arXiv cs.AI· Shuo Zhang, Aman Sunesh, Semiha Ergan, Kaan Ozbay·· 6 天前AI 评分20
基于人在回路驾驶数据的道路施工区自动驾驶轨迹预测
Trajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data
AI 导读
研究团队构建了 WZDrive-Data 多模态数据集，包含 33 名驾驶员在施工区段的 1,183 段驾驶记录，通过人在回路驾驶模拟器采集驾驶员控制与注视信号。其提出的多模态轨迹预测器 WZDrive 实现 minADE (K=6) 1.09 m、minFDE (K=6) 2.12 m，相比各指标最优基线分别降低 7.18% 和 13.18%。
正文 · 原文
Abstract:Ego-trajectory prediction in urban roadway work zones remains an underexplored topic in autonomous-driving research, with limited dedicated data and systematic evaluation. Roadway work zones involve temporary changes in the lane layouts and connectivity of the roads, complicating interactions with surrounding vehicles and workers. These changes make future vehicle trajectories difficult to predict. To address these challenges, we collect WZDrive-Data, a multimodal dataset comprising 1,183 work-zone driving segments from 33 drivers, using a human-in-the-loop driving simulator with prerecorded worker animations and VR-controlled workers. Driver control and gaze signals are recorded from human participants, while vehicle trajectories and scene information are obtained from the simulator. Our proposed multimodal ego-trajectory predictor, WZDrive, achieves a mean minADE (K=6) of 1.09 m and minFDE (K=6) of 2.12 m. Compared with the best-performing state-of-the-art baseline for each metric in our benchmark, WZDrive reduces minADE (K=6) by 7.18% and minFDE (K=6) by 13.18%. This research addresses a gap in autonomous-driving research on urban work zones by combining human-in-the-loop data collection with multimodal learning from human driving signals and in the context of work zones.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.12747 [cs.RO] |
| (or arXiv:2610.12747v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12747 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shuo Zhang [view email]
[v1]
Thu, 8 Oct 2026 21:48:35 UTC (1,054 KB)
来源：arXiv cs.AI · arxiv.org