Algorithm for hierarchical robot planning

Wei Xiong Zhang, Bo Zhang, Yan Qing Zhou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A representation scheme called the goal-model net (GMN), which is used to represent a goal which a robot is supposed to achieve, is proposed. The planning sequence produced by GMN is in two forms: (1) a combination of parallel and sequential plan steps and (2) sequential steps only. A domain-specific heuristic is used for the generation of sequential plans from combinatorial ones. Overall, the planning approach based on GMN reduces the interaction among subgoals by avoiding the unreasonable decomposition of the goal. Hierarchical GMN-based planning decreases computational complexity. The approach has been implemented in the Lisp programming language and utilized in an intelligent robot system for assembling parts in an artificial intelligence laboratory.

Original languageEnglish
Title of host publicationProc 1988 Int Conf Syst Man Cybern
PublisherPubl by IEEE
Pages909-912
Number of pages4
ISBN (Print)7800030393
StatePublished - 1988
EventProceedings of the 1988 International Conference on Systems, Man, and Cybernetics - Beijing/Shenyang, China
Duration: Aug 8 1988Aug 12 1988

Publication series

NameProc 1988 Int Conf Syst Man Cybern

Conference

ConferenceProceedings of the 1988 International Conference on Systems, Man, and Cybernetics
CityBeijing/Shenyang, China
Period08/8/8808/12/88

Fingerprint

Dive into the research topics of 'Algorithm for hierarchical robot planning'. Together they form a unique fingerprint.

Cite this