Title :
Contact-Force Distribution Optimization and Control for Quadruped Robots Using Both Gradient and Adaptive Neural Networks
Author :
Zhijun Li ; Shuzhi Sam Ge ; Sibang Liu
Author_Institution :
Key Lab. of Autonomous Syst. & Network Control, South China Univ. of Technol., Guangzhou, China
Abstract :
This paper investigates optimal feet forces´ distribution and control of quadruped robots under external disturbance forces. First, we formulate a constrained dynamics of quadruped robots and derive a reduced-order dynamical model of motion/force. Consider an external wrench on quadruped robots; the distribution of required forces and moments on the supporting legs of a quadruped robot is handled as a tip-point force distribution and used to equilibrate the external wrench. Then, a gradient neural network is adopted to deal with the optimized objective function formulated as to minimize this quadratic objective function subjected to linear equality and inequality constraints. For the obtained optimized tip-point force and the motion of legs, we propose the hybrid motion/force control based on an adaptive neural network to compensate for the perturbations in the environment and approximate feedforward force and impedance of the leg joints. The proposed control can confront the uncertainties including approximation error and external perturbation. The verification of the proposed control is conducted using a simulation.
Keywords :
adaptive control; feedforward; force control; legged locomotion; motion control; neurocontrollers; quadratic programming; reduced order systems; robot dynamics; uncertain systems; adaptive neural network; approximation error; constrained dynamics; contact-force control; contact-force distribution optimization; external disturbance forces; external perturbation; external wrench equilibration; feedforward force; gradient neural network; hybrid motion-force control; leg joint impedance; leg motion; linear equality constraint; linear inequality constraint; moment distribution; motion model; optimal feet force distribution; optimized objective function; perturbation compensation; quadratic objective function minimization; quadruped robots; reduced-order dynamical model; supporting legs; tip-point force distribution; uncertainties; Force; Friction; Legged locomotion; Neural networks; Optimization; Vectors; External wrench; forces distribution; motion/force control; quadruped robot; quadruped robot.;
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
DOI :
10.1109/TNNLS.2013.2293500