返回
Solving the motion planning problem using learning experience through case-based reasoning and machine learning algorithms
DOI:10.1016/j.asej.2019.10.007.png)
摘要
En 中文
This article presents two novel methodologies for solving the motion planning problem through retained experience. Both approaches employ AI's case-based reasoning (CBR) technique. Case-based reasoning is an expert system development methodology which reuses past solutions to solve new problems. The first approach uses CBR to retain K similar cases to solve the motion planning problem by merging those solutions into a set. Afterwards, it picks from this set based on a heuristic function to assemble a final solution. Regarding the second approach, it employs the retained K similar cases differently. It uses those solution to build a graph which can be queried using traditional graph search algorithms. Results prove the success of such approaches concerning solution quality and success rate compared to different experience-based algorithms. Such utilization for CBR systems develops new research directions for building systems that can solve NP problems based on retained experiences exclusively. (C) 2019 The Authors. Published by Elsevier B.V. on behalf of Faculty of Engineering, Ain Shams University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Keyword:
Sampling-based algorithms
Experience-based algorithms
Case-based reasoning
Artificial intelligence
Motion planning
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.9
论文数:
3.4K
被引数:
1.2W
机构
引用论文
Does it take older adults longer than younger adults to perceptually segregate a speech target from a background masker?在感知上将语音目标与背景掩蔽器隔离开来是否需要老年人比年轻人更长的时间?
Application of ATR-FTIR spectroscopy in quantitative analysis of deuterium in basic solutions
Analusis
IF0

