Browse State-of-the-Art › Trajectory Prediction

Trajectory Prediction

341 papers with code · 32 benchmarks · 35 datasets archive 2025-07-28

Computer VisionTime Series

Trajectory Prediction is the problem of predicting the short-term (1-3 seconds) and long-term (3-5 seconds) spatial coordinates of various road-agents such as cars, buses, pedestrians, rickshaws, and animals, etc. These road-agents have different dynamic behaviors that may correspond to aggressive or conservative driving styles.

Source: Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

32 leaderboard tables shown for this task, 32 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 32 until expanded.

Syntology 3 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): ETH/UCY (2 judged, 0 placed), NGSIM (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
nuScenes (34 rows) UniTraj (MTR) UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
Stanford Drone (24 rows) NSP-SFM Human Trajectory Prediction via Neural Social Physics code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
ETH/UCY (20 rows) NSP Human Trajectory Prediction via Neural Social Physics code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
ETH (5 rows) Social-Implicit Social-Implicit: Rethinking Trajectory Prediction Evaluation and... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
JAAD (5 rows) SGNet Stepwise Goal-Driven Networks for Trajectory Prediction code — Compare
PIE (5 rows) SGNet Stepwise Goal-Driven Networks for Trajectory Prediction code — Compare
ActEV (4 rows) Pishgu Pishgu: Universal Path Prediction Network Architecture for... code — Compare
INTERACTION Dataset - Validation (4 rows) ITRA Imagining The Road Ahead: Multi-Agent Trajectory Prediction via... code Syntology 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
PAID (3 rows) DESIRE DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents code Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
TrajNet++ (3 rows) Social-NCE + Social-LSTM Social NCE: Contrastive Learning of Socially-aware Motion Representations code Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
ApolloScape (2 rows) SpectralCows Forecasting Trajectory and Behavior of Road-Agents Using Spectral... — — Compare
HEV-I (2 rows) SGNet Stepwise Goal-Driven Networks for Trajectory Prediction code — Compare
NGSIM (2 rows) Pishgu Pishgu: Universal Path Prediction Network Architecture for... code — Compare
Apolloscape Trajectory (1 row) Trafficpredict TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents code — Compare
Argoverse (1 row) HeteroGCN Dynamic Scenario Representation Learning for Motion Forecasting... — — Compare
Argoverse2 (1 row) HeteroGCN Dynamic Scenario Representation Learning for Motion Forecasting... — — Compare
ETH BIWI Walking Pedestrians dataset (1 row) Social Ways Social Ways: Learning Multi-Modal Distributions of Pedestrian... code — Compare
ForkingPaths (1 row) Multiverse The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
GPS (1 row) Support Vector Machines Inferring hybrid transportation modes from sparse GPS data using a... — — Compare
GTA-IM Dataset (1 row) Skeleton-Graph Skeleton-Graph: Long-Term 3D Motion Prediction From 2D... code — Compare
Hotel BIWI Walking Pedestrians dataset (1 row) Social Ways Social Ways: Learning Multi-Modal Distributions of Pedestrian... code — Compare
Lyft Level 5 (1 row) SpectralCows Forecasting Trajectory and Behavior of Road-Agents Using Spectral... — — Compare
PROX (1 row) Skeleton-Graph Skeleton-Graph: Long-Term 3D Motion Prediction From 2D... code — Compare
SDD (1 row) Multiclass-SGCN (ours) Multiclass-SGCN: Sparse Graph-based Trajectory Prediction with... code — Compare
STATS SportVu NBA [ATK] (1 row) DAG-Net DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting code — Compare
STATS SportVu NBA [DEF] (1 row) DAG-Net DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting code — Compare
TRAF (1 row) TraPHic TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic... code Syntology 0 ran · 1 unverified Compare
TrajAir: A General Aviation Trajectory Dataset (1 row) TrajAirNet Predicting Like A Pilot: Dataset and Method to Predict... code — Compare
UCY (1 row) Social-Implicit Social-Implicit: Rethinking Trajectory Prediction Evaluation and... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
YJMob100K@B (1 row) ST-MoE-BERT ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for... code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified Compare
YJMob100K@C (1 row) ST-MoE-BERT ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for... code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified Compare
YJMob100K@D (1 row) ST-MoE-BERT ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for... code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

35 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 35 until expanded.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 1,004 · with a code link: 341 · where Syntology ran a sample: 87 (76 with a run with no instrument failure, 11 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (87 of 1,004 tagged: 76 with a run with no instrument failure, 11 where every run was a failure of Syntology's instrument)

Page 1 of 11: papers 1 to 100 of 1,004, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 30 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections