Decentralized Autonomous Traffic Management through Corridor Networks

2026-06-22

AI Summary

This study addresses the lack of scalable, decentralized traffic management solutions for high-density autonomous aerial vehicles operating in complex corridor networks, where traditional centralized approaches struggle to coordinate large-scale heterogeneous fleets. The authors propose a decentralized multi-agent reinforcement learning strategy that enables efficient global traffic flow using only local observations. Notably, the method achieves zero-shot transfer across network topologies without requiring central coordination or model retraining, supporting autonomous navigation of heterogeneous aircraft under dynamic changes in traffic density and network structure. Experimental results demonstrate superior performance in boundary compliance, mission completion rate, average speed, path efficiency, and inter-vehicle separation maintenance, confirming the approach’s effectiveness and robustness.

Abstract

As autonomous aircraft are introduced at scale and traffic density increases, centralized management becomes insufficient to coordinate the large numbers of crewed and uncrewed aircraft. Dedicated Advanced Air Mobility (AAM) corridors have therefore been proposed for organizing high-density autonomous traffic flows. The desire to scalably provide autonomous aircraft flexibility in trajectory planning motivates the development of decentralized approaches to traffic management in AAM corridors. In this work, we extend a multi-agent reinforcement learning (MARL) approach to address the challenge of decentralized traffic flow management in air corridor networks. We test policies trained in a single-corridor setting on increasingly complex multi-corridor networks with combinations of merges and splits in a zero-shot manner. Experimental results demonstrate that learned behaviors transfer well to scenarios with varying traffic density, network geometry, and heterogeneous vehicle performance, without needing centralized coordination or model retraining. We evaluate system-level performance in terms of conformance to corridor boundaries, completion rates, average speeds, distance traveled, and maintenance of inter-aircraft separation. We find that although our policies require only locally coordinated entry, traversal, and exit behaviors, they collectively produce desirable traffic flows through the corridor network.

Problem

• Decentralized Traffic Management
• Autonomous Aircraft
• Air Corridor Networks
• Advanced Air Mobility
• Scalable Coordination

Innovation

• decentralized traffic management
• multi-agent reinforcement learning
• Advanced Air Mobility corridors
• zero-shot transfer
• autonomous aircraft coordination