CaltechAUTHORS
  A Caltech Library Service

GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning with End-to-End Learning

Rivière, Benjamin and Hönig, Wolfgang and Yue, Yisong and Chung, Soon-Jo (2020) GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning with End-to-End Learning. IEEE Robotics and Automation Letters, 5 (3). pp. 4249-4256. ISSN 2377-3766. https://resolver.caltech.edu/CaltechAUTHORS:20200514-141356088

[img] PDF - Submitted Version
See Usage Policy.

1720Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200514-141356088

Abstract

We present GLAS: Global-to- Local Autonomy Synthesis, a provably-safe, automated distributed policy generation for multi-robot motion planning. Our approach combines the advantage of centralized planning of avoiding local minima with the advantage of decentralized controllers of scalability and distributed computation. In particular, our synthesized policies only require relative state information of nearby neighbors and obstacles, and compute a provably-safe action. Our approach has three major components: i) we generate demonstration trajectories using a global planner and extract local observations from them, ii) we use deep imitation learning to learn a decentralized policy that can run efficiently online, and iii) we introduce a novel differentiable safety module to ensure collision-free operation, thereby allowing for end-to-end policy training. Our numerical experiments demonstrate that our policies have a 20% higher success rate than optimal reciprocal collision avoidance, ORCA, across a wide range of robot and obstacle densities. We demonstrate our method on an aerial swarm, executing the policy on low-end microcontrollers in real-time.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/lra.2020.2994035DOIArticle
https://arxiv.org/abs/2002.11807arXivDiscussion Paper
https://youtu.be/z9LjSfLfG6cRelated ItemVideo
https://github.com/bpriviere/glasRelated ItemCode
ORCID:
AuthorORCID
Rivière, Benjamin0000-0003-4189-4090
Hönig, Wolfgang0000-0002-0773-028X
Yue, Yisong0000-0001-9127-1989
Chung, Soon-Jo0000-0002-6657-3907
Additional Information:© 2020 IEEE. Manuscript received February 24, 2020; accepted April 20, 2020. Date of publicationMay 11, 2020; date of current version May 25, 2020. This letter was recommended for publication by Associate Editor M. Ani Hsieh and Editor N.Y. Chong upon evaluation of the reviewers’ comments. This work was supported by the Raytheon Company and Caltech/NASA Jet Propulsion Laboratory. Video: https://youtu.be/z9LjSfLfG6c. Code: https://github.com/bpriviere/glas.
Group:Center for Autonomous Systems and Technologies (CAST), GALCIT
Funders:
Funding AgencyGrant Number
Raytheon CompanyUNSPECIFIED
NASA/JPL/CaltechUNSPECIFIED
Subject Keywords:Distributed Robot Systems, Path Planning for Multiple Mobile Robots or Agents, Imitation Learning
Issue or Number:3
Record Number:CaltechAUTHORS:20200514-141356088
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200514-141356088
Official Citation:B. Rivière, W. Hönig, Y. Yue and S. Chung, "GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning With End-to-End Learning," in IEEE Robotics and Automation Letters, vol. 5, no. 3, pp. 4249-4256, July 2020, doi: 10.1109/LRA.2020.2994035.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:103207
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:14 May 2020 21:26
Last Modified:27 May 2020 17:21

Repository Staff Only: item control page