Behavior-Inspired Neural Networks for Relational Inference
This work addresses the challenge of modeling complex, intermingling relationships in multi-agent systems, which is incremental by refining existing categorical distribution approaches.
The paper tackled the problem of learning interpretable relationship categories between agents in dynamical systems by introducing an abstraction layer that maps agent observations to preferences for latent categories, integrated with a nonlinear opinion dynamics model. The result demonstrated improved interpretability and efficacy in long-horizon trajectory prediction through extensive experiments.
From pedestrians to Kuramoto oscillators, interactions between agents govern how dynamical systems evolve in space and time. Discovering how these agents relate to each other has the potential to improve our understanding of the often complex dynamics that underlie these systems. Recent works learn to categorize relationships between agents based on observations of their physical behavior. These approaches model relationship categories as outcomes of a categorical distribution which is limiting and contrary to real-world systems, where relationship categories often intermingle and interact. In this work, we introduce a level of abstraction between the observable behavior of agents and the latent categories that determine their behavior. To do this, we learn a mapping from agent observations to agent preferences for a set of latent categories. The learned preferences and inter-agent proximity are integrated in a nonlinear opinion dynamics model, which allows us to naturally identify mutually exclusive categories, predict an agent's evolution in time, and control an agent's behavior. Through extensive experiments, we demonstrate the utility of our model for learning interpretable categories, and the efficacy of our model for long-horizon trajectory prediction.