Neural joint control for Space Shuttle Remote Manipulator SystemNeural networks are being used to control a robot arm in a telerobotic operation. The concept uses neural networks for both joint and inverse kinematics in a robotic control application. An upper level neural network is trained to learn inverse kinematic mappings. The output, a trajectory, is then fed to the Decentralized Adaptive Joint Controllers. This neural network implementation has shown that the controlled arm recovers from unexpected payload changes while following the reference trajectory. The neural network-based decentralized joint controller is faster, more robust and efficient than conventional approaches. Implementations of this architecture are discussed that would relax assumptions about dynamics, obstacles, and heavy loads. This system is being developed to use with the Space Shuttle Remote Manipulator System.
Document ID
19920050568
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Atkins, Mark A. (NASA Marshall Space Flight Center Huntsville, AL, United States)
Cox, Chadwick J. (NASA Marshall Space Flight Center Huntsville, AL, United States)
Lothers, Michael D. (NASA Marshall Space Flight Center Huntsville, AL, United States)
Pap, Robert M. (Accurate Automation Corp. Chattanooga, TN, United States)
Thomas, Charles R. (Accurate Automation Corp. Chattanooga, TN; Covenant College, Lookout Mountain, GA, United States)