Latent Chain-of-Thought World Modeling for End-to-End Driving
Recent Vision-Language-Action (VLA) models for autonomous driving explore inference-time reasoning as a way to improve driving performance and safety in challenging scenarios. Most prior work uses natural language to express chain-of-thought (CoT) reasoning before producing driving actions. However, text may not be the most efficient representation for reasoning. In this work, we present Latent-CoT-Drive (LCDrive): a model that expresses CoT in a latent language that captures possible outcomes of the driving actions being considered. Our approach unifies CoT reasoning and decision making by representing both in an action-aligned latent space. Instead of natural language, the model reasons by interleaving (1) action-proposal tokens, which use the same vocabulary as the model's output actions; and (2) world model tokens, which are grounded in a learned latent world model and express future outcomes of these actions. We cold start latent CoT by supervising the model's action proposals and world model tokens based on ground-truth future rollouts of the scene. We then post-train with closed-loop reinforcement learning to strengthen reasoning capabilities. On a large-scale end-to-end driving benchmark, LCDrive achieves faster inference, better trajectory quality, and larger improvements from interactive reinforcement learning compared to both non-reasoning and text-reasoning baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningAutonomous DrivingDecision MakingSimilar Papers 제목 키워드 기반
FutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model
In autonomous driving, end-to-end planners learn scene representations from raw sensor data and utilize them to generate a motion plan or control actions. However, exclusive reliance on the current scene for motion plann…
Autonomous DrivingMotion PlanningDriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving
End-to-end driving has made significant progress in recent years, demonstrating benefits such as system simplicity and competitive driving performance under both open-loop and closed-loop settings. Nevertheless, the lack…
CARLA Leaderboard 2.0Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning
The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in aligning model behavior with task objectives. Existing reasoning chai…
Reinforcement LearningDRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests
Large vision-language models (LVLMs) augment language models with visual understanding, enabling multimodal reasoning. However, due to the modality gap between textual and visual data, they often face significant challen…
Multimodal ReasoningMultiple-choiceVisual ReasoningPonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space
The remarkable success of Chain-of-Thought (CoT), which enhances performance by scaling generation steps at test-time, inspires us to ask: can we leverage a similar scaling of computational steps during pretraining to im…