考虑车辆交互与不确定性，提升自动驾驶轨迹预测安全性
Interaction-Aware Trajectory Prediction for Safe Motion Planning in Autonomous Driving: A Transformer-Transfer Learning Approach
- 用Transformer+迁移学习建模自动驾驶车与人类驾驶车的交互
- 在真实数据上验证，预测误差降低且规划更安全
- 适合关注自动驾驶决策安全性的研究者与工程师
自动驾驶车辆安全高效运动规划的关键在于应对周边人类驾驶车辆（HDV）复杂多变的行为。尽管已有大量关于驾驶员行为预测的研究，但现有方法通常忽略自动驾驶车辆（AV）与人类驾驶车辆（HDV）之间的交互，假设HDV轨迹不受AV动作影响。为弥补这一空白，本文提出一种基于Transformer与迁移学习的交互感知轨迹预测方法，聚焦于一辆AV与一辆HDV之间的车对车（V2V）交互场景。具体而言，利用广泛可得的HDV轨迹数据构建基于Transformer的交互感知预测器，并通过少量AV-HDV交互数据进行迁移学习。为进一步将预测结果融入自动驾驶运动规划模块，引入不确定性量化方法表征预测误差，并将其整合进路径规划过程。实验结果表明，显式考虑交互关系并处理不确定性具有显著价值。
原文摘要 · Abstract (English)
A critical aspect of safe and efficient motion planning for autonomous vehicles (AVs) is to handle the complex and uncertain behavior of surrounding human-driven vehicles (HDVs). Despite intensive research on driver behavior prediction, existing approaches typically overlook the interactions between AVs and HDVs assuming that HDV trajectories are not affected by AV actions. To address this gap, we present a transformer-transfer learning-based interaction-aware trajectory predictor for safe motion planning of autonomous driving, focusing on a vehicle-to-vehicle (V2V) interaction scenario consisting of an AV and an HDV. Specifically, we construct a transformer-based interaction-aware trajectory predictor using widely available datasets of HDV trajectory data and further transfer the learned predictor using a small set of AV-HDV interaction data. Then, to better incorporate the proposed trajectory predictor into the motion planning module of AVs, we introduce an uncertainty quantification method to characterize the errors of the predictor, which are integrated into the path-planning process. Our experimental results demonstrate the value of explicitly considering interactions and handling uncertainties.
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。