RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts

arXiv:2609.36851 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-30

Code: https://github.com/OpenDriveLab/OpenScene

Terminology

• World Model — 50× in this paper · explained in 7 episodes
• Reinforcement Learning — 21× in this paper · explained in 4 episodes
• GRPO — 14× in this paper · explained in 6 episodes
• Ablation — 11× in this paper · explained in 1 episode
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Ablation Studies — 7× in this paper · explained in 1 episode
• Action-Vision Faithfulness Evaluator — 6× in this paper
• Fidelity — 6× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 4× in this paper
• Group Relative Policy Optimization — 4× in this paper
• Rectified Flow — 4× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 4× in this paper · explained in 25 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Average Displacement Error — 3× in this paper
• Sim-to-Real Gap — 3× in this paper · explained in 6 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Agent Interactions — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Causal Inference — 2× in this paper · explained in 4 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Group Relative Policy Optimization (GRPO) — 2× in this paper · explained in 5 episodes
• 3D Gaussian Splatting — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Action-Conditioned World Model — 1× in this paper · explained in 1 episode
• Active Perception — 1× in this paper · explained in 2 episodes
• Affordance — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Final Displacement Errors — 1× in this paper
• Gaussian Splatting — 1× in this paper · explained in 4 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Imitation Learning (IL) — 1× in this paper · explained in 2 episodes
• Latent Reasoning — 1× in this paper · explained in 2 episodes
• Latent World Models — 1× in this paper · explained in 2 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Proximal Policy Optimization — 1× in this paper
• Proximal Policy Optimization (PPO) — 1× in this paper · explained in 4 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Cosmos 3: Omnimodal World Models for Physical AI
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• End to End Learning for Self-Driving Cars
• RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
• RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
• World Models
• DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving
• AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
• Enhancing End-to-End Autonomous Driving with Latent World Model
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
• Generalized Trajectory Scoring for End-to-end Multimodal Planning
• Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving
• Latent Chain-of-Thought World Modeling for End-to-End Driving

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models