. D. Ingham, and J.-J. E. Slotine.Attached Files
Submitted - 2102.12668.pdf
Files
Name | Size | Download all |
---|---|---|
md5:fb519bf0a59d2ec94116011b94de9d93
|
1.2 MB | Preview Download |
Additional details
- Alternative title
- Imitation Learning for Robust and Safe Real-time Motion Planning: A Contraction Theory Approach
- Eprint ID
- 108308
- DOI
- 10.1109/LRA.2021.3091019
- Resolver ID
- CaltechAUTHORS:20210304-094303690
- JPL/Caltech
- Created
-
2021-03-04Created from EPrint's datestamp field
- Updated
-
2021-07-12Created from EPrint's last_modified field
- Caltech groups
- GALCIT