paper-with-me

홈 › Papers

Generative Planning with 3D-vision Language Pre-training for End-to-End Autonomous Driving

2025-01-15 · Tengpeng Li, Hanli Wang, Xianfei Li, Wenlong Liao, Tao He, Pai Peng

Autonomous driving is a challenging task that requires perceiving and understanding the surrounding environment for safe trajectory planning. While existing vision-based end-to-end models have achieved promising results, these methods are still facing the challenges of vision understanding, decision reasoning and scene generalization. To solve these issues, a generative planning with 3D-vision language pre-training model named GPVL is proposed for end-to-end autonomous driving. The proposed paradigm has two significant aspects. On one hand, a 3D-vision language pre-training module is designed to bridge the gap between visual perception and linguistic understanding in the bird's eye view. On the other hand, a cross-modal language model is introduced to generate holistic driving decisions and fine-grained trajectories with perception and navigation information in an auto-regressive manner. Experiments on the challenging nuScenes dataset demonstrate that the proposed scheme achieves excellent performances compared with state-of-the-art methods. Besides, the proposed GPVL presents strong generalization ability and real-time potential when handling high-level commands in various scenarios. It is believed that the effective, robust and efficient performance of GPVL is crucial for the practical application of future autonomous driving systems. Code is available at https://github.com/ltp1995/GPVL

📄 PDF Abstract BibTeX arXiv:2501.08861

Code (1)

ltp1995/gpvl 공식 구현 pytorch

Tasks

Autonomous DrivingTrajectory Planning

Similar Papers 제목 키워드 기반

Generative Scenario Rollouts for End-to-End Autonomous Driving

2026-01-16 · Rajeev Yasarla, Deepti Hegde, Shizhong Han, Hsin-Pai Cheng 외 arxiv

Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation learning from sparse trajectory annotations …

Reinforcement LearningAutonomous Driving

LLaViDA: A Large Language Vision Driving Assistant for Explicit Reasoning and Enhanced Trajectory Planning

2025-12-20 · Yudong Liu, Spencer Hallyburton, Jiwoo Kim, Yueqian Lin 외 arxiv

Trajectory planning is a fundamental yet challenging component of autonomous driving. End-to-end planners frequently falter under adverse weather, unpredictable human behavior, or complex road layouts, primarily because …

Scene UnderstandingTrajectory PlanningAutonomous Driving

Distilling Multi-modal Large Language Models for Autonomous Driving

2025-01-16 · CVPR 2025 1 · Deepti Hegde, Rajeev Yasarla, Hong Cai, Shizhong Han 외

Autonomous driving demands safe motion planning, especially in critical "long-tail" scenarios. Recent end-to-end autonomous driving systems leverage large language models (LLMs) as planners to improve generalizability to…

Autonomous DrivingMotion PlanningWorld Knowledge

Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

2024-10-29 · Bo Jiang, Shaoyu Chen, Bencheng Liao, Xingyu Zhang 외

End-to-end autonomous driving demonstrates strong planning capabilities with large-scale data but still struggles in complex, rare scenarios due to limited commonsense. In contrast, Large Vision-Language Models (LVLMs) e…

Autonomous DrivingScene UnderstandingTrajectory Prediction

VLP: Vision Language Planning for Autonomous Driving

2024-01-10 · CVPR 2024 1 · Chenbin Pan, Burhaneddin Yaman, Tommaso Nesti, Abhirup Mallik 외

Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning. While vision-only autonomous driving methods have recently achieved notable performance, t…

Autonomous DrivingMotion PlanningScene Understanding