probabilistic roadmaps for path planning in high-dimensional.pptVIP

下载本文档

7
0
约4.3千字
约 19页
2016-03-05 发布于广东
举报
版权申诉

probabilistic roadmaps for path planning in high-dimensional.ppt

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

probabilistic roadmaps for path planning in high-dimensional

Probabilistic Roadmaps for Path Planning in High-Dimensional Configuration Spaces Authors: Lydia E. Kavraki, Petr Svestka, Jean-Claude Latombe, and Mark H. Overmars Presented By: Aninoy Mahapatra Agenda Motivation Introduction Previous Work The Method Experiments Results References Motivation Applications: Car assembly lines Nuclear plant cooling pipes Cleaning airplane fuselages Complex workspaces Tedious programming Efficient, reliable planner required to reduce burden Introduction Motion planning in static workspaces Holonomic robots, with many degrees of freedom Static obstacles, avoid collision Introduction (contd.) Inputs: Geometry of robot and obstacles Kinematics of robot (degrees of freedom) Initial and goal robot configurations (placements) Outputs: Continuous sequence of collision-free robot configurations connecting the initial and goal configurations Robotic Arm Video Source: /~latombe/projects/motion-planning.ppt Previous Work Potential Fields: /watch?v=r9FD7P76zJs Potential field / cell decomposition based methods RPP (fails for several examples, falling into local minima bounded by obstacles) variational dynamic programming Use of genetic algorithms Roadmap based methods Visibility graph (low dimension C-spaces) Voronoi diagram (low dimension C-spaces) Silhouette method (any dimension but complex, hence impractical) The Method Learning Phase Construction: reasonably connected graph covering C-space Expansion: improve connectivity Local paths not memorized (cheap to re-compute) The Method (contd.) The Method (contd.) Query Phase Connect start and goal configurations to roadmap (say, ? and ?) Find path between ? and ? in roadmap ? and ? should be in same connected component, else failure If too many failures, increase learning time Principle of Probabilistic Roadmaps Probabilistic Roadmaps (contd.) Properties of PRM Planners Is probabilistically complete, i.e., whenever a solution exists, the probability that it finds one tends toward 1