Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
cs.CV, cs.LG
Submitted: 2026-05-20
Updated: 2026-11-10
Code: https://github.com/OpenDriveLab/OpenScene
Terminology
Sources
- NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- EMMA: End-to-End Multimodal Model for Autonomous Driving
- IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
- Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
- AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
- Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
- SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving
- UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
- Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
- X-Driver: Explainable Autonomous Driving with Vision-Language Models
- AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
- Representation Learning with Contrastive Predictive Coding
- Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
- Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
- WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
- AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models
- Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs