paper-with-me

홈 › Papers

MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving

2025-12-04 · Bin Sun, Yaoguang Cao, Yan Wang, Rui Wang, Jiachen Shang, Xiejie Feng, Jiayi Lu, Jia Shi, Shichun Yang, Xiaoyu Yan, Ziying Song arxiv

End-to-End autonomous driving (E2E-AD) has emerged as a new paradigm, where trajectory planning plays a crucial role. Existing studies mainly follow two directions: trajectory generation oriented, which focuses on producing high-quality trajectories with simple decision mechanisms, and trajectory selection oriented, which performs multi-dimensional evaluation to select the best trajectory yet lacks sufficient generative capability. In this work, we propose MindDrive, a harmonized framework that integrates high-quality trajectory generation with comprehensive decision reasoning. It establishes a structured reasoning paradigm of "context simulation - candidate generation - multi-objective trade-off". In particular, the proposed Future-aware Trajectory Generator (FaTG), based on a World Action Model (WaM), performs ego-conditioned "what-if" simulations to predict potential future scenes and generate foresighted trajectory candidates. Building upon this, the VLM-oriented Evaluator (VLoE) leverages the reasoning capability of a large vision-language model to conduct multi-objective evaluations across safety, comfort, and efficiency dimensions, leading to reasoned and human-aligned decision making. Extensive experiments on the NAVSIM-v1 and NAVSIM-v2 benchmarks demonstrate that MindDrive achieves state-of-the-art performance across multi-dimensional driving metrics, significantly enhancing safety, compliance, and generalization. This work provides a promising path toward interpretable and cognitively guided autonomous driving.

📄 PDF Abstract BibTeX arXiv:2512.04441

Code (0)

등록된 구현이 없습니다.

Tasks

Trajectory PlanningAutonomous DrivingDecision Making

Similar Papers 제목 키워드 기반

MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving

2026-02-25 · Lingjun Zhang, Yujian Yuan, Changjie Wu, Xinyuan Chang 외 arxiv

Vision-Language Models (VLM) exhibit strong reasoning capabilities, showing promise for end-to-end autonomous driving systems. Chain-of-Thought (CoT), as VLM's widely used reasoning strategy, is facing critical challenge…

Multimodal ReasoningTrajectory PlanningAutonomous Driving

MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning

2025-12-15 · Haoyu Fu, Diankun Zhang, Zongchuang Zhao, Jianfeng Cui 외 arxiv

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement L…

Reinforcement LearningAutonomous Driving

VLA-R: Vision-Language Action Retrieval toward Open-World End-to-End Autonomous Driving

2025-11-16 · Hyunki Seong, Seongwoo Moon, Hojin Ahn, Jehun Kang 외 arxiv

Exploring open-world situations in an end-to-end manner is a promising yet challenging task due to the need for strong generalization capabilities. In particular, end-to-end autonomous driving in unstructured outdoor env…

Contrastive LearningAutonomous Driving

Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation

2018-03-21 · ECCV 2018 9 · Xin Wang, Wenhan Xiong, Hongmin Wang, William Yang Wang

Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not cons…

Deep Reinforcement LearningmodelModel-based Reinforcement Learningreinforcement-learning+5

Text-to-Decision Agent: Learning Generalist Policies from Natural Language Supervision

2025-04-21 · Shilin Zhang, Zican Hu, Wenhao Wu, Xinyi Xie 외

RL systems usually tackle generalization by inferring task beliefs from high-quality samples or warmup explorations. The restricted form limits their generality and usability since these supervision signals are expensive…

MuJoCoZero-shot Generalization