Scholarlink

<p>This study presents a novel approach to addressing the task scheduling problem in fog-based Internet of Everything (IoE) environments, drawing inspiration from RoboSoccer’s obstacle avoidance and navigation techniques. This methodology exploits RoboSoccer’s dynamic adaptability, advanced problem-solving capabilities, and established simulation environments to improve task scheduling efficiency in IoE systems. By integrating feature engineering and reinforcement learning, the task scheduling challenge is reformulated within the RoboSoccer domain, enabling the application of advanced control and decision-making strategies. The core objective of this study is to evaluate the effectiveness of this mapping on the performance of various algorithms, with a focus on five key metrics: Makespan (MS), Resource Utilization Ratio (RUR), Average Task Completion Time (ATCT), Resource Allocation Accuracy (RAA), and in Processing Speed (PS). One of the key benefits of this method is its ability to quickly adapt to changes in dynamic environments, making it a suitable solution for real-world IoE applications, reducing complexity in agent interactions, and improving algorithm reusability through knowledge transfer. Furthermore, RoboSoccer’s diverse simulators ensure scalability, making the method applicable across a wide range of task scheduling scenarios. Experimental results show total average improvements of 19.56% in MS, 6.68% in RUR, 4.87% in ATCT, 0.61% in RAA, and 0.29% in PS, thus demonstrating the effectiveness of the proposed RoboSoccer Mapping Trick in advanced recurrent RL algorithms. This groundbreaking methodology not only redefines RoboSoccer’s potential in optimizing task scheduling in resource-constrained IoE environments but also sets the stage for revolutionary advancements in problem-solving techniques across diverse domains.</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

The mapping trick: leveraging RoboSoccer obstacle avoidance and navigation for advanced task scheduling solutions in foggy IoE ecosystems

  • 期刊论文

  • 发表日期：

    2025年4月15日

查看全文
  • Seyed Omid Azarkasb,
  • Seyed Hossein Khasteh

摘要

This study presents a novel approach to addressing the task scheduling problem in fog-based Internet of Everything (IoE) environments, drawing inspiration from RoboSoccer’s obstacle avoidance and navigation techniques. This methodology exploits RoboSoccer’s dynamic adaptability, advanced problem-solving capabilities, and established simulation environments to improve task scheduling efficiency in IoE systems. By integrating feature engineering and reinforcement learning, the task scheduling challenge is reformulated within the RoboSoccer domain, enabling the application of advanced control and decision-making strategies. The core objective of this study is to evaluate the effectiveness of this mapping on the performance of various algorithms, with a focus on five key metrics: Makespan (MS), Resource Utilization Ratio (RUR), Average Task Completion Time (ATCT), Resource Allocation Accuracy (RAA), and in Processing Speed (PS). One of the key benefits of this method is its ability to quickly adapt to changes in dynamic environments, making it a suitable solution for real-world IoE applications, reducing complexity in agent interactions, and improving algorithm reusability through knowledge transfer. Furthermore, RoboSoccer’s diverse simulators ensure scalability, making the method applicable across a wide range of task scheduling scenarios. Experimental results show total average improvements of 19.56% in MS, 6.68% in RUR, 4.87% in ATCT, 0.61% in RAA, and 0.29% in PS, thus demonstrating the effectiveness of the proposed RoboSoccer Mapping Trick in advanced recurrent RL algorithms. This groundbreaking methodology not only redefines RoboSoccer’s potential in optimizing task scheduling in resource-constrained IoE environments but also sets the stage for revolutionary advancements in problem-solving techniques across diverse domains.