Unification of Consensus-Based Multi-Objective Optimization and Multi-Robot Path Planning
Michael P. Wozniak
TL;DR
The paper addresses unifying consensus-based multi-agent control with multi-objective optimization in a rover path-planning context for lunar exploration. It formulates a dual-objective problem with $f_1$ representing explored area and $f_2$ representing consensus measured by RSS, normalizes them via utopia points to form $\phi_1$ and $\phi_2$, and minimizes $f = a_1\phi_1 + a_2\phi_2$ using Sequential Quadratic Programming (SQP). The approach optimizes edge weights and the lead rover's heading to achieve fast convergence and robust consensus while maximizing exploration, demonstrated through three simulations on a four-agent graph. The results show fast convergence (often under 1 second), heading agreement guided by a non-cooperative leader, and a path that maximizes area coverage, illustrating a practical, scalable framework for autonomous multi-robot lunar missions and related domains.
Abstract
Multi-agent systems seeking consensus may also have other objective functions to optimize, requiring the research of multi-objective optimization in consensus. Several recent publications have explored this domain using various methods such as weighted-sum optimization and penalization methods. This paper reviews the state of the art for consensus-based multi-objective optimization, poses a multi-agent lunar rover exploration problem seeking consensus and maximization of explored area, and achieves optimal edge weights and steering angles by applying SQP algorithms.