Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Boris Ivanovic, Marco Pavone• 2018

Related benchmarks

TaskDatasetResultRank
Trajectory PredictionETH UCY (test)
ADE0.22
65
Trajectory PredictionZARA1 v1.0 (test)
ADE0.17
58
Trajectory PredictionETH-UCY--
57
Trajectory PredictionHotel ETH-UCY (test)
ADE0.12
48
Trajectory PredictionZARA2 v1.0 (test)
ADE0.12
36
Trajectory PredictionETH v1.0 (test)
ADE0.59
33
Pedestrian trajectory predictionETH (test)--
29
Trajectory ForecastingTrajNet++ real world Type III (test)
ADE0.6
19
Trajectory ForecastingHotel ETH scene (test)
ADE0.35
12
Trajectory ForecastingUniv UCY scene (test)
ADE0.54
12
Showing 10 of 20 rows

Other info

Follow for update