Scholarlink

The traditional artificial potential field (APF) method is widely used in the field of intelligent collision avoidance due to its simplicity and ease of calculation, and it has achieved significant success. However, the traditional APF method has noticeable shortcomings, such as frequently getting trapped in local optima and generally performing poorly in avoiding dynamic obstacles. This paper utilizes Time to Closest Point of Approach (TCPA) and Distance to Closest Point of Approach (DCPA) as variables in the APF method and improves the variable functions within the traditional artificial potential field method. The enhanced approach demonstrates better obstacle avoidance performance for both dynamic and static obstacles. Additionally, we have simplified the potential field function, making the force calculation more straightforward and efficient.

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

Research on Artificial Potential Fields Based on Minimum Encounter Distance and Time

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yonghong Zhang,
  • Zongkai Wang,
  • Yang Liu,
  • Guanquan Dai

摘要

The traditional artificial potential field (APF) method is widely used in the field of intelligent collision avoidance due to its simplicity and ease of calculation, and it has achieved significant success. However, the traditional APF method has noticeable shortcomings, such as frequently getting trapped in local optima and generally performing poorly in avoiding dynamic obstacles. This paper utilizes Time to Closest Point of Approach (TCPA) and Distance to Closest Point of Approach (DCPA) as variables in the APF method and improves the variable functions within the traditional artificial potential field method. The enhanced approach demonstrates better obstacle avoidance performance for both dynamic and static obstacles. Additionally, we have simplified the potential field function, making the force calculation more straightforward and efficient.