Reference-Free Formula Drift with Reinforcement Learning: From Driving Data to Tire Energy-Inspired, Real-World Policies
This addresses the challenge of real-time control for autonomous vehicles in adverse conditions, though it is incremental as it builds on existing reinforcement learning and simulation methods.
The paper tackles the problem of enabling autonomous cars to perform controlled drifting for enhanced safety and flexibility, achieving a tracking error as low as 10 cm and sideslip angles up to 63° in real-world tests.
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°.