Sensor-based driving of a car with fuzzy inferencing VLSI chips and boards

Conference · Tue Sep 01 04:00:00 EDT 1992

OSTI ID:10173102

Pin, F G; Watanabe, Y

This paper discusses the sensor-based driving of a car in a-priori unknown environments using ``human-like`` reasoning schemes. The schemes are implemented on custom-designed VLSI fuzzy inferencing boards and are used to investigate two control modes for driving a car on the basis of very sparse and imprecise range data. In the first mode, the car navigates fully autonomously, while in the second mode, the system acts as a driver`s aid providing the driver with linguistic (fuzzy) commands to turn left or right and speed up, slow down, stop, or back up depending on the obstacles perceived by the sensors. Experiments with both modes of control are described in which the system uses only three acoustic range (sonar) sensor channels to perceive the environment. Sample results are presented which illustrate the feasibility of developing autonomous navigation systems and robust safety enhancing driver`s aid using the new fuzzy inferencing VLSI hardware and ``human-like`` reasoning schemes.

• Research Organization: Oak Ridge National Lab., TN (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: AC05-84OR21400
• OSTI ID: 10173102
• Report Number(s): CONF-921181--1; ON: DE92017819
• Country of Publication: United States
• Language: English

Related Subjects

42 ENGINEERING
420200
426000
ACOUSTIC MEASUREMENTS
AUTOMOBILES
COMPONENTS
ELECTRON DEVICES AND CIRCUITS
FACILITIES, EQUIPMENT, AND TECHNIQUES
FUZZY LOGIC
LOGIC CIRCUITS
NAVIGATION
PERFORMANCE
REMOTE CONTROL
REMOTE SENSING
ROBOTS
SONAR