Scholarlink

<p>Controlling Omni-Wheel Drive Mobile Robot Systems (OWDMRS) presents unique challenges due to their ability to move in multiple directions such as rotation, sideways, and forward/backward motion while minimizing energy consumption and voltage fluctuations. This study introduces a novel framework that enhances motion control and trajectory tracking by integrating an advanced fractional-order proportional–integral–derivative (FOPID) controller with an adaptive neuro-fuzzy inference system (ANFIS). To optimize controller performance, six different optimization algorithms are compared are Accelerated Convergence Black Hole Optimization (ACBHO), Black Hole Optimization (BHO), Aquila Optimizer (AO), Hybrid Firefly Particle Swarm Optimization (HFPSO), Enhanced JAYA (EJAYA), and Sunflower Optimizer (SFO). Among these, the proposed ACBHO algorithm significantly improved trajectory tracking accuracy and control efficiency. The framework effectively manages voltage regulation and enhances motion precision by fine-tuning FOPID and ANFIS parameters. These results demonstrate the potential of ACBHO-based optimization as a robust solution for improving control system performance in advanced mobile robotics 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

Accelerated black hole optimization algorithm with enhanced FOPID controller for omni-wheel drive mobile robot system

  • 期刊论文

  • 发表日期：

    2025年6月8日

查看全文
  • Noorulden Basil,
  • Hamzah M. Marhoon,
  • Dheyaaldeen Faez Sahib,
  • Abdullah Fadhil Mohammed,
  • Hussein Mohammed Ridha,
  • Alfian Ma’arif

摘要

Controlling Omni-Wheel Drive Mobile Robot Systems (OWDMRS) presents unique challenges due to their ability to move in multiple directions such as rotation, sideways, and forward/backward motion while minimizing energy consumption and voltage fluctuations. This study introduces a novel framework that enhances motion control and trajectory tracking by integrating an advanced fractional-order proportional–integral–derivative (FOPID) controller with an adaptive neuro-fuzzy inference system (ANFIS). To optimize controller performance, six different optimization algorithms are compared are Accelerated Convergence Black Hole Optimization (ACBHO), Black Hole Optimization (BHO), Aquila Optimizer (AO), Hybrid Firefly Particle Swarm Optimization (HFPSO), Enhanced JAYA (EJAYA), and Sunflower Optimizer (SFO). Among these, the proposed ACBHO algorithm significantly improved trajectory tracking accuracy and control efficiency. The framework effectively manages voltage regulation and enhances motion precision by fine-tuning FOPID and ANFIS parameters. These results demonstrate the potential of ACBHO-based optimization as a robust solution for improving control system performance in advanced mobile robotics applications.