解耦神经关系推断用于可解释的运动预测
Disentangled Neural Relational Inference for Interpretable Motion Prediction
AI总结：
本文提出一种结合图表示与时间序列模型的解耦变分自编码器框架，通过在潜在空间推断动态交互图并解耦边特征，有效提升了动态智能体运动预测的可解释性与分布外泛化能力。
摘要：
动态智能体的有效交互建模和行为预测在自主机器人的交互式运动规划中起着重要作用。尽管现有方法提高了预测精度，但很少有研究致力于提升预测模型的可解释性和分布外（OOD）泛化能力。本工作通过设计一个结合图表示和时间序列模型的变分自编码器框架来解决这两个挑战，以高效捕捉交互智能体间的时空关系并预测其动态。我们的模型在潜在空间中推断动态交互图，该空间通过可解释的边特征进行增强，以表征交互作用。此外，我们通过解耦边特征的潜在空间来提升模型在OOD场景下的可解释性和性能，从而增强模型的通用性和鲁棒性。我们通过在模拟和真实世界数据集上的大量实验验证了该方法。结果表明，与现有方法相比，在建模时空关系、运动预测和识别时间不变潜在特征方面表现出更优的性能。
英文摘要：
Effective interaction modeling and behavior prediction of dynamic agents play a significant role in interactive motion planning for autonomous robots. Although existing methods have improved prediction accuracy, few research efforts have been devoted to enhancing prediction model interpretability and out-of-distribution (OOD) generalizability. This work addresses these two challenging aspects by designing a variational auto-encoder framework that integrates graph-based representations and time-sequence models to efficiently capture spatio-temporal relations between interactive agents and predict their dynamics. Our model infers dynamic interaction graphs in a latent space augmented with interpretable edge features that characterize the interactions. Moreover, we aim to enhance model interpretability and performance in OOD scenarios by disentangling the latent space of edge features, thereby strengthening model versatility and robustness. We validate our approach through extensive experiments on both simulated and real-world datasets. The results show superior performance compared to existing methods in modeling spatio-temporal relations, motion prediction, and identifying time-invariant latent features.
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。
