English

Adaptive Control in Autonomous Driving via Real-Time Recurrent RL

Robotics 2026-05-19 v4 Machine Learning Neural and Evolutionary Computing Systems and Control Systems and Control

Abstract

We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without backpropagation through time. We extend RTRRL to support LrcSSM, a recently proposed nonlinear diagonal state-space model, and combine offline behavioral cloning with online RTRRL fine-tuning to adapt policies to distribution shifts at deployment. We validate the approach in the CarRacing simulation and on a 1:10-scale RoboRacer platform equipped with an event camera, where a pretrained policy is fine-tuned online during real-world line-following. To our knowledge, this is the first demonstration of online RL fine-tuning with event-camera observations on standard (non-spiking) hardware in closed-loop control. LrcSSM-based policies improve fastest and most consistently across both settings.

Keywords

Cite

@article{arxiv.2602.02236,
  title  = {Adaptive Control in Autonomous Driving via Real-Time Recurrent RL},
  author = {Julian Lemmel and Felix Resch and Mónika Farsang and Ramin Hasani and Daniela Rus and Radu Grosu},
  journal= {arXiv preprint arXiv:2602.02236},
  year   = {2026}
}
R2 v1 2026-07-01T09:32:07.214Z