- 要旨で参照されている研究:GATeD(obstacle-blind D* Lite planner with typed vetoes)。
- 関連手法:Graph Attention Network (GAT)、D* Lite planner。
- 同分野の定番:マルチエージェント衝突回避のための学習ベース手法(例:Collision Avoidance with Deep Reinforcement Learning)、幾何学的衝突チェック(例:FCL, Bullet)。
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.