Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting Article Swipe
Kaouther Messaoud
,
Matthieu Cord
,
Alexandre Alahi
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.04815
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.04815
Existing vehicle trajectory prediction models struggle with generalizability, prediction uncertainties, and handling complex interactions. It is often due to limitations like complex architectures customized for a specific dataset and inefficient multimodal handling. We propose Perceiver with Register queries (PerReg+), a novel trajectory prediction framework that introduces: (1) Dual-Level Representation Learning via Self-Distillation (SD) and Masked Reconstruction (MR), capturing global context and fine-grained details. Additionally, our approach of reconstructing segmentlevel trajectories and lane segments from masked inputs with query drop, enables effective use of contextual information and improves generalization; (2) Enhanced Multimodality using register-based queries and pretraining, eliminating the need for clustering and suppression; and (3) Adaptive Prompt Tuning during fine-tuning, freezing the main architecture and optimizing a small number of prompts for efficient adaptation. PerReg+ sets a new state-of-the-art performance on nuScenes [1], Argoverse 2 [2], and Waymo Open Motion Dataset (WOMD) [3]. Remarkable, our pretrained model reduces the error by 6.8% on smaller datasets, and multi-dataset training enhances generalization. In cross-domain tests, PerReg+ reduces B-FDE by 11.8% compared to its non-pretrained variant.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2501.04815
- https://arxiv.org/pdf/2501.04815
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406271038
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406271038Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2501.04815Digital Object Identifier
- Title
-
Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive PromptingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-08Full publication date if available
- Authors
-
Kaouther Messaoud, Matthieu Cord, Alexandre AlahiList of authors in order
- Landing page
-
https://arxiv.org/abs/2501.04815Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2501.04815Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2501.04815Direct OA link when available
- Concepts
-
Trajectory, Representation (politics), Dual (grammatical number), Computer science, Artificial intelligence, Machine learning, Art, Political science, Physics, Law, Astronomy, Literature, PoliticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4406271038 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2501.04815 |
| ids.doi | https://doi.org/10.48550/arxiv.2501.04815 |
| ids.openalex | https://openalex.org/W4406271038 |
| fwci | |
| type | preprint |
| title | Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11099 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9962999820709229 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2203 |
| topics[0].subfield.display_name | Automotive Engineering |
| topics[0].display_name | Autonomous Vehicle Technology and Safety |
| topics[1].id | https://openalex.org/T11344 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9886999726295471 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2215 |
| topics[1].subfield.display_name | Building and Construction |
| topics[1].display_name | Traffic Prediction and Management Techniques |
| topics[2].id | https://openalex.org/T10370 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9739000201225281 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2213 |
| topics[2].subfield.display_name | Safety, Risk, Reliability and Quality |
| topics[2].display_name | Traffic and Road Safety |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C13662910 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7375761270523071 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q193139 |
| concepts[0].display_name | Trajectory |
| concepts[1].id | https://openalex.org/C2776359362 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6801396608352661 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[1].display_name | Representation (politics) |
| concepts[2].id | https://openalex.org/C2780980858 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6327170729637146 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q110022 |
| concepts[2].display_name | Dual (grammatical number) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5035333037376404 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.47548067569732666 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3904940187931061 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C142362112 |
| concepts[6].level | 0 |
| concepts[6].score | 0.09999614953994751 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[6].display_name | Art |
| concepts[7].id | https://openalex.org/C17744445 |
| concepts[7].level | 0 |
| concepts[7].score | 0.08495190739631653 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[7].display_name | Political science |
| concepts[8].id | https://openalex.org/C121332964 |
| concepts[8].level | 0 |
| concepts[8].score | 0.07959184050559998 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[8].display_name | Physics |
| concepts[9].id | https://openalex.org/C199539241 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[9].display_name | Law |
| concepts[10].id | https://openalex.org/C1276947 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q333 |
| concepts[10].display_name | Astronomy |
| concepts[11].id | https://openalex.org/C124952713 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8242 |
| concepts[11].display_name | Literature |
| concepts[12].id | https://openalex.org/C94625758 |
| concepts[12].level | 2 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[12].display_name | Politics |
| keywords[0].id | https://openalex.org/keywords/trajectory |
| keywords[0].score | 0.7375761270523071 |
| keywords[0].display_name | Trajectory |
| keywords[1].id | https://openalex.org/keywords/representation |
| keywords[1].score | 0.6801396608352661 |
| keywords[1].display_name | Representation (politics) |
| keywords[2].id | https://openalex.org/keywords/dual |
| keywords[2].score | 0.6327170729637146 |
| keywords[2].display_name | Dual (grammatical number) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5035333037376404 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.47548067569732666 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.3904940187931061 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/art |
| keywords[6].score | 0.09999614953994751 |
| keywords[6].display_name | Art |
| keywords[7].id | https://openalex.org/keywords/political-science |
| keywords[7].score | 0.08495190739631653 |
| keywords[7].display_name | Political science |
| keywords[8].id | https://openalex.org/keywords/physics |
| keywords[8].score | 0.07959184050559998 |
| keywords[8].display_name | Physics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2501.04815 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2501.04815 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2501.04815 |
| locations[1].id | doi:10.48550/arxiv.2501.04815 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2501.04815 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5063024690 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-4602-8100 |
| authorships[0].author.display_name | Kaouther Messaoud |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Messaoud, Kaouther |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5108118084 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0627-5844 |
| authorships[1].author.display_name | Matthieu Cord |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Cord, Matthieu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5068504559 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5004-1498 |
| authorships[2].author.display_name | Alexandre Alahi |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Alahi, Alexandre |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2501.04815 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11099 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9962999820709229 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2203 |
| primary_topic.subfield.display_name | Automotive Engineering |
| primary_topic.display_name | Autonomous Vehicle Technology and Safety |
| related_works | https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W4387369504, https://openalex.org/W3046775127, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W3107602296, https://openalex.org/W4364306694, https://openalex.org/W4312192474 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2501.04815 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2501.04815 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2501.04815 |
| primary_location.id | pmh:oai:arXiv.org:2501.04815 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2501.04815 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2501.04815 |
| publication_date | 2025-01-08 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.2 | 134 |
| abstract_inverted_index.a | 25, 39, 116, 126 |
| abstract_inverted_index.In | 160 |
| abstract_inverted_index.It | 14 |
| abstract_inverted_index.We | 32 |
| abstract_inverted_index.by | 150, 166 |
| abstract_inverted_index.is | 15 |
| abstract_inverted_index.of | 66, 82, 119 |
| abstract_inverted_index.on | 130, 152 |
| abstract_inverted_index.to | 18, 169 |
| abstract_inverted_index.(1) | 46 |
| abstract_inverted_index.(2) | 88 |
| abstract_inverted_index.(3) | 104 |
| abstract_inverted_index.and | 10, 28, 53, 60, 70, 85, 94, 101, 103, 114, 136, 155 |
| abstract_inverted_index.due | 17 |
| abstract_inverted_index.for | 24, 99, 121 |
| abstract_inverted_index.its | 170 |
| abstract_inverted_index.new | 127 |
| abstract_inverted_index.our | 64, 144 |
| abstract_inverted_index.the | 97, 111, 148 |
| abstract_inverted_index.use | 81 |
| abstract_inverted_index.via | 50 |
| abstract_inverted_index.(SD) | 52 |
| abstract_inverted_index.6.8% | 151 |
| abstract_inverted_index.Open | 138 |
| abstract_inverted_index.[1], | 132 |
| abstract_inverted_index.[2], | 135 |
| abstract_inverted_index.[3]. | 142 |
| abstract_inverted_index.from | 73 |
| abstract_inverted_index.lane | 71 |
| abstract_inverted_index.like | 20 |
| abstract_inverted_index.main | 112 |
| abstract_inverted_index.need | 98 |
| abstract_inverted_index.sets | 125 |
| abstract_inverted_index.that | 44 |
| abstract_inverted_index.with | 6, 35, 76 |
| abstract_inverted_index.(MR), | 56 |
| abstract_inverted_index.11.8% | 167 |
| abstract_inverted_index.B-FDE | 165 |
| abstract_inverted_index.Waymo | 137 |
| abstract_inverted_index.drop, | 78 |
| abstract_inverted_index.error | 149 |
| abstract_inverted_index.model | 146 |
| abstract_inverted_index.novel | 40 |
| abstract_inverted_index.often | 16 |
| abstract_inverted_index.query | 77 |
| abstract_inverted_index.small | 117 |
| abstract_inverted_index.using | 91 |
| abstract_inverted_index.(WOMD) | 141 |
| abstract_inverted_index.Masked | 54 |
| abstract_inverted_index.Motion | 139 |
| abstract_inverted_index.Prompt | 106 |
| abstract_inverted_index.Tuning | 107 |
| abstract_inverted_index.during | 108 |
| abstract_inverted_index.global | 58 |
| abstract_inverted_index.inputs | 75 |
| abstract_inverted_index.masked | 74 |
| abstract_inverted_index.models | 4 |
| abstract_inverted_index.number | 118 |
| abstract_inverted_index.tests, | 162 |
| abstract_inverted_index.Dataset | 140 |
| abstract_inverted_index.PerReg+ | 124, 163 |
| abstract_inverted_index.complex | 12, 21 |
| abstract_inverted_index.context | 59 |
| abstract_inverted_index.dataset | 27 |
| abstract_inverted_index.enables | 79 |
| abstract_inverted_index.prompts | 120 |
| abstract_inverted_index.propose | 33 |
| abstract_inverted_index.queries | 37, 93 |
| abstract_inverted_index.reduces | 147, 164 |
| abstract_inverted_index.smaller | 153 |
| abstract_inverted_index.vehicle | 1 |
| abstract_inverted_index.Adaptive | 105 |
| abstract_inverted_index.Enhanced | 89 |
| abstract_inverted_index.Existing | 0 |
| abstract_inverted_index.Learning | 49 |
| abstract_inverted_index.Register | 36 |
| abstract_inverted_index.approach | 65 |
| abstract_inverted_index.compared | 168 |
| abstract_inverted_index.details. | 62 |
| abstract_inverted_index.enhances | 158 |
| abstract_inverted_index.freezing | 110 |
| abstract_inverted_index.handling | 11 |
| abstract_inverted_index.improves | 86 |
| abstract_inverted_index.nuScenes | 131 |
| abstract_inverted_index.segments | 72 |
| abstract_inverted_index.specific | 26 |
| abstract_inverted_index.struggle | 5 |
| abstract_inverted_index.training | 157 |
| abstract_inverted_index.variant. | 172 |
| abstract_inverted_index.Argoverse | 133 |
| abstract_inverted_index.Perceiver | 34 |
| abstract_inverted_index.capturing | 57 |
| abstract_inverted_index.datasets, | 154 |
| abstract_inverted_index.effective | 80 |
| abstract_inverted_index.efficient | 122 |
| abstract_inverted_index.framework | 43 |
| abstract_inverted_index.handling. | 31 |
| abstract_inverted_index.(PerReg+), | 38 |
| abstract_inverted_index.Dual-Level | 47 |
| abstract_inverted_index.clustering | 100 |
| abstract_inverted_index.contextual | 83 |
| abstract_inverted_index.customized | 23 |
| abstract_inverted_index.multimodal | 30 |
| abstract_inverted_index.optimizing | 115 |
| abstract_inverted_index.prediction | 3, 8, 42 |
| abstract_inverted_index.pretrained | 145 |
| abstract_inverted_index.trajectory | 2, 41 |
| abstract_inverted_index.Remarkable, | 143 |
| abstract_inverted_index.adaptation. | 123 |
| abstract_inverted_index.eliminating | 96 |
| abstract_inverted_index.inefficient | 29 |
| abstract_inverted_index.information | 84 |
| abstract_inverted_index.introduces: | 45 |
| abstract_inverted_index.limitations | 19 |
| abstract_inverted_index.performance | 129 |
| abstract_inverted_index.architecture | 113 |
| abstract_inverted_index.cross-domain | 161 |
| abstract_inverted_index.fine-grained | 61 |
| abstract_inverted_index.fine-tuning, | 109 |
| abstract_inverted_index.pretraining, | 95 |
| abstract_inverted_index.segmentlevel | 68 |
| abstract_inverted_index.suppression; | 102 |
| abstract_inverted_index.trajectories | 69 |
| abstract_inverted_index.Additionally, | 63 |
| abstract_inverted_index.Multimodality | 90 |
| abstract_inverted_index.architectures | 22 |
| abstract_inverted_index.interactions. | 13 |
| abstract_inverted_index.multi-dataset | 156 |
| abstract_inverted_index.Reconstruction | 55 |
| abstract_inverted_index.Representation | 48 |
| abstract_inverted_index.non-pretrained | 171 |
| abstract_inverted_index.reconstructing | 67 |
| abstract_inverted_index.register-based | 92 |
| abstract_inverted_index.uncertainties, | 9 |
| abstract_inverted_index.generalization. | 159 |
| abstract_inverted_index.generalization; | 87 |
| abstract_inverted_index.state-of-the-art | 128 |
| abstract_inverted_index.Self-Distillation | 51 |
| abstract_inverted_index.generalizability, | 7 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |