Bridging the Gap: Regularized Reinforcement Learning for Improved Classical Motion Planning with Safety Modules

Classical navigation planners can provide safe navigation, albeit often suboptimally and with hindered human norm compliance. ML-based, contemporary autonomous navigation algorithms can imitate more natural and humancompliant navigation, but usually require large and realistic datasets and do not al...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Goldsztejn, Elias, Brafman, Ronen I
Format: Article
Language:English
Subjects:
Algorithms
Autonomous navigation
Machine learning
Motion planning
Safety
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Classical navigation planners can provide safe navigation, albeit often suboptimally and with hindered human norm compliance. ML-based, contemporary autonomous navigation algorithms can imitate more natural and humancompliant navigation, but usually require large and realistic datasets and do not always provide safety guarantees. We present an approach that leverages a classical algorithm to guide reinforcement learning. This greatly improves the results and convergence rate of the underlying RL algorithm and requires no human-expert demonstrations to jump-start the process. Additionally, we incorporate a practical fallback system that can switch back to a classical planner to ensure safety. The outcome is a sample efficient ML approach for mobile navigation that builds on classical algorithms, improves them to ensure human compliance, and guarantees safety.
ISSN:2331-8422