arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.13152cs.CVcs.AI
收藏

基于智能体选择和物理系数的轨迹预测可解释交互建模

Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient

College of Computer Science and Technology, Zhejiang University of Technology(计算机科学与技术学院,浙江工业大学)

Shiji Huang, Lei Ye, Min Chen, Wenhai Luo, Dihong Wang, Chenqi Xu, Deyuan Liang

AI总结:

本研究提出 ASPILin 方法,通过手动选择交互智能体并用物理相关系数替代 Transformer 注意力分数,提升了轨迹预测中交互建模的可解释性,在降低计算成本的同时显著优于现有方法。

摘要:

深入理解目标智能体与周围智能体之间的交互是准确进行轨迹预测的先决条件。尽管已有许多方法被探索,但它们以纯基于学习的方式为周围智能体分配相关系数。在本研究中,我们提出了 ASPILin,该方法手动选择交互智能体,并用新计算的物理相关系数替换 Transformer 中的注意力分数,从而增强了交互建模的可解释性。令人惊讶的是,这些简单的修改能够显著提升预测性能并大幅降低计算成本。我们有意简化了模型的其他方面,例如地图编码。值得注意的是,在 INTERACTION、highD 和 CitySim 数据集上进行的实验表明,我们的方法高效且直接,优于其他最先进的方法。

英文摘要:

A thorough understanding of the interaction between the target agent and surrounding agents is a prerequisite for accurate trajectory prediction. Although many methods have been explored, they assign correlation coefficients to surrounding agents in a purely learning-based manner. In this study, we present ASPILin, which manually selects interacting agents and replaces the attention scores in Transformer with a newly computed physical correlation coefficient, enhancing the interpretability of interaction modeling. Surprisingly, these simple modifications can significantly improve prediction performance and substantially reduce computational costs. We intentionally simplified our model in other aspects, such as map encoding. Remarkably, experiments conducted on the INTERACTION, highD, and CitySim datasets demonstrate that our method is efficient and straightforward, outperforming other state-of-the-art methods.

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。

↑