Scholarlink

<p>There are numerous challenges in multi-target point path planning for inspection robots operating in high-risk industrial environments. Sequence optimization frequently substitutes Euclidean distance for actual travel costs, resulting in suboptimal inspection sequences prone to local minima. Point-to-point planning prioritizes shortest paths over balancing multi-objective constraints. Furthermore, the lack of tight coupling between these approaches makes it difficult to coordinate global sequencing and point-to-point path planning. This paper proposes a two-layer hybrid path planning algorithm composed of the Improved Grey Wolf Optimization (IGWO) and the Improved A* algorithm (I-A*). The I-A* algorithm combines path length, energy consumption, and safety cost into a weighted composite cost, and precomputes a directed cost matrix for each pair of target points. IGWO employs this matrix as its sole fitness function, combining the Iterative Approximation Method (IAM-TSP) initialization with elite 2-Opt local search, and optimizing to obtain the optimal traversal order of inspection targets. Subsequently, I-A* plans the paths between target points segment by segment using this optimal traversal order, resulting in closed-loop coupling between the upper and lower layers. Simulation experiments demonstrate that, across six test cases in the TSPLIB dataset, the IGWO algorithm reduces path lengths by 22.75% to 75.64% compared to the Grey Wolf Optimization (GWO) algorithm. Across three simulation environments, the I-A* algorithm reduced comprehensive path costs by 26.73%, 18.67%, and 18.08% compared to A*, with turning energy consumption decreases of 14.19%, 20.29%, and 18.24%, and safety costs decreased by 89.4%, 81.35%, and 88.38%, respectively. The planning time remained comparable to A*. Furthermore, the average comprehensive path cost of IGWO-I-A* decreased by 36.28%, 37.69%, and 49.19% compared to the baseline GWO-I-A* in the three complex environments. In summary, the proposed method addresses the shortcomings of existing approaches to inter-layer coordination while satisfying multi-objective constraints and maintaining stable convergence, demonstrating its suitability for deployment in industrial inspection tasks.</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

Multi-target point path planning for inspection robots based on improved Grey Wolf Optimization and A* algorithms

  • 期刊论文

  • 发表日期：

    2026年3月30日

查看全文
  • Lichen Shi,
  • Guoning Zhang,
  • Yixin Li,
  • Yi Wang,
  • Juning Tian

摘要

There are numerous challenges in multi-target point path planning for inspection robots operating in high-risk industrial environments. Sequence optimization frequently substitutes Euclidean distance for actual travel costs, resulting in suboptimal inspection sequences prone to local minima. Point-to-point planning prioritizes shortest paths over balancing multi-objective constraints. Furthermore, the lack of tight coupling between these approaches makes it difficult to coordinate global sequencing and point-to-point path planning. This paper proposes a two-layer hybrid path planning algorithm composed of the Improved Grey Wolf Optimization (IGWO) and the Improved A* algorithm (I-A*). The I-A* algorithm combines path length, energy consumption, and safety cost into a weighted composite cost, and precomputes a directed cost matrix for each pair of target points. IGWO employs this matrix as its sole fitness function, combining the Iterative Approximation Method (IAM-TSP) initialization with elite 2-Opt local search, and optimizing to obtain the optimal traversal order of inspection targets. Subsequently, I-A* plans the paths between target points segment by segment using this optimal traversal order, resulting in closed-loop coupling between the upper and lower layers. Simulation experiments demonstrate that, across six test cases in the TSPLIB dataset, the IGWO algorithm reduces path lengths by 22.75% to 75.64% compared to the Grey Wolf Optimization (GWO) algorithm. Across three simulation environments, the I-A* algorithm reduced comprehensive path costs by 26.73%, 18.67%, and 18.08% compared to A*, with turning energy consumption decreases of 14.19%, 20.29%, and 18.24%, and safety costs decreased by 89.4%, 81.35%, and 88.38%, respectively. The planning time remained comparable to A*. Furthermore, the average comprehensive path cost of IGWO-I-A* decreased by 36.28%, 37.69%, and 49.19% compared to the baseline GWO-I-A* in the three complex environments. In summary, the proposed method addresses the shortcomings of existing approaches to inter-layer coordination while satisfying multi-objective constraints and maintaining stable convergence, demonstrating its suitability for deployment in industrial inspection tasks.