Papers › TNT: Target-driveN Trajectory Prediction

TNT: Target-driveN Trajectory Prediction

19 Aug 2020arXiv:2008.08294archive 2025-07-28

Hang Zhao, Jiyang Gao, Tian Lan, Chen Sun, Benjamin Sapp, Balakrishnan Varadarajan, Yue Shen, Yi Shen, Yuning Chai, Cordelia Schmid, Cong-Cong Li, Dragomir Anguelov

Predicting the future behavior of moving agents is essential for real world applications. It is challenging as the intent of the agent and the corresponding behavior is unknown and intrinsically multimodal. Our key insight is that for prediction within a moderate time horizon, the future modes can be effectively captured by a set of target states. This leads to our target-driven trajectory prediction (TNT) framework. TNT has three stages which are trained end-to-end. It first predicts an agent's potential target states T steps into the future, by encoding its interactions with the environment and the other agents. TNT then generates trajectory state sequences conditioned on targets. A final stage estimates trajectory likelihoods and a final compact set of trajectory predictions is selected. This is in contrast to previous work which models agent intents as latent variables, and relies on test-time sampling to generate diverse trajectories. We benchmark TNT on trajectory prediction of vehicles and pedestrians, where we outperform state-of-the-art on Argoverse Forecasting, INTERACTION, Stanford Drone and an in-house Pedestrian-at-Intersection dataset.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

henry1iu/tnt-trajectory-prediction mentioned on GitHubpytorch report
henry1iu/tnt-trajectory-predition mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Motion ForecastingPredictionTrajectory Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 DAC (K=6) 0.9889 #148 of 299 Archive leaderboard report
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 MR (K=1) 0.7097 #148 of 299 Archive leaderboard report
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 MR (K=6) 0.1656 #148 of 299 Archive leaderboard report
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 brier-minFDE (K=6) 2.1401 #148 of 299 Archive leaderboard report
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 minADE (K=1) 2.174 #148 of 299 Archive leaderboard report
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 minADE (K=6) 0.9097 #148 of 299 Archive leaderboard report
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 minFDE (K=1) 4.9593 #148 of 299 Archive leaderboard report
Motion Forecasting Argoverse CVPR 2020 TNT - CoRL20 minFDE (K=6) 1.4457 #148 of 299 Archive leaderboard report
Trajectory Prediction INTERACTION Dataset - Validation TNT minADE6 0.21 #2 of 4 Archive leaderboard report
Trajectory Prediction INTERACTION Dataset - Validation TNT minFDE6 0.67 #2 of 4 Archive leaderboard report
Trajectory Prediction PAID TNT minADE3 0.18 #3 of 3 Archive leaderboard report
Trajectory Prediction PAID TNT minFDE3 0.32 #3 of 3 Archive leaderboard report
Trajectory Prediction Stanford Drone TNT ADE (8/12) @K=5 12.23 #19 of 24 Archive leaderboard report
Trajectory Prediction Stanford Drone TNT FDE(8/12) @K=5 21.16 #19 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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