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!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Xu, Pei
Jean-Bernard Hayet
Karamouzas, Ioannis
description 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.
doi_str_mv 10.48550/arxiv.2203.08207
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2640165154</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2640165154</sourcerecordid><originalsourceid>FETCH-LOGICAL-a957-a34a2d78fd4995b02903361ba5b82d129af09ca3bd7e40c56bd23287ff11d4d63</originalsourceid><addsrcrecordid>eNotzU1LwzAYwPEgCI65D-At4Ln1yZN3wcMY0wkFBYvXkTappGytJq0v396Bnv6335-QKwalMFLCjUvf8bNEBF6CQdBnZIGcs8IIxAuyyrkHAFQapeQLcvcyttEdXtfbW7qbj26gdXJ9aKcx_dDnFHxspzgOdM5xeKN1PIavmAOt3BSGKV-S884dclj9d0nq-2292RXV08PjZl0VzkpdOC4cem06L6yVDaAFzhVrnGwMeobWdWBbxxuvg4BWqsYjR6O7jjEvvOJLcv3HvqfxYw552vfjnIbTcY9KAFOSScF_ARW5SS4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2640165154</pqid></control><display><type>article</type><title>SocialVAE: Human Trajectory Prediction using Timewise Latents</title><source>Publicly Available Content Database</source><creator>Xu, Pei ; Jean-Bernard Hayet ; Karamouzas, Ioannis</creator><creatorcontrib>Xu, Pei ; Jean-Bernard Hayet ; Karamouzas, Ioannis</creatorcontrib><description>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.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2203.08207</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Agents (artificial intelligence) ; Benchmarks ; Datasets ; Decision making ; Human motion ; Navigation ; Predictions ; Recurrent neural networks</subject><ispartof>arXiv.org, 2022-07</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2640165154?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>777,781,25734,27906,36993,44571</link.rule.ids></links><search><creatorcontrib>Xu, Pei</creatorcontrib><creatorcontrib>Jean-Bernard Hayet</creatorcontrib><creatorcontrib>Karamouzas, Ioannis</creatorcontrib><title>SocialVAE: Human Trajectory Prediction using Timewise Latents</title><title>arXiv.org</title><description>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.</description><subject>Agents (artificial intelligence)</subject><subject>Benchmarks</subject><subject>Datasets</subject><subject>Decision making</subject><subject>Human motion</subject><subject>Navigation</subject><subject>Predictions</subject><subject>Recurrent neural networks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNotzU1LwzAYwPEgCI65D-At4Ln1yZN3wcMY0wkFBYvXkTappGytJq0v396Bnv6335-QKwalMFLCjUvf8bNEBF6CQdBnZIGcs8IIxAuyyrkHAFQapeQLcvcyttEdXtfbW7qbj26gdXJ9aKcx_dDnFHxspzgOdM5xeKN1PIavmAOt3BSGKV-S884dclj9d0nq-2292RXV08PjZl0VzkpdOC4cem06L6yVDaAFzhVrnGwMeobWdWBbxxuvg4BWqsYjR6O7jjEvvOJLcv3HvqfxYw552vfjnIbTcY9KAFOSScF_ARW5SS4</recordid><startdate>20220731</startdate><enddate>20220731</enddate><creator>Xu, Pei</creator><creator>Jean-Bernard Hayet</creator><creator>Karamouzas, Ioannis</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220731</creationdate><title>SocialVAE: Human Trajectory Prediction using Timewise Latents</title><author>Xu, Pei ; Jean-Bernard Hayet ; Karamouzas, Ioannis</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a957-a34a2d78fd4995b02903361ba5b82d129af09ca3bd7e40c56bd23287ff11d4d63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Agents (artificial intelligence)</topic><topic>Benchmarks</topic><topic>Datasets</topic><topic>Decision making</topic><topic>Human motion</topic><topic>Navigation</topic><topic>Predictions</topic><topic>Recurrent neural networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Xu, Pei</creatorcontrib><creatorcontrib>Jean-Bernard Hayet</creatorcontrib><creatorcontrib>Karamouzas, Ioannis</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xu, Pei</au><au>Jean-Bernard Hayet</au><au>Karamouzas, Ioannis</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SocialVAE: Human Trajectory Prediction using Timewise Latents</atitle><jtitle>arXiv.org</jtitle><date>2022-07-31</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>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.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2203.08207</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2640165154
source Publicly Available Content Database
subjects Agents (artificial intelligence)
Benchmarks
Datasets
Decision making
Human motion
Navigation
Predictions
Recurrent neural networks
title SocialVAE: Human Trajectory Prediction using Timewise Latents
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T21%3A28%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SocialVAE:%20Human%20Trajectory%20Prediction%20using%20Timewise%20Latents&rft.jtitle=arXiv.org&rft.au=Xu,%20Pei&rft.date=2022-07-31&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2203.08207&rft_dat=%3Cproquest%3E2640165154%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a957-a34a2d78fd4995b02903361ba5b82d129af09ca3bd7e40c56bd23287ff11d4d63%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2640165154&rft_id=info:pmid/&rfr_iscdi=true