LEARNING IN NAVIGATION: GOAL FINDING IN GRAPHS

Author:

CUCKA PETER1,NETANYAHU NATHAN S.12,ROSENFELD AZRIEL1

Affiliation:

1. Computer Vision Laboratory, Center for Automation Research, University of Maryland, College Park, MD 20742-3275, USA

2. Center of Excellence in Space Data and Information Sciences, NASA Goddard Space Flight Center, Code 930.5, Greenbelt, MD 20771, USA

Abstract

A robotic agent operating in an unknown and complex environment may employ a search strategy of some kind to perform a navigational task such as reaching a given goal. In the process of performing the task, the agent can attempt to discover characteristics of its environment that enable it to choose a more efficient search strategy for that environment. If the agent is able to do this, we can say that it has "learned to navigate" — i.e., to improve its navigational performance. This paper describes how an agent can learn to improve its goal-finding performance in a class of discrete spaces, represented by graphs embedded in the plane. We compare several basic search strategies on two different classes of "random" graphs and show how information collected during the traversal of a graph can be used to classify the graph, thus allowing the agent to choose the search strategy best suited for that graph.

Publisher

World Scientific Pub Co Pte Lt

Subject

Artificial Intelligence,Computer Vision and Pattern Recognition,Software

Cited by 12 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. On the performance of greedy forwarding on Yao and Theta graphs;Journal of Parallel and Distributed Computing;2018-07

2. New Memoryless Online Routing Algorithms for Delaunay Triangulations;IEEE Transactions on Parallel and Distributed Systems;2012-08

3. Finding patterns in an unknown graph;AI Communications;2012

4. Multi-agent Physical A* with Large Pheromones;Autonomous Agents and Multi-Agent Systems;2005-09-26

5. Competitive online routing in geometric graphs;Theoretical Computer Science;2004-09

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3