Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis
| Title: | Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis |
|---|---|
| Authors: | Fragkedaki, Kleio, Jiang, Frank J., Johansson, Karl H., Mårtensson, Jonas |
| Publication Year: | 2024 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics, Electrical Engineering and Systems Science - Systems and Control |
| More Details: | In this work, we present a transformer-based framework for predicting future pedestrian states based on clustered historical trajectory data. In previous studies, researchers propose enhancing pedestrian trajectory predictions by using manually crafted labels to categorize pedestrian behaviors and intentions. However, these approaches often only capture a limited range of pedestrian behaviors and introduce human bias into the predictions. To alleviate the dependency on manually crafted labels, we utilize a transformer encoder coupled with hierarchical density-based clustering to automatically identify diverse behavior patterns, and use these clusters in data-driven reachability analysis. By using a transformer-based approach, we seek to enhance the representation of pedestrian trajectories and uncover characteristics or features that are subsequently used to group trajectories into different "behavior" clusters. We show that these behavior clusters can be used with data-driven reachability analysis, yielding an end-to-end data-driven approach to predicting the future motion of pedestrians. We train and evaluate our approach on a real pedestrian dataset, showcasing its effectiveness in forecasting pedestrian movements. |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2408.15250 |
| Accession Number: | edsarx.2408.15250 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2408.15250 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20240809&spage=&pages=&title=Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis&atitle=Pedestrian%20Motion%20Prediction%20Using%20Transformer-based%20Behavior%20Clustering%20and%20Data-Driven%20Reachability%20Analysis&aulast=Fragkedaki%2C%20Kleio&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2408.15250 RelevancyScore: 1112 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1112.24304199219 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Fragkedaki%2C+Kleio%22">Fragkedaki, Kleio</searchLink><br /><searchLink fieldCode="AR" term="%22Jiang%2C+Frank+J%2E%22">Jiang, Frank J.</searchLink><br /><searchLink fieldCode="AR" term="%22Johansson%2C+Karl+H%2E%22">Johansson, Karl H.</searchLink><br /><searchLink fieldCode="AR" term="%22Mårtensson%2C+Jonas%22">Mårtensson, Jonas</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Robotics%22">Computer Science - Robotics</searchLink><br /><searchLink fieldCode="DE" term="%22Electrical+Engineering+and+Systems+Science+-+Systems+and+Control%22">Electrical Engineering and Systems Science - Systems and Control</searchLink> – Name: Abstract Label: Description Group: Ab Data: In this work, we present a transformer-based framework for predicting future pedestrian states based on clustered historical trajectory data. In previous studies, researchers propose enhancing pedestrian trajectory predictions by using manually crafted labels to categorize pedestrian behaviors and intentions. However, these approaches often only capture a limited range of pedestrian behaviors and introduce human bias into the predictions. To alleviate the dependency on manually crafted labels, we utilize a transformer encoder coupled with hierarchical density-based clustering to automatically identify diverse behavior patterns, and use these clusters in data-driven reachability analysis. By using a transformer-based approach, we seek to enhance the representation of pedestrian trajectories and uncover characteristics or features that are subsequently used to group trajectories into different "behavior" clusters. We show that these behavior clusters can be used with data-driven reachability analysis, yielding an end-to-end data-driven approach to predicting the future motion of pedestrians. We train and evaluate our approach on a real pedestrian dataset, showcasing its effectiveness in forecasting pedestrian movements. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2408.15250" linkWindow="_blank">http://arxiv.org/abs/2408.15250</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2408.15250 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2408.15250 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general – SubjectFull: Computer Science - Robotics Type: general – SubjectFull: Electrical Engineering and Systems Science - Systems and Control Type: general Titles: – TitleFull: Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Fragkedaki, Kleio – PersonEntity: Name: NameFull: Jiang, Frank J. – PersonEntity: Name: NameFull: Johansson, Karl H. – PersonEntity: Name: NameFull: Mårtensson, Jonas IsPartOfRelationships: – BibEntity: Dates: – D: 09 M: 08 Type: published Y: 2024 |
| ResultId | 1 |