Using Custom-designed Vlsi Fuzzy Inferencing Chips For The Autonomous Navigation Of A Mobile Robot

Abstract

This report was prepared as an account of work sponsoredby an agencyof the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees,makes any warranty, expressor implied, or assumes any legal liability or responsibility for the accuracy,completeness,or usefulnessof any information,apparatus, product, or process disclosed,or represents that its use would not infringeprivately owned rights. Reference herein to any specificcommercialproduct, prcx:ess, or serviceby trade name, trademark, manufacturer, or otherwise does not necessarilyconstitute or imply its endorsement,recommendation, or favoringby the United States Governmentor any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Governmentor any agencythereof.

Mobile Robot Navigation using alpha level fuzzy logic system: Experimental investigations

“…Song et.al. [ Pin F.G(1992)] presented a scheme for independent control of two drive wheels on their simulated robot. When an obstacle is detected by one of the robot's proximity sensors, the fuzzy controller increases the speed of the respective wheel to turn away from it.…”

Driving a car using reflexive fuzzy behaviors

“…When the goal is a heading, a compass is used to directly provide the relative goal direction as the difference between the platform current heading and the goal heading. As explained in [4], membership functions representing the levels of uncertainty with which the values were obtained are applied to the four input values.…”

“…Very robust navigation characteristics were obtained in the laboratory experiments using these very sparse and imprecise sensor data (purposefully selected as such to emphasize the feasibility demonstration), and as little as fourteen fuzzy rules representing the six basic behaviors controlling the platform's turning rate and speed (see [4] or [9]): GD + TR, GD -+ TS,OP + TS, "far" O P -+ TR, "near" OP + TR, "very near" OP -+ TR. As an example of the rule base format, the three rules which constitute the GD -+ TR behavior are shown in Fig.…”

“…In cooperation with MCNC, Inc. and the University of North Carolina, two types of VME-bus-compatible computer boards including custom-designed VLSI chips have been developed to add a qualitative reasoning capability to real-time control systems [1],[2],[3], [4]. The methodologies embodied on the VLSI hardware utilize the Fuzzy Set Theoretic operations [5], [6], [7], [8] to implement a production rule type of inferencing on input and output variables that can directly be specified as qualitative variables through membership functions.…”

“…The basic operation of these boards and a formalism merging the fuzzy and behaviorist theories for the development of qualitative reasoning schemes emulating human-like navigation have been discussed in [4]. The approach using superposition of elemental sensor-based fuzzy behaviors has been shown to allow easy development and testing of the inferencing rule base, while providing for progressive addition of behaviors to resolve situations of increasing complexity.…”