Pith. sign in

REVIEW 4 cited by

UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.15098 v3 pith:FO2PM2CC submitted 2024-03-22 cs.CV

Lan Feng , Mohammadhossein Bahari , Kaouther Messaoud Ben Amor , Éloi Zablocki , Matthieu Cord , Alexandre Alahi This is my paper
classification cs.CV
keywords unitrajdatadatasetdatasetspredictiontrajectoryvehicleframework
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored. While these questions can be studied by employing multiple datasets, it is challenging due to several discrepancies, e.g., in data formats, map resolution, and semantic annotation types. To address these challenges, we introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria, presenting new opportunities for the vehicle trajectory prediction field. In particular, using UniTraj, we conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. However, enlarging data size and diversity can substantially improve performance, leading to a new state-of-the-art result for the nuScenes dataset. We provide insights into dataset characteristics to explain these findings. The code can be found here: https://github.com/vita-epfl/UniTraj

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Active Probing with Multimodal Predictions for Motion Planning

    cs.RO 2025-07 conditional novelty 6.0 of 10

    An MPC framework that uses a Wasserstein-based risk metric and a Boltzmann model of agent behavior to actively probe and infer other vehicles' intentions in multimodal prediction settings.

  2. Improving Traffic Signal Data Quality for the Waymo Open Motion Dataset

    cs.RO 2025-06 conditional novelty 6.0 of 10

    A trajectory-based, ring-and-barrier-constrained method imputes 71.7% of missing traffic signal states in the Waymo Open Motion Dataset and lowers the estimated red-light running rate from 15.7% to 2.9%.

  3. HiLO: High-Level Object Fusion for Autonomous Driving using Transformers

    cs.RO 2025-06 conditional novelty 6.0 of 10

    A transformer-based high-level fusion method (HiLO) improves F1 by up to 25.9 points over Kalman-filter baselines on a real urban and highway dataset, with code and data promised publicly.

  4. Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics

    cs.CV 2025-07 conditional novelty 5.0 of 10

    FiM predicts future trajectories by first learning a reward distribution over a grid world via inverse reinforcement learning, then rolling out intention plans that condition a Mamba-enhanced trajectory decoder.

Pith tools