Cost Adaptation for Robust Decentralized Swarm Behaviour

TL;DR

This paper introduces a cost adaptation mechanism for decentralized receding horizon control in swarm robotics, enabling flexible, efficient, and robust multi-agent coordination under network delays and heterogeneity.

Contribution

We propose a meta-learning based cost adaptation method for D-RHC that improves swarm control robustness and scalability in complex, networked environments.

Findings

Cost adaptation improves task efficiency in large swarms.

Method handles network delays and agent heterogeneity.

Validated on a simulated exploration task with network failures.

Abstract

Decentralized receding horizon control (D-RHC) provides a mechanism for coordination in multi-agent settings without a centralized command center. However, combining a set of different goals, costs, and constraints to form an efficient optimization objective for D-RHC can be difficult. To allay this problem, we use a meta-learning process -- cost adaptation -- which generates the optimization objective for D-RHC to solve based on a set of human-generated priors (cost and constraint functions) and an auxiliary heuristic. We use this adaptive D-RHC method for control of mesh-networked swarm agents. This formulation allows a wide range of tasks to be encoded and can account for network delays, heterogeneous capabilities, and increasingly large swarms through the adaptation mechanism. We leverage the Unity3D game engine to build a simulator capable of introducing artificial networking failures and delays in the swarm. Using the simulator we validate our method on an example coordinated exploration task. We demonstrate that cost adaptation allows for more efficient and safer task completion under varying environment conditions and increasingly large swarm sizes. We release our simulator and code to the community for future work.