SocialVAE: Human Trajectory Prediction using Timewise Latents

Predicting pedestrian movement is critical for human behavior analysis and also for safe and efficient human-agent interactions. However, despite significant advancements, it is still challenging for existing approaches to capture the uncertainty and multimodality of human navigation decision making...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-07
Main Authors: Xu, Pei, Jean-Bernard Hayet, Karamouzas, Ioannis
Format: Article
Language:English
Subjects:
Agents (artificial intelligence)
Benchmarks
Datasets
Decision making
Human motion
Navigation
Predictions
Recurrent neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Predicting pedestrian movement is critical for human behavior analysis and also for safe and efficient human-agent interactions. However, despite significant advancements, it is still challenging for existing approaches to capture the uncertainty and multimodality of human navigation decision making. In this paper, we propose SocialVAE, a novel approach for human trajectory prediction. The core of SocialVAE is a timewise variational autoencoder architecture that exploits stochastic recurrent neural networks to perform prediction, combined with a social attention mechanism and a backward posterior approximation to allow for better extraction of pedestrian navigation strategies. We show that SocialVAE improves current state-of-the-art performance on several pedestrian trajectory prediction benchmarks, including the ETH/UCY benchmark, Stanford Drone Dataset, and SportVU NBA movement dataset. Code is available at: https://github.com/xupei0610/SocialVAE.
ISSN:2331-8422
DOI:10.48550/arxiv.2203.08207