Saved in:
Bibliographic Details
Main Authors: Djeumou, Franck, Thompson, Michael, Suminaka, Makoto, Subosits, John
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.20990
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916457057615872
author Djeumou, Franck
Thompson, Michael
Suminaka, Makoto
Subosits, John
author_facet Djeumou, Franck
Thompson, Michael
Suminaka, Makoto
Subosits, John
contents The skill to drift a car--i.e., operate in a state of controlled oversteer like professional drivers--could give future autonomous cars maximum flexibility when they need to retain control in adverse conditions or avoid collisions. We investigate real-time drifting strategies that put the car where needed while bypassing expensive trajectory optimization. To this end, we design a reinforcement learning agent that builds on the concept of tire energy absorption to autonomously drift through changing and complex waypoint configurations while safely staying within track bounds. We achieve zero-shot deployment on the car by training the agent in a simulation environment built on top of a neural stochastic differential equation vehicle model learned from pre-collected driving data. Experiments on a Toyota GR Supra and Lexus LC 500 show that the agent is capable of drifting smoothly through varying waypoint configurations with tracking error as low as 10 cm while stably pushing the vehicles to sideslip angles of up to 63°.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reference-Free Formula Drift with Reinforcement Learning: From Driving Data to Tire Energy-Inspired, Real-World Policies
Djeumou, Franck
Thompson, Michael
Suminaka, Makoto
Subosits, John
Robotics
Machine Learning
Systems and Control
The skill to drift a car--i.e., operate in a state of controlled oversteer like professional drivers--could give future autonomous cars maximum flexibility when they need to retain control in adverse conditions or avoid collisions. We investigate real-time drifting strategies that put the car where needed while bypassing expensive trajectory optimization. To this end, we design a reinforcement learning agent that builds on the concept of tire energy absorption to autonomously drift through changing and complex waypoint configurations while safely staying within track bounds. We achieve zero-shot deployment on the car by training the agent in a simulation environment built on top of a neural stochastic differential equation vehicle model learned from pre-collected driving data. Experiments on a Toyota GR Supra and Lexus LC 500 show that the agent is capable of drifting smoothly through varying waypoint configurations with tracking error as low as 10 cm while stably pushing the vehicles to sideslip angles of up to 63°.
title Reference-Free Formula Drift with Reinforcement Learning: From Driving Data to Tire Energy-Inspired, Real-World Policies
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2410.20990