Optimization of the computational load of a hypercube supercomputer onboard a mobile robot

Jacob Barhen, N. Toomarian, V. Protopopescu

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

A combinatorial optimization methodology is developed, which enables the efficient use of hypercube multiprocessors onboard mobile intelligent robots dedicated to time-critical missions. The methodology is implemented in terms of large-scale concurrent algorithms based either on fast simulated annealing, or on nonlinear asynchronous neural networks. In particular, analytic expressions are given for the effect of singleneuron perturbations on the systems' configuration energy. Compact neuromorphic data structures are used to model effects such as precedence constraints, processor idling times, and task-schedule overlaps. Results for a typical robot-dynamics benchmark are presented.

Original languageEnglish
Pages (from-to)5007-5014
Number of pages8
JournalApplied Optics
Volume26
Issue number23
DOIs
StatePublished - Dec 1987

Fingerprint

Dive into the research topics of 'Optimization of the computational load of a hypercube supercomputer onboard a mobile robot'. Together they form a unique fingerprint.

Cite this