CaltechAUTHORS
  A Caltech Library Service

Imitation Learning for Robust and Safe Real-time Motion Planning: A Contraction Theory Approach

Tsukamoto, Hiroyasu and Chung, Soon-Jo (2021) Imitation Learning for Robust and Safe Real-time Motion Planning: A Contraction Theory Approach. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20210304-094303690

[img] PDF - Submitted Version
See Usage Policy.

1187Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210304-094303690

Abstract

This paper presents Learning-based Autonomous Guidance with Robustness, Optimality, and Safety guarantees (LAG-ROS), a real-time robust motion planning algorithm for safety-critical nonlinear systems perturbed by bounded disturbances. The LAG-ROS method consists of three phases: 1) Control Lyapunov Function (CLF) construction via contraction theory; 2) imitation learning of the CLF-based robust feedback motion planner; and 3) its real-time and decentralized implementation with a learning-based model predictive safety filter. For the CLF, we exploit a neural-network-based method of Neural Contraction Metrics (NCMs), which provides a differential Lyapunov function to minimize an upper bound of the steady-state Euclidean distance between perturbed and unperturbed system trajectories. The NCM ensures the perturbed state to stay in bounded error tubes around given desired trajectories, where we sample training data for imitation learning of the NCM-CLF-based robust centralized motion planner. Using local observations in training also enables its decentralized implementation. Simulation results for perturbed nonlinear systems show that the LAG-ROS achieves higher control performance and task success rate with faster execution speed for real-time computation, when compared with the existing real-time robust MPC and learning-based feedforward motion planners.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2102.12668arXivDiscussion Paper
ORCID:
AuthorORCID
Chung, Soon-Jo0000-0002-6657-3907
Additional Information:This work was funded by the Jet Propulsion Laboratory, California Institute of Technology, and benefited from discussions with Julie Castillo-Rogez, Michel D. Ingham, and Jean-Jacques E. Slotine.
Group:GALCIT
Funders:
Funding AgencyGrant Number
JPL/CaltechUNSPECIFIED
Subject Keywords:Terms—Machine Learning for Robot Control, Robust/ Adaptive Control, Optimization and Optimal Control
Record Number:CaltechAUTHORS:20210304-094303690
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210304-094303690
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108308
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:04 Mar 2021 21:35
Last Modified:04 Mar 2021 21:35

Repository Staff Only: item control page