基于案例的自主式水下机器人全局路径规划的学习算法

Autonomous Underwater Vehicles Global Path Planning Using Case-Based Learning Algorithm

首次讨论了基于案例的学习方法在自主式水下机器人全局路径规划中的应用问题．基于案例的学习方法是一种增量式的学习过程，它根据过去的经验进行学习及问题求解．本文对基于案例的学习方法在自主式水下机器人的全局路径规划中的应用框架进行了初步研究，对案例属性的提取、案例的匹配和择优以及案例库的更新等问题提出了相应的算法．最后给出了几组仿真结果．

This paper presents an AUV global path planning scheme using case-based learning algorithm.Case-based learning is a relatively new approach to path planning.Case-based learning is learning and reasoning from past episodic information about the enviromment .Retrieving and adapting an old one ,which approximately matches the current situation,can generate a new and suitable solution.In this research,the algorithm includes these parts:establishment of path attribute extracted from its features,matching and retrieving case from the case library,and updating the case library.The effectiveness of the algorithm is verified through simulations.