High-Level Planning In A Mobile Robot Domain

Citation

Wilkins, D. E. (1986). High-Level Planning in a Mobile Robot Domain (Preprint). SRI INTERNATIONAL MENLO PARK CA ARTIFICIAL INTELLIGENCE CENTER.

Abstract

An application of the SIPE planning system to high-level task planning for an autonomous indoor mobile robot is presented. The primary purpose was to evaluate the adequacy of SIPE for this domain, extending and improving the system in the process. The mobile robot domain as encoded in SIPE and the approach to interfacing the planner and the lower-level routines are described. The bulk of the paper presents both problems encountered during the process of encoding this domain, and extensions of the planning system that were made to solve them.

The most significant addition was a redesign of the deductive capability of the planner, which is described in some detail. Efficiency considerations and the ability to intermingle planning and execution are discussed. The most important problem encountered involved hierarchical planning, an ambiguous term. We present a definition of it, and examine several of the reasons for this ambiguity. An explication of hierarchical-planning implementations entails two distinct notions: abstraction level and planning level. A problem in currently implemented planners that is caused by mixing these two levels is presented and various remedies suggested. Three solutions that have been implemented in the current SIPE planning system are described.


Read more from SRI

  • Banner and attendees at the IEEE Hard Tech Venture Summit

    Cultivating hard tech startups that scale

    IEEE’s Hard Tech Venture Summit convened innovators at SRI to refine strategies and build new networks.

  • Patient going into a MRI

    Bringing surgical tools inside the MRI

    Drawing on SRI’s unique innovation ecosystem, the startup Medical Devices Corner is seeking to improve cancer surgery by advancing MRI-safe teleoperation.

  • Christopher Mims and Susan Patrick

    PARC Forum: How to AI

    The Wall Street Journal tech columnist Christopher Mims and SRI Education’s Susan Patrick discuss how AI can strengthen human agency.