arXiv Machine Learning By Damiano Da Col, Maximilian Igl, Peter Karkus, Kashyap Chitta, Boris Ivanovic, Marco Pavone, Konrad Schindler, Christos Sakaridis

OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher

Read the original on arXiv Machine Learning →

OPTED is a method for on‑policy fine‑tuning of end‑to‑end driving models that separates reinforcement learning from the policy update. A privileged teacher trained with RL on vectorized inputs (HD‑maps and bounding boxes) supervises the pre‑trained student during closed‑loop post‑training. Applied to the camera‑based models TransFuser and VaVAM in AlpaSim, OPTED boosts driving scores by 1.6× and 9.5×, respectively, while requiring roughly three orders of magnitude fewer simulator interactions than direct RL post‑training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI
Aug 12

Threat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement Learning

arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.

By Xincong Hu (Nanjing University), Lei Ou (Nanjing University), Maosen Li (Yinwang Intelligent Technology Co., Ltd), Jingtao Zhang (Yinwang Intelligent Technology Co., Ltd), Liguo Hou (Yinwang Intelligent Technology Co., Ltd), Zongzhang Zhang (Nanjing University)
arXiv Machine Learning
1d ago

MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving

MILER is an end‑to‑end reinforcement learning framework that achieves zero‑shot sim‑to‑real transfer for autonomous driving in unstructured environments. It uses a custom semantic mid‑level representation (MLR) simulator for offline training, and during deployment it processes real camera and LiDAR data with BEVFusion to produce a compatible bird’s‑eye‑view representation. The policy’s actions are applied via a trajectory‑alignment strategy, allowing the system to drive 17.3 km on a 3.0 km test track without human intervention, all running on a Jetson AGX Orin.

By Thomas Steinecker, Denis Trescher, Alexander Bienemann, Thorsten Luettel, Mirko Maehlisch
arXiv Machine Learning
Jun 16

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

arXiv:2510. 12560v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving models trained with imitation learning (IL) often generalize poorly, particularly in long-tail scenarios where expert demonstrations are sparse.

By Xiaoji Zheng, Ziyuan Yang, Yanhao Chen, Yuhang Peng, Yuanrong Tang, Gengyuan Liu, Bokui Chen, Jiangtao Gong
arXiv AI
2d ago

Imitation Learning for Autonomous Driving in CARLA

The paper presents a compact multimodal policy trained via behavioral cloning to drive autonomously in the CARLA simulator. Using five‑frame histories of RGB images, LiDAR, telemetry, and lane waypoints, the 1.36‑million‑parameter model predicts throttle, brake, and steering at 20 Hz. Trained on 236,882 windows (≈3.3 hours of driving) from 448 captures, the policy drives for hours on both training and unseen routes without collisions, demonstrating qualitative transfer and recovery from large trajectory deviations.

By Jordy Kieto
arXiv AI
Sep 4

A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle

The paper introduces a low‑cost, open experimental platform for end‑to‑end autonomous driving on miniature Ackermann vehicles, combining a physical car, printed track, data collection tools, trajectory registration, and a Webots digital twin. It implements command‑conditioned behavior cloning, achieving a mean cross‑track error of 6.1 cm on the real vehicle and demonstrating the impact of camera field of view in simulation. Using synthetic data from the digital twin and a sim‑to‑real image translator, a higher‑capacity policy trained on both synthetic and real data completes all four track routes, outperforming the baseline trained only on real data.

By Gustavo Claudio Karl Couto, Eric Aislan Antonelo, Gabriel George Zipperer