Inferring interactions from multi-agent trajectories has broad applications
in physics, vision and robotics. Neural relational inference (NRI) is a deep
generative model that can reason about relations in complex dynamics without
supervision. In this paper, we take a careful look at this approach for
relational inference in multi-agent trajectories. First, we discover that NRI
can be fundamentally limited without sufficient long-term observations. Its
ability to accurately infer interactions degrades drastically for short output
sequences. Next, we consider a more general setting of relational inference
when interactions are changing overtime. We propose an extension ofNRI, which
we call the DYnamic multi-AgentRelational Inference (DYARI) model that can
reason about dynamic relations. We conduct exhaustive experiments to study the
effect of model architecture, under-lying dynamics and training scheme on the
performance of dynamic relational inference using a simulated physics system.
We also showcase the usage of our model on real-world multi-agent basketball
trajectories.

本文介绍了神经关系推理 (NRI) 模型在多智能体轨迹的关系推理领域的应用。作者发现没有足够长期的记录会严重损害 NRI 模型的推理结果，为此提出了一种叫做 DYARI 模型的扩展模型，能够处理关系动态变化的情况。作者通过对模型结构、底层动态和训练方案的详细研究，并在模拟物理系统和真实多智能体篮球轨迹上验证了 DYARI 模型的有效性。