arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2608.21414cs.ROcs.LG

RiskWorld:面向自动驾驶风险识别的以对象为中心的潜在世界建模

RiskWorld: Object-Centric Latent World Modeling for Autonomous Driving Risk Identification

Jingzheng Li, Yufei Ge, Qianren Mao, Zhijun Chen, Bing Li, Xingyu Peng, Baochang Zhang, Xianglong Liu

首次发表
浏览论文内容

中文总结 AI 辅助

提出 RiskWorld 模型,以对象为中心的潜在世界建模,结合预训练视频表示与自车-对象历史,在 RiskBench 上实现 63.0% F1 和 2.1% 误报率,可有效识别自动驾驶风险。

中文摘要 AI 辅助

自动驾驶风险识别旨在确定哪个观测对象可能对 ego 车辆(自车)构成安全关键威胁。现有方法通常预测场景级事故、从自车行为间接推断风险对象,或在轨迹预测后应用几何检查,未直接利用预测的自车-对象关系进行风险源定位。我们提出 RiskWorld,一种以对象为中心的潜在世界模型,通过想象每个候选对象相对于自车的演化来识别风险。RiskWorld 将预训练的预测视频表示与结构化的自车-对象历史相结合,对观测到的交互进行情境化处理,并使用 RSSM 风格的潜在动力学将感知关系的对象状态滚动到未来。它将滚动结果解码为对象级风险分数,辅助未来关系和时间风险预测提供支持。推理仅使用截至当前时间的观测数据,而记录的未来数据提供训练监督。在 RiskBench 上,RiskWorld 实现了 63.0% 的最佳整体 F1 值和 2.1% 的最低误报率。进一步分析表明,学习到的滚动结果捕捉了关键事件前对象级风险的演化,而 RiskWorld 的选择在过滤后的观测下保留了规划关键信息。

英文摘要

Autonomous driving risk identification aims to determine which observed object is likely to become safety-critical to the ego vehicle. Existing approaches typically predict scene-level accidents, infer risk objects indirectly from ego behavior, or apply geometric checks after trajectory forecasting, without directly using predicted ego--object relations for risk-source localization. We propose RiskWorld, an object-centric latent world model that identifies risk from the imagined evolution of each candidate relative to the ego vehicle. RiskWorld combines pretrained predictive video representations with structured ego--object histories, contextualizes observed interactions, and rolls relation-aware object states into the future using RSSM-style latent dynamics. It decodes the rollout into object-level risk scores, supported by auxiliary future-relation and temporal-risk predictions. Inference uses only observations up to the current time, while logged futures provide training supervision. On RiskBench, RiskWorld achieves the best overall F1 of 63.0\% and the lowest false-alarm rate of 2.1\%. Further analyses show that the learned rollout captures the evolution of object-level risk before critical events, while RiskWorld's selections preserve planning-critical information under filtered observation.

↑