Scholarlink

<p>Industrial automation relies heavily on robust and efficient robotic vision systems for tasks such as object detection, localization, and manipulation. This paper presents a novel approach to optimizing robotic vision using Modified Trace and Forage (MTF) and Coati Optimization Algorithm (COA) algorithms. The study focuses on enhancing the performance of Convolutional Neural Networks (CNNs) through preprocessing with MTF-COA algorithms and weight optimization during training. A comprehensive quantitative analysis is conducted to evaluate the effectiveness of the proposed approach in improving the accuracy and efficiency of robotic vision systems. Experimental results demonstrate significant enhancements in object recognition and localization tasks, highlighting the potential of MTF-COA algorithms for advancing industrial automation. The findings of this research contribute to the development of next-generation robotic vision systems capable of meeting the demanding requirements of industrial applications.</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

Optimization of Robotics Vision Using Modified MTF-COA Algorithms

  • 期刊论文

  • 发表日期：

    2025年11月27日

查看全文
  • Yogesh Kamble,
  • Nitin K. Kamble,
  • Sandeep Sarnobat,
  • Sudhanshu Pathak,
  • Sachin Mane

摘要

Industrial automation relies heavily on robust and efficient robotic vision systems for tasks such as object detection, localization, and manipulation. This paper presents a novel approach to optimizing robotic vision using Modified Trace and Forage (MTF) and Coati Optimization Algorithm (COA) algorithms. The study focuses on enhancing the performance of Convolutional Neural Networks (CNNs) through preprocessing with MTF-COA algorithms and weight optimization during training. A comprehensive quantitative analysis is conducted to evaluate the effectiveness of the proposed approach in improving the accuracy and efficiency of robotic vision systems. Experimental results demonstrate significant enhancements in object recognition and localization tasks, highlighting the potential of MTF-COA algorithms for advancing industrial automation. The findings of this research contribute to the development of next-generation robotic vision systems capable of meeting the demanding requirements of industrial applications.