Autonomous Drifting Based on Maximal Safety Probability Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hoshino, Hikaru, Li, Jiaxing, Menon, Arnav, Dolan, John M., Nakahira, Yorie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909305953845248
author Hoshino, Hikaru
Li, Jiaxing
Menon, Arnav
Dolan, John M.
Nakahira, Yorie
author_facet Hoshino, Hikaru
Li, Jiaxing
Menon, Arnav
Dolan, John M.
Nakahira, Yorie
contents This paper proposes a novel learning-based framework for autonomous driving based on the concept of maximal safety probability. Efficient learning requires rewards that are informative of desirable/undesirable states, but such rewards are challenging to design manually due to the difficulty of differentiating better states among many safe states. On the other hand, learning policies that maximize safety probability does not require laborious reward shaping but is numerically challenging because the algorithms must optimize policies based on binary rewards sparse in time. Here, we show that physics-informed reinforcement learning can efficiently learn this form of maximally safe policy. Unlike existing drift control methods, our approach does not require a specific reference trajectory or complex reward shaping, and can learn safe behaviors only from sparse binary rewards. This is enabled by the use of the physics loss that plays an analogous role to reward shaping. The effectiveness of the proposed approach is demonstrated through lane keeping in a normal cornering scenario and safe drifting in a high-speed racing scenario.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03160
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Autonomous Drifting Based on Maximal Safety Probability Learning
Hoshino, Hikaru
Li, Jiaxing
Menon, Arnav
Dolan, John M.
Nakahira, Yorie
Robotics
Systems and Control
This paper proposes a novel learning-based framework for autonomous driving based on the concept of maximal safety probability. Efficient learning requires rewards that are informative of desirable/undesirable states, but such rewards are challenging to design manually due to the difficulty of differentiating better states among many safe states. On the other hand, learning policies that maximize safety probability does not require laborious reward shaping but is numerically challenging because the algorithms must optimize policies based on binary rewards sparse in time. Here, we show that physics-informed reinforcement learning can efficiently learn this form of maximally safe policy. Unlike existing drift control methods, our approach does not require a specific reference trajectory or complex reward shaping, and can learn safe behaviors only from sparse binary rewards. This is enabled by the use of the physics loss that plays an analogous role to reward shaping. The effectiveness of the proposed approach is demonstrated through lane keeping in a normal cornering scenario and safe drifting in a high-speed racing scenario.
title Autonomous Drifting Based on Maximal Safety Probability Learning
topic Robotics
Systems and Control
url https://arxiv.org/abs/2409.03160