REVIEW 3 cited by
$AIR^2$ for Interaction Prediction
Not yet reviewed by Pith; the record is open.
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
abstract
The 2021 Waymo Interaction Prediction Challenge introduced a problem of predicting the future trajectories and confidences of two interacting agents jointly. We developed a solution that takes an anchored marginal motion prediction model with rasterization and augments it to model agent interaction. We do this by predicting the joint confidences using a rasterized image that highlights the ego agent and the interacting agent. Our solution operates on the cartesian product space of the anchors; hence the $"^2"$ in $AIR^2$. Our model achieved the highest mAP (the primary metric) on the leaderboard.
Forward citations
Cited by 3 Pith papers
-
TrajFlow: Multi-modal Motion Prediction via Flow Matching
TrajFlow uses flow matching with a multi-query transformer to predict multiple trajectories in one pass and a Plackett-Luce ranking loss to improve confidence scores, reporting small SOTA gains on WOMD.
-
Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Prediction
Vehicles whose multimodal predictions are confident and concentrated are frozen early in a level-k game planner, reducing compute and modestly improving accuracy.
-
JAM: Keypoint-Guided Joint Prediction after Classification-Aware Marginal Proposal for Multi-Agent Interaction
A two-stage joint trajectory prediction model that uses trajectory-type classification in a marginal proposal stage and keypoint-guided joint refinement beats prior methods on Waymo interaction metrics for position error.
Discussion (0). Continue with ORCID to comment.