arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09117cs.CVcs.AIcs.LGcs.MAcs.RO
收藏

用于多智能体预测与跟踪的时空图双重注意力网络

Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking

University of California, Berkeley（加州大学伯克利分校）

Jiachen Li, Hengbo Ma, Zhihao Zhang, Jinning Li, Masayoshi Tomizuka

备注：
This work has been submitted to the IEEE for possible publication
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出STG-DAT生成式神经系统，利用动态图、关系归纳偏置和双重注意力建模异构智能体交互，并加入运动学约束，在三个基准上提升轨迹预测与多目标跟踪精度。

摘要：

有效地理解环境并准确预测周围动态障碍物的轨迹，对于智能移动系统（例如自动驾驶车辆和社交机器人）在高度交互且拥挤的场景中导航时实现安全、高质量的规划是不可或缺的。由于场景演化中存在频繁交互和不确定性，预测系统需要能够对不同实体进行关系推理，并为每个智能体提供未来轨迹的分布。本文提出了一个通用的生成式神经系统（称为STG-DAT），用于涉及异构智能体的多智能体轨迹预测。该系统通过将关系归纳偏置与动态图表示相结合，在显式交互建模方面更进一步，并同时利用轨迹和场景上下文信息。我们还采用了一个高效的运动学约束层，应用于车辆轨迹预测。该约束不仅确保物理可行性，还提升了模型性能。此外，所提出的预测模型可以方便地被多目标跟踪框架采用。实证结果证明跟踪精度得到提高。所提出的系统在三个轨迹预测公共基准数据集上进行了评估，其中智能体涵盖行人、骑行者和道路车辆。实验结果表明，我们的模型在预测和跟踪精度方面优于多种基线方法。

英文摘要：

An effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (e.g. autonomous vehicles and social robots) to achieve safe and high-quality planning when they navigate in highly interactive and crowded scenarios. Due to the existence of frequent interactions and uncertainty in the scene evolution, it is desired for the prediction system to enable relational reasoning on different entities and provide a distribution of future trajectories for each agent. In this paper, we propose a generic generative neural system (called STG-DAT) for multi-agent trajectory prediction involving heterogeneous agents. The system takes a step forward to explicit interaction modeling by incorporating relational inductive biases with a dynamic graph representation and leverages both trajectory and scene context information. We also employ an efficient kinematic constraint layer applied to vehicle trajectory prediction. The constraint not only ensures physical feasibility but also enhances model performance. Moreover, the proposed prediction model can be easily adopted by multi-target tracking frameworks. The tracking accuracy proves to be improved by empirical results. The proposed system is evaluated on three public benchmark datasets for trajectory prediction, where the agents cover pedestrians, cyclists and on-road vehicles. The experimental results demonstrate that our model achieves better performance than various baseline approaches in terms of prediction and tracking accuracy.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑