Title :
Representation and learning of nonlinear compliance using neural nets
Author_Institution :
Dept. of Mech. Eng., Massachusetts Inst. of Technol., Cambridge, MA, USA
fDate :
12/1/1993 12:00:00 AM
Abstract :
A new approach to compliant motion control using neural networks is presented. In the paper, “compliance” is treated as a nonlinear mapping from a measured force to a corrected motion. The nonlinear mapping by a multilayer neural network is outlined, this allows one to deal with complex control strategies that cannot be represented by linear compliance, such as in stiffness and damping control
Keywords :
compliance control; force measurement; learning (artificial intelligence); neural nets; position control; robots; complex control strategies; compliant motion control; damping control; learning; multilayer neural network; nonlinear compliance; nonlinear mapping; stiffness; Damping; Force measurement; Mechanical engineering; Motion control; Motion measurement; Multi-layer neural network; Neural networks; Robot kinematics; Robot motion; Robotic assembly;
Journal_Title :
Robotics and Automation, IEEE Transactions on
