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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Bin, Cao, Yaoguang, Wang, Yan, Wang, Rui, Shang, Jiachen, Feng, Xiejie, Lu, Jiayi, Shi, Jia, Yang, Shichun, Yan, Xiaoyu, Song, Ziying
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912752998547456
author Sun, Bin
Cao, Yaoguang
Wang, Yan
Wang, Rui
Shang, Jiachen
Feng, Xiejie
Lu, Jiayi
Shi, Jia
Yang, Shichun
Yan, Xiaoyu
Song, Ziying
author_facet Sun, Bin
Cao, Yaoguang
Wang, Yan
Wang, Rui
Shang, Jiachen
Feng, Xiejie
Lu, Jiayi
Shi, Jia
Yang, Shichun
Yan, Xiaoyu
Song, Ziying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04441
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving
Sun, Bin
Cao, Yaoguang
Wang, Yan
Wang, Rui
Shang, Jiachen
Feng, Xiejie
Lu, Jiayi
Shi, Jia
Yang, Shichun
Yan, Xiaoyu
Song, Ziying
Computer Vision and Pattern Recognition
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.
title MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.04441