Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving

• URL: http://arxiv.org/abs/2605.21139v2
• Date: Fri, 22 May 2026 01:55:27 GMT
• Title: Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
• Abstract summary: CoPhy is a CognitivePhysical reinforcement learning framework for autonomous driving.<n>We distill VLM knowledge into the BEV encoder, then discard the VLM entirely.<n>We build an auto-regressive BEV world model that explicitly predicts future semantic maps conditioned on candidate actions.
• Score: 32.98870275484187
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement learning offers a path to smarter autonomy, it demands two missing pieces of infrastructure: (1) a cognitive foundation that understands traffic semantics and driving intent, and (2) a foresighted physical environment that can anticipate the consequences of candidate actions. To this end, we propose CoPhy, a CognitivePhysical reinforcement learning framework for autonomous driving. To distill to think, we distill VLM knowledge into the BEV encoder and then discard the VLM entirely, retaining cognitive ability at zero inference cost while releasing the cognitive channel as a pluggable interface for optional human language commands. To foresee to act, we build an auto-regressive BEV world model that explicitly predicts future semantic maps conditioned on candidate actions, serving as an interpretable physical sandbox from which safety metrics are directly derived. Built upon this dual infrastructure, we optimize the driving policy via GRPO with a novel dual-reward mechanism: a physical reward derived from BEV rollouts enforces hard safety constraints, while a cognitive reward from a language-aligned scorer ensures intent compliance. Extensive experiments demonstrate that CoPhy not only achieves state-of-the-art results on NAVSIM v1 and v2 benchmarks, but also enables safer driving via cognitively informed scene compliance and flexible intent control through user-defined language instructions.

Related papers

• MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving [62.43744546817599]
  Vision-language--action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings.<n>We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model.<n> MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
  arXiv  Detail & Related papers  (2026-05-13T23:35:14Z)
• DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving [7.788062051923755]
  DriveVLM-RL is a neuroscience-inspired framework that integrates vision-language models into reinforcement learning.<n>The framework decomposes semantic reward learning into a Static Pathway for continuous spatial safety assessment.<n>A hierarchical reward synthesis mechanism fuses semantic signals with vehicle states, while an asynchronous training pipeline decouples expensive VLM inference from environment interaction.
  arXiv  Detail & Related papers  (2026-03-18T21:55:29Z)
• Large Multimodal Models for Embodied Intelligent Driving: The Next Frontier in Self-Driving? [68.82027978227008]
  This article introduces a novel semantics and policy dual-driven hybrid decision framework to tackle this challenge.<n>The framework merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning (DRL) for real-time policy optimization.<n>Case study is conducted experimentally to validate the performance superiority of our framework in completing lane-change planning task.
  arXiv  Detail & Related papers  (2026-01-13T11:05:12Z)
• Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future [125.92052530850425]
  Vision-Language-Action (VLA) frameworks integrate perception with language-grounded decision making.<n>VLA frameworks offer a pathway toward more interpretable, generalizable, and human-aligned driving policies.<n>This work aims to establish a coherent foundation for advancing human-compatible autonomous driving systems.
  arXiv  Detail & Related papers  (2025-12-18T16:57:44Z)
• MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning [51.20229133553804]
  Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL)<n>Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning.<n>We propose MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters.<n>By feeding trajectory-level rewards back into the reasoning space, MindDrive enables trial-and-error learning over a finite set of discrete linguistic driving decisions.
  arXiv  Detail & Related papers  (2025-12-15T18:31:32Z)
• Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving [55.13109926181247]
  We introduce ReflectDrive, a learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion.<n>Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient.<n>Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors.
  arXiv  Detail & Related papers  (2025-09-24T13:35:15Z)
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [49.07731497951963]
  ReCogDrive is a novel Reinforced Cognitive framework for end-to-end autonomous driving.<n>We introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers.<n>We then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner.
  arXiv  Detail & Related papers  (2025-06-09T03:14:04Z)
• A Language Agent for Autonomous Driving [31.359413767191608]
  We propose a paradigm shift to integrate human-like intelligence into autonomous driving systems. Our approach, termed Agent-Driver, transforms the traditional autonomous driving pipeline by introducing a versatile tool library. Powered by Large Language Models (LLMs), our Agent-Driver is endowed with intuitive common sense and robust reasoning capabilities.
  arXiv  Detail & Related papers  (2023-11-17T18:59:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.