Project Title:
A Fault-Tolerant, Intelligent, Robotic Control System
05.05-4717
911689
A Fault-Tolerant, Intelligent, Robotic Control System
Sohar, Inc.
8421 Wilshire Boulevard, Suite 201
Beverly Hills
CA
90211-3204
Kam Sing
Tso
213-653-4717
JPL
NAS7-1172
091
05.05-4717
911689
Abstract:
A Fault-Tolerant, Intelligent Robotic Control System
The goal of this project is to develop the application of a distributed fault-tolerant
system architecture for robot control in order to tolerate hardware and software
faults, and a knowledge-based diagnosis and recovery system to tolerate faults due
to operational errors. The underlying architecture to support this research is the
extended distributed recovery block (EDRB). Fault-tolerance provisions already implemented
in the architecture include protection against failures in application software,
system software, hardware, and networks. The knowledge-based system will use the
expert system shell, CLIPS, developed at the NASA Johnson Space Center. Advanced
automation techniques such as rule-based and model-based reasoning will be utilized
to monitor, diagnose, and recover from unexpected events. The two-level design provides
tolerance of two or more faults occurring serially at any level of command, control,
sensing, or actuation. The potential benefits of such a fault-tolerant, robotic control
system include a minimized potential for damage to humans, the work site, and the
robot itself; continuous operation with a minimum of uncommanded motion in the presence
of failures; and more reliable autonomous operation, providing increased efficiency
in the execution of robotic tasks and decreased demand on human operators for controlling
and monitoring the robotic servicing routines.
Fault-tolerant techniques building dependable robotic systems can be used in applications
that require a high degree of reliability and safety, such as servicing tasks in
Space Station Freedom, waste cleanup tasks in nuclear facilities, and patient-tending
tasks in medical facilities. The knowledge-based fault diagnostics and recovery system
can also be used in industrial robots to cope with various unexpected events occurring
during the manufacturing process.
recovery blocks, knowledge-based system, robotic systems, fault-tolerant, fault-diagnosis,
error recovery