Resilient and Efficient Allocation for Large-Scale Autonomous Fleets via Decentralized Coordination

TL;DR

This paper introduces a decentralized resource allocation method for large autonomous fleets that improves resilience and efficiency by combining distributional predictions, local risk models, and lightweight consensus algorithms, validated on urban and satellite networks.

Contribution

It presents a novel side-information-aware, decentralized coordination framework that scales efficiently and reduces failure rates significantly in large autonomous systems.

Findings

Reduces failure rates by 30-55% compared to baselines.

Scales to thousands of agents with near-linear runtime.

Maintains high feasibility probability under uncertainty.

Abstract

Operating large autonomous fleets demands fast, resilient allocation of scarce resources (such as energy and fuel, charger access and maintenance slots, time windows, and communication bandwidth) under uncertainty. We propose a side-information-aware approach for resource allocation at scale that combines distributional predictions with decentralized coordination. Local side information shapes per-agent risk models for consumption, which are coupled through chance constraints on failures. A lightweight consensus-ADMM routine coordinates agents over a sparse communication graph, enabling near-centralized performance while avoiding single points of failure. We validate the framework on real urban road networks with autonomous vehicles and on a representative satellite constellation, comparing against greedy, no-side-information, and oracle central baselines. Our method reduces failure rates by 30-55% at matched cost and scales to thousands of agents with near-linear runtime, while preserving feasibility with high probability.