Pith. sign in

REVIEW 5 cited by

Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans

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 2001.00735 v2 pith:H7AZKUSC submitted 2020-01-03 cs.CV cs.RO

Nachiket Deo , Mohan M. Trivedi This is my paper
classification cs.CVcs.RO
keywords trajectoriesscenetrajectoryconditionedfuturemaxentpolicystructure
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We address the problem of forecasting pedestrian and vehicle trajectories in unknown environments, conditioned on their past motion and scene structure. Trajectory forecasting is a challenging problem due to the large variation in scene structure and the multimodal distribution of future trajectories. Unlike prior approaches that directly learn one-to-many mappings from observed context to multiple future trajectories, we propose to condition trajectory forecasts on plans sampled from a grid based policy learned using maximum entropy inverse reinforcement learning (MaxEnt IRL). We reformulate MaxEnt IRL to allow the policy to jointly infer plausible agent goals, and paths to those goals on a coarse 2-D grid defined over the scene. We propose an attention based trajectory generator that generates continuous valued future trajectories conditioned on state sequences sampled from the MaxEnt policy. Quantitative and qualitative evaluation on the publicly available Stanford drone and NuScenes datasets shows that our model generates trajectories that are diverse, representing the multimodal predictive distribution, and precise, conforming to the underlying scene structure over long prediction horizons.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Mode Collapse Happens: Evaluating Critical Interactions in Joint Trajectory Prediction Models

    cs.RO 2025-06 conditional novelty 6.0 of 10

    A new evaluation framework measures mode collapse, correctness, and coverage of interaction modes in joint trajectory prediction, and shows that current models do collapse interaction modes in safety-critical scenes.

  2. GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction

    cs.CV 2025-06 conditional novelty 6.0 of 10

    GoIRL couples maximum entropy inverse reinforcement learning with vectorized lane-graph features to predict multiple future trajectories, reporting competitive benchmark numbers but not the stated state-of-the-art on ...

  3. DeMo++: Motion Decoupling for Autonomous Driving

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A decoupled mode/state query representation with hybrid Attention+Mamba and cross-scene interaction achieves top results on Argoverse 2, nuScenes, nuPlan, and NAVSIM, but the Argoverse 2 and nuPlan evaluations use a r...

  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.

  5. AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    AMD combines momentum and decoupled contrastive learning, trajectory augmentations, and online clustering to improve prediction on rare driving scenarios.

Pith tools