skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Using custom-designed VLSI fuzzy inferencing chips for the autonomous navigation of a mobile robot

Conference ·
OSTI ID:5572716
;  [1]; ;  [2]
  1. Oak Ridge National Lab., TN (United States)
  2. North Carolina Univ., Chapel Hill, NC (United States). Dept. of Computer Science

Two types of computer boards including custom-designed VLSI fuzzy inferencing chips have been developed to add a qualitative reasoning capability to the real-time control of autonomous mobile robots. The design and operation of these boards are first described and an example of their use for the autonomous navigation of mobile robot is presented. The development of qualitative reasoning schemes emulating human-like navigation in apriori unknown environments is discussed. An approach using superposition of elemental sensor-based behaviors is shown to alloy easy development and testing of the inferencing rule base, while providing for progressive addition of behaviors to resolve situations of increasing complexity. The efficiency of such schemes, which can consist of as little as a dozen qualitative rules, is illustrated in experiments involving an autonomous mobile robot navigating on the basis of very sparse and inaccurate sensor data. 17 refs., 6 figs.

Research Organization:
Oak Ridge National Lab., TN (United States)
Sponsoring Organization:
USDOE; USDOE, Washington, DC (United States)
DOE Contract Number:
AC05-84OR21400
OSTI ID:
5572716
Report Number(s):
CONF-920724-1; ON: DE92000424
Resource Relation:
Conference: 1992 Institute of Electrical and Electronic Engineers (IEEE) international conference on intelligent robots and systems, Raleigh, NC (United States), 7-10 Jul 1992
Country of Publication:
United States
Language:
English