Scholarlink

To overcome the issues encountered by traditional Artificial Potential Field (APF) algorithms in handling complex obstacle environments, such as local minima, unreachable targets, and path tortuosity, this paper proposes an improved path planning method that combines APF with the Douglas-Peucker algorithm. Recognizing the limitations of traditional path planning methods in addressing the uncertainties and flexibility of human behavior in human-machine interaction systems, this study introduces adaptive step length strategies and path simplification techniques to enhance real-time responsiveness and computational efficiency. By dynamically adjusting the step length during path planning and utilizing the Douglas-Peucker algorithm to reduce the number of nodes in the path, this method significantly optimizes the path generation process. Additionally, the use of cubic B-spline curve smoothing techniques further enhances the smoothness and applicability of the path. Simulation results validate the effectiveness of the improved algorithm in complex environments, demonstrating a significant increase in path planning accuracy and efficiency. The number of nodes was reduced by approximately 86.2%, greatly decreasing computational load and memory consumption. This approach is particularly suitable for simulation systems requiring high dynamic interaction.

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

Path Planning for Human-Machine Interaction in Complex Environments: Application Study of the DP-APF Algorithm

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Xiang Liu,
  • Hao Meng,
  • Xian Yue,
  • Zhilin Huo,
  • Siqu Liu,
  • Yi Zhang,
  • Yiyang Duan,
  • Daomeng Cai

摘要

To overcome the issues encountered by traditional Artificial Potential Field (APF) algorithms in handling complex obstacle environments, such as local minima, unreachable targets, and path tortuosity, this paper proposes an improved path planning method that combines APF with the Douglas-Peucker algorithm. Recognizing the limitations of traditional path planning methods in addressing the uncertainties and flexibility of human behavior in human-machine interaction systems, this study introduces adaptive step length strategies and path simplification techniques to enhance real-time responsiveness and computational efficiency. By dynamically adjusting the step length during path planning and utilizing the Douglas-Peucker algorithm to reduce the number of nodes in the path, this method significantly optimizes the path generation process. Additionally, the use of cubic B-spline curve smoothing techniques further enhances the smoothness and applicability of the path. Simulation results validate the effectiveness of the improved algorithm in complex environments, demonstrating a significant increase in path planning accuracy and efficiency. The number of nodes was reduced by approximately 86.2%, greatly decreasing computational load and memory consumption. This approach is particularly suitable for simulation systems requiring high dynamic interaction.