Scholarlink

<p>Robots are increasingly utilized in healthcare applications through Ambient Assisted Living techniques to enhance lifestyles and improve task efficiency. However, optimizing task allocation in multiple-robot systems remains a significant challenge due to dynamic requirements, robot heterogeneity, and computational constraints. This paper introduces the Bacterial Foraging Optimization Building Block Distribution (BFOBBD) algorithm, a novel approach for dynamically allocating tasks to robots based on utility, interdependence, and computational efficiency. The proposed algorithm addresses the limitations of existing methods by integrating probabilistic modeling with multivariate factorization to optimize task allocation. Experimental results demonstrate that the BFOBBD algorithm reduces task allocation time to 4.23&#xa0;s, significantly outperforming methods such as FA-POWERSET-MART (20.19&#xa0;s) and FA-QABC-MART (5.26&#xa0;s). This work contributes a robust, scalable solution for task allocation in healthcare environments, enabling robots to handle multiple tasks efficiently with minimal computation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bacterial foraging optimization building block distribution algorithm based dynamic allocation in multiple robotic system

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月10日

查看全文
  • P. Anand Raj,
  • S. Palanimurugan,
  • S. Senthilkumar

摘要

Robots are increasingly utilized in healthcare applications through Ambient Assisted Living techniques to enhance lifestyles and improve task efficiency. However, optimizing task allocation in multiple-robot systems remains a significant challenge due to dynamic requirements, robot heterogeneity, and computational constraints. This paper introduces the Bacterial Foraging Optimization Building Block Distribution (BFOBBD) algorithm, a novel approach for dynamically allocating tasks to robots based on utility, interdependence, and computational efficiency. The proposed algorithm addresses the limitations of existing methods by integrating probabilistic modeling with multivariate factorization to optimize task allocation. Experimental results demonstrate that the BFOBBD algorithm reduces task allocation time to 4.23 s, significantly outperforming methods such as FA-POWERSET-MART (20.19 s) and FA-QABC-MART (5.26 s). This work contributes a robust, scalable solution for task allocation in healthcare environments, enabling robots to handle multiple tasks efficiently with minimal computation.