A Study on Multi-Robot Task Allocation in Railway Scenarios Based on the Improved NSGA-II Algorithm

TL;DR

This paper proposes an improved algorithm for multi-robot task allocation in railway maintenance to optimize efficiency and reduce costs.

Contribution

The study introduces a hybrid NSGA-II and MOPSO algorithm with dynamic task planning and adaptive parameters for railway scenarios.

Findings

The proposed algorithm reduces makespan and total travel distance for railway maintenance robots.

Dynamic task planning and multi-elite archive strategy improve solution diversity and prevent premature convergence.

Experiments confirm the algorithm's effectiveness in varying task sizes and robot quantities.

Abstract

With the advent of Industry 4.0, the seamless integration of industrial systems and unmanned technologies has significantly accelerated the development of smart industries. However, the research on task allocation for railway maintenance robots remains limited, particularly with respect to optimizing costs and efficiency within smart railway systems. To address this gap, the present study explores multi-robot task allocation for automated orbital bolt maintenance, aiming to enhance operational efficiency by minimizing both makespan and total travel distance for all robots. To achieve this, an improved hybrid algorithm combining NSGA-II and MOPSO is proposed. Initially, a dynamic task planning method, tailored to the specific conditions of railway operations, is developed. This method uses the coordinates of track bolts to extract environmental features, enabling the dynamic partitioning of task areas. Subsequently, a multi-elite archive strategy is introduced, along with an adaptive mechanism for adjusting crossover and mutation probabilities. This ensures the preservation and maintenance of multiple solutions across various Pareto fronts, effectively mitigating the premature convergence commonly observed in traditional NSGA-II algorithms. Moreover, the integration of the MOPSO algorithm strikes a balance between local and global search capabilities, thereby enhancing both optimization efficiency and solution quality. Finally, a series of experiments, conducted with varying task sizes and robot quantities during the railway maintenance window, validate the effectiveness and improved performance of the proposed algorithm in addressing the multi-robot task allocation problem.

Figures