Scholarlink

<p>Due to technical advancements in robotics, mobile robots (MR) are playing an increasingly important role in medical applications that call for a high level of delicacy, precision, and effectiveness. MR is predominantly nonlinear and time-varying system that necessitates intelligent controller rather than traditional controllers. When MR is combined with artificial intelligence (AI), the resulting system becomes intelligent or fully autonomous. Thus, the meta-heuristic algorithms genetic algorithm (GA), firefly algorithm (FA), particle swarm optimisation (PSO), grey-wolf optimisation (GWO) and fused grey-wolf particle swarm optimisation (FGWPSO) are employed to achieve the optimal result and enhance the controller's overall performance, which ultimately leads to an overall improvement in the system. The comparative study demonstrates that proposed FGWPSO control is preferable to traditional control for nonlinear and time-varying MR by improving search ability, convergence speed and accuracy of the system. The attained accuracy, which registers below 0.02, coupled with a 0% overshoot, exemplifies the efficacy of the proposed methodology.</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

Intelligent speed regulation of mobile robot using fused grey-wolf particle swarm optimisation: a hybrid optimisation approach

  • 期刊论文

  • 发表日期：

    2025年6月21日

查看全文
  • Shailu Sachan,
  • Aditya Sirsa,
  • Gaurav Gupta

摘要

Due to technical advancements in robotics, mobile robots (MR) are playing an increasingly important role in medical applications that call for a high level of delicacy, precision, and effectiveness. MR is predominantly nonlinear and time-varying system that necessitates intelligent controller rather than traditional controllers. When MR is combined with artificial intelligence (AI), the resulting system becomes intelligent or fully autonomous. Thus, the meta-heuristic algorithms genetic algorithm (GA), firefly algorithm (FA), particle swarm optimisation (PSO), grey-wolf optimisation (GWO) and fused grey-wolf particle swarm optimisation (FGWPSO) are employed to achieve the optimal result and enhance the controller's overall performance, which ultimately leads to an overall improvement in the system. The comparative study demonstrates that proposed FGWPSO control is preferable to traditional control for nonlinear and time-varying MR by improving search ability, convergence speed and accuracy of the system. The attained accuracy, which registers below 0.02, coupled with a 0% overshoot, exemplifies the efficacy of the proposed methodology.