Robust multi-agent flight paths improve safety in decentralized air traffic
Strategically Robust Game-Theoretic Multi-Agent Trajectory Optimization
Computer Science and Game TheoryMultiagent Systems
Summary
When multiple autonomous flights plan their paths without a central controller, they need to predict what others will do to avoid collisions. The authors introduce a way for each flight to plan its path while considering possible small unexpected changes in others' plans, making the whole system safer. They use a game theory approach that can efficiently handle these uncertainties and still find good flight paths. Their experiments show that this method reduces risky situations without much extra computation.
What this means in practice
- •For aviation traffic managers: Enhance autonomous flight planning by incorporating robustness against unexpected control changes in decentralized air mobility operations.
- •For autonomous vehicle developers: Create multi-agent trajectory planning algorithms that maintain safety under uncertainty in other agents' control inputs.
Authors
Victor L. Qin, Nicolas Lanzetti, Saverio Bolognani, Hamsa Balakrishnan
Abstract
Aviation authorities worldwide expect Advanced Air Mobility (AAM) traffic management to be decentralized among service providers, requiring AAM flights to autonomously plan trajectories by predicting other flights' control inputs rather than relying on centralized coordination. Game-theoretic approaches that formulate multi-agent collision avoidance as an exact dynamic potential game can efficiently find open-loop equilibria, but they assume that agents exactly follow their equilibrium trajectories---an unrealistic assumption given uncertainties in actuation, perception, and computation. We propose a strategically robust formulation where each agent protects against a fictitious adversary that, for each timestep, perturbs other agents' control inputs within a bounded budget to minimize distance at that timestep. We show that, under reasonable assumptions on agents' distance cost and robustness levels, the strategically robust game remains an exact dynamic potential game and admits a quasi-closed-form solution to the inner adversarial problem for linear dynamics, which limits computational overhead. Experiments with up to eight agents using logarithmic distance costs show that strategic robustness selects more robust trajectories in high-collision-risk configurations while leaving low-risk trajectories nearly unchanged, with only a modest increase in runtime.