The Trajectron: Probabilistic Multi-Agent Trajectory Modeling With Dynamic Spatiotemporal Graphs

TL;DR

The Trajectron is a probabilistic, graph-based model that predicts multiple potential future trajectories for agents in dynamic, multimodal scenarios, advancing safe human-robot interaction.

Contribution

It introduces a novel graph-structured deep generative model that predicts diverse future trajectories for multiple agents simultaneously in complex environments.

Findings

Achieves state-of-the-art trajectory prediction accuracy.

Effectively models multimodal and dynamic multi-agent scenarios.

Introduces a new metric for comparing probabilistic trajectory models.

Abstract

Developing safe human-robot interaction systems is a necessary step towards the widespread integration of autonomous agents in society. A key component of such systems is the ability to reason about the many potential futures (e.g. trajectories) of other agents in the scene. Towards this end, we present the Trajectron, a graph-structured model that predicts many potential future trajectories of multiple agents simultaneously in both highly dynamic and multimodal scenarios (i.e. where the number of agents in the scene is time-varying and there are many possible highly-distinct futures for each agent). It combines tools from recurrent sequence modeling and variational deep generative modeling to produce a distribution of future trajectories for each agent in a scene. We demonstrate the performance of our model on several datasets, obtaining state-of-the-art results on standard trajectory prediction metrics as well as introducing a new metric for comparing models that output distributions.