Reducing Collision Risk in Multi-Agent Path Planning: Application to Air traffic Management

TL;DR

This paper introduces a game-theoretic approach to reduce collision risks in multi-agent path planning, specifically applied to air traffic management, by modeling the problem as a Markov decision process congestion game.

Contribution

It formulates a novel congestion game with stochastic dynamics and demonstrates its application to real-world air traffic collision risk reduction.

Findings

Nash equilibria align with KKT points of a non-convex optimization problem.

Application to historical flight data shows effective collision risk reduction.

Provides a new framework for multi-agent collision avoidance in stochastic environments.

Abstract

To minimize collision risks in the multi-agent path planning problem with stochastic transition dynamics, we formulate a Markov decision process congestion game with a multi-linear congestion cost. Players within the game complete individual tasks while minimizing their own collision risks. We show that the set of Nash equilibria coincides with the first-order KKT points of a non-convex optimization problem. Our game is applied to a historical flight plan over France to reduce collision risks between commercial aircraft.