Multi-objective collaborative optimization for multi-robot systems with high coupling characteristics

doi:10.1016/j.swevo.2026.102387

Return

Multi-objective collaborative optimization for multi-robot systems with high coupling characteristics

2026-04-17

PRE

DOI：10.1016/j.swevo.2026.102387

Original

Original request for help

Save

Abstract

En 中文

Multi-robot welding systems are highly suitable for mass production in modern manufacturing, especially for optimizing the large-scale manufacturing processes of standard components in automotive manufacturing industry. However, collaborative planning in such systems involves highly coupled sub-problems, including weld point allocation, welding sequence planning and posture planning, robot motion path generation, external axis positioning, and welding gun actuation, all under stringent industrial constraints. To address these challenges, this paper proposes a collaborative planning framework for single-station multi-robot welding systems. A three-objective optimization model is established, addressing weld point allocation, robot welding sequences, and welding posture selection. To effectively solve this model, problem-specific population initialization, encoding–decoding schemes, and tailored crossover and mutation operators are designed and integrated into an advanced multi-objective optimization algorithm. Experimental results demonstrate that the proposed method consistently outperforms state-of-the-art multi-objective optimization approaches in terms of convergence and solution quality. Moreover, the proposed framework is applied to the coordination planning of actual multi-robot systems, revealing that the solution presented in this paper can enhance factory-scale production efficiency and holds significant practical implications for optimizing highly coupled welding systems.

Keywords:

Multi-robot welding

Collaborative planning

Multi-objective optimization

Weld point allocation

Posture selection