PaperScope
LIVE · 2026-09-29 05:40 UTC

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

Alan Debbas, Edwin Meriaux, Gregory Dudek

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.32783 v1
Category
Submitted
2026-09-26

Abstract

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.

Comment: 5 pages, 4 figures, 1 table, 2 algorithms. Accepted to the 2026 IEEE MIT Undergraduate Research Technology Conference (URTC)

arXiv abs page · PDF · same-day batch