# AIR2 for Interaction Prediction

arXiv: https://arxiv.org/abs/2111.08184 · HTML: https://mlsanity.com/paper/2111.08184/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 1 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 1 of 1)

- [MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction](https://mlsanity.com/paper/1910.05449/) (2019)

## Built on by (most cited first, 9 of 9)

- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving](https://mlsanity.com/paper/2303.05760/) (2023)
- [MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying](https://mlsanity.com/paper/2306.17770/) (2023)
- [M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction](https://mlsanity.com/paper/2202.11884/) (2022)
- [TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction](https://mlsanity.com/paper/2303.04116/) (2023)
- [FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs](https://mlsanity.com/paper/2211.16197/) (2022)
- [R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement](https://mlsanity.com/paper/2211.08609/) (2022)
- [BiFF: Bi-level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction](https://mlsanity.com/paper/2306.14161/) (2023)
- [Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Prediction](https://mlsanity.com/paper/2506.05810/) (2025)

## Abstract (arXiv)

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 AIR2. Our model achieved the highest mAP (the primary metric) on the leaderboard.