解釈可能な運動予測のための分離型ニューラル関係推論
Disentangled Neural Relational Inference for Interpretable Motion Prediction
グラフ表現と時系列モデルを統合した変分オートエンコーダで、動的エージェント間の相互作用を潜在空間で推論し、エッジ特徴を分離して解釈性と分布外汎化性能を高めた運動予測手法を提案。
著者: Victoria M. Dax, Jiachen Li, Enna Sachdeva, Nakul Agarwal, Mykel J. Kochenderfer
分類: cs.RO, cs.AI
原文アブストラクト
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.
