SafeDriveVLA:可识别导航冲突的驾驶VLA模型
一篇被CoRL 2026接收、10月14日提交到arXiv(arXiv:2610.20609)的论文提出SafeDriveVLA:它显式预测三级“导航遵从模式”,把冲突推理与动作生成解耦,并用以导航为条件的世界模型“dreaming”来判断遵从导航信号在何时是安全的。作者同时给出一个将导航跟随、冲突感知与对抗鲁棒性放在一起评估的基准套件,称现有VLA在两方面均不足,SimLingo在闭环中未能完成任何语言指令变道。作者报告SafeDriveVLA在Bench2Drive上取得88.16驾驶分数与68.64%成功率,闭环语言跟随提升49.3%,不安全指令下的碰撞从60次降到38次(对比最佳SimLingo变体)。
论文指出,自由文本导航接口带来了新的脆弱面:分心的驾驶员可能给出与当前场景冲突的不安全指令,恶意用户也可能故意下达危险指令,因此模型需要显式判断何时不应遵从。
Computer Science > Robotics
arXiv:2610.20609 (cs)
[Submitted on 14 Oct 2026]
Title:SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving
Authors:Shaoyuan Xie, Zihan Zhang, Jingxuan Wang, Jiashu Qu, Xiaoqing Liang, Lingdong Kong, Junchi Lu, Henrik I. Christensen, Qi Alfred Chen
View a PDF of the paper titled SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving, by Shaoyuan Xie and 8 other authors