G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System

G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System

Navigating dynamic physical environments without obstructing or damaging human assets is of quintessential importance for social robots. In this work, we solve autonomous drone navigation's sub-problem of predicting out-of-domain human and agent trajectories using a deep generative model. Our m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Garg, Aryan, Rameshan, Renu M
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Computer Science - Robotics
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Garg, Aryan
Rameshan, Renu M
description Navigating dynamic physical environments without obstructing or damaging human assets is of quintessential importance for social robots. In this work, we solve autonomous drone navigation's sub-problem of predicting out-of-domain human and agent trajectories using a deep generative model. Our method: General-PECNet or G-PECNet observes an improvement of 9.5\% on the Final Displacement Error (FDE) on 2020's benchmark: PECNet through a combination of architectural improvements inspired by periodic activation functions and synthetic trajectory (data) augmentations using Hidden Markov Models (HMMs) and Reinforcement Learning (RL). Additionally, we propose a simple geometry-inspired metric for trajectory non-linearity and outlier detection, helpful for the task. Code available at https://github.com/Aryan-Garg/PECNet-Pedestrian-Trajectory-Prediction.git
doi_str_mv 10.48550/arxiv.2210.09846
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_09846</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_09846</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-c8f4bc88331fdbea5f0ac7a6b512963f7e4116e84031a6dc7094cb56ada72a33</originalsourceid><addsrcrecordid>eNotz81KxDAYheFsXMjoBbgyN9AxaX7rTspYBwYtTPflS_IFIp1W0qLWq1dHVwfexYGHkBvOttIqxe4gf6b3bVn-BFZZqS_JvinaXf2Myz3tpg_IYaZAGxwxw5C-wA1IWww4LznBSLsMr-iXKa-0zRiSX9I00uM6L3i6IhcRhhmv_3dDjo-7rn4qDi_Nvn44FKCNLryN0nlrheAxOAQVGXgD2ileVlpEg5JzjVYywUEHb1glvVMaApgShNiQ27_XM6V_y-kEee1_Sf2ZJL4Ba7lGxg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System</title><source>arXiv.org</source><creator>Garg, Aryan ; Rameshan, Renu M</creator><creatorcontrib>Garg, Aryan ; Rameshan, Renu M</creatorcontrib><description>Navigating dynamic physical environments without obstructing or damaging human assets is of quintessential importance for social robots. In this work, we solve autonomous drone navigation's sub-problem of predicting out-of-domain human and agent trajectories using a deep generative model. Our method: General-PECNet or G-PECNet observes an improvement of 9.5\% on the Final Displacement Error (FDE) on 2020's benchmark: PECNet through a combination of architectural improvements inspired by periodic activation functions and synthetic trajectory (data) augmentations using Hidden Markov Models (HMMs) and Reinforcement Learning (RL). Additionally, we propose a simple geometry-inspired metric for trajectory non-linearity and outlier detection, helpful for the task. Code available at https://github.com/Aryan-Garg/PECNet-Pedestrian-Trajectory-Prediction.git</description><identifier>DOI: 10.48550/arxiv.2210.09846</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Computer Science - Robotics</subject><creationdate>2022-10</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,887</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.09846$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.09846$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Garg, Aryan</creatorcontrib><creatorcontrib>Rameshan, Renu M</creatorcontrib><title>G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System</title><description>Navigating dynamic physical environments without obstructing or damaging human assets is of quintessential importance for social robots. In this work, we solve autonomous drone navigation's sub-problem of predicting out-of-domain human and agent trajectories using a deep generative model. Our method: General-PECNet or G-PECNet observes an improvement of 9.5\% on the Final Displacement Error (FDE) on 2020's benchmark: PECNet through a combination of architectural improvements inspired by periodic activation functions and synthetic trajectory (data) augmentations using Hidden Markov Models (HMMs) and Reinforcement Learning (RL). Additionally, we propose a simple geometry-inspired metric for trajectory non-linearity and outlier detection, helpful for the task. Code available at https://github.com/Aryan-Garg/PECNet-Pedestrian-Trajectory-Prediction.git</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81KxDAYheFsXMjoBbgyN9AxaX7rTspYBwYtTPflS_IFIp1W0qLWq1dHVwfexYGHkBvOttIqxe4gf6b3bVn-BFZZqS_JvinaXf2Myz3tpg_IYaZAGxwxw5C-wA1IWww4LznBSLsMr-iXKa-0zRiSX9I00uM6L3i6IhcRhhmv_3dDjo-7rn4qDi_Nvn44FKCNLryN0nlrheAxOAQVGXgD2ileVlpEg5JzjVYywUEHb1glvVMaApgShNiQ27_XM6V_y-kEee1_Sf2ZJL4Ba7lGxg</recordid><startdate>20221015</startdate><enddate>20221015</enddate><creator>Garg, Aryan</creator><creator>Rameshan, Renu M</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221015</creationdate><title>G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System</title><author>Garg, Aryan ; Rameshan, Renu M</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-c8f4bc88331fdbea5f0ac7a6b512963f7e4116e84031a6dc7094cb56ada72a33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Garg, Aryan</creatorcontrib><creatorcontrib>Rameshan, Renu M</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Garg, Aryan</au><au>Rameshan, Renu M</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System</atitle><date>2022-10-15</date><risdate>2022</risdate><abstract>Navigating dynamic physical environments without obstructing or damaging human assets is of quintessential importance for social robots. In this work, we solve autonomous drone navigation's sub-problem of predicting out-of-domain human and agent trajectories using a deep generative model. Our method: General-PECNet or G-PECNet observes an improvement of 9.5\% on the Final Displacement Error (FDE) on 2020's benchmark: PECNet through a combination of architectural improvements inspired by periodic activation functions and synthetic trajectory (data) augmentations using Hidden Markov Models (HMMs) and Reinforcement Learning (RL). Additionally, we propose a simple geometry-inspired metric for trajectory non-linearity and outlier detection, helpful for the task. Code available at https://github.com/Aryan-Garg/PECNet-Pedestrian-Trajectory-Prediction.git</abstract><doi>10.48550/arxiv.2210.09846</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.09846
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_09846
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Computer Science - Robotics
title G-PECNet: Towards a Generalizable Pedestrian Trajectory Prediction System
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-03T20%3A48%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=G-PECNet:%20Towards%20a%20Generalizable%20Pedestrian%20Trajectory%20Prediction%20System&rft.au=Garg,%20Aryan&rft.date=2022-10-15&rft_id=info:doi/10.48550/arxiv.2210.09846&rft_dat=%3Carxiv_GOX%3E2210_09846%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true