用生成数据提升自动驾驶避撞能力，效果比现有方法高56%。
Enhancing Autonomous Driving Safety with Collision Scenario Integration
- 引入安全指标训练，让模型从碰撞数据中学习避障。
- 生成多样高质场景，解决真实碰撞数据稀缺问题。
- 适合关注自动驾驶安全与数据增强的研究者。
自动驾驶安全对无人驾驶的落地至关重要。然而，现有规划方法过度依赖模仿学习，难以有效利用碰撞数据；同时，收集碰撞或近碰撞数据存在风险及伦理难题。本文提出SafeFusion训练框架，通过在训练中融入面向安全的度量，实现避撞学习。为缓解碰撞数据稀缺问题，提出CollisionGen——一种基于自然语言提示、生成模型和规则过滤的可扩展数据生成流程，用于生成多样化高质量场景。实验表明，该方法在易发生碰撞的场景下，规划性能相比现有最先进方法提升56%，同时在常规驾驶场景中仍保持高效。本工作为提升自动驾驶系统安全性提供了可扩展且有效的解决方案。
原文摘要 · Abstract (English)
Autonomous vehicle safety is crucial for the successful deployment of self-driving cars. However, most existing planning methods rely heavily on imitation learning, which limits their ability to leverage collision data effectively. Moreover, collecting collision or near-collision data is inherently challenging, as it involves risks and raises ethical and practical concerns. In this paper, we propose SafeFusion, a training framework to learn from collision data. Instead of over-relying on imitation learning, SafeFusion integrates safety-oriented metrics during training to enable collision avoidance learning. In addition, to address the scarcity of collision data, we propose CollisionGen, a scalable data generation pipeline to generate diverse, high-quality scenarios using natural language prompts, generative models, and rule-based filtering. Experimental results show that our approach improves planning performance in collision-prone scenarios by 56\% over previous state-of-the-art planners while maintaining effectiveness in regular driving situations. Our work provides a scalable and effective solution for advancing the safety of autonomous driving systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。