# CollisionGAT: Controller-Agnostic One-Step Collision Screening for Multi-Agent Motion

arXiv: https://arxiv.org/abs/2609.32783 · HTML: https://mlsanity.com/paper/2609.32783/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 8 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control](https://mlsanity.com/paper/2401.14554/) (2024)
- [Learning-Based Proxy Collision Detection for Robot Motion Planning Applications](https://mlsanity.com/paper/1902.08164/) (2019)
- [Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation](https://mlsanity.com/paper/2210.09378/) (2022)
- [On Mobile Ad Hoc Networks for Coverage of Partially Observable Worlds](https://mlsanity.com/paper/2512.09495/) (2025)

## Abstract (arXiv)

Before a team of robots moves, each proposed step must be checked for collisions with other robots and with obstacles. We present CollisionGAT, a graph-attention network that reads the current and proposed states of moving agents together with locally relevant stationary obstacles and returns one collision-risk score per moving agent. Any controller can use these scores to accept, repair, replan, or postpone a proposed step. We mount CollisionGAT on a continuous path-following controller and on GATeD, an obstacle-blind D* Lite planner that uses typed vetoes to update its planning graphs. Exact geometric checks supply the training labels and independently audit every executed step.