Redundant Robot Kinematics Control with HCMAC Neural Network Manipulability Enhancement

2008 ◽  
Vol 41 (2) ◽  
pp. 5450-5455
Author(s):  
V. Řikovský ◽  
Š. Kozák
Keyword(s):  
Neural Network ◽  
Robot Kinematics ◽  
Redundant Robot

Obstacle Avoidance for Quadruped Robots Using a Neural Network

2003 ◽  
Vol 7 (2) ◽  
pp. 115-123 ◽  
Author(s):  
Tomohiro Yamaguchi ◽  
◽  
Keigo Watanabe ◽  
Kiyotaka Izumi ◽  
Kazuo Kiguchi
Keyword(s):  
Neural Network ◽  
Mobile Robots ◽  
Obstacle Avoidance ◽  
Body Motion ◽  
Design Parameters ◽  
Robot Kinematics ◽  
Avoidance Task ◽  
Quadruped Robots ◽  
Current State ◽  
Leg Motion

Legged mobile robots, which differ from wheeled and crawler, need not avoid all obstacles by altering the path in the obstacle avoidance task. Because, legged mobile robots can get over or stride some obstacles, depending on the obstacle configuration and the current state of the robot. Legged mobile robots muse have suitable motion for each leg. We propose body motion control of a quadruped robot using a neural network (NN) for an obstacle avoidance task. Each leg motion is calculated by robot kinematics using body motion from the NN. NN design parameters are tuned off-line by a genetic algorithm (GA). Effectiveness of the present method is proved through an experiment.

On avoiding singularities in redundant robot kinematics

Robotica ◽  
1995 ◽  
Vol 13 (6) ◽  
pp. 599-606 ◽  
Author(s):  
Krzysztof Tchoń ◽  
Aleksander Matuszok
Keyword(s):  
Vector Field ◽  
Equilibrium Points ◽  
Motion Vector ◽  
Sufficient Conditions ◽  
The Self ◽  
Robot Kinematics ◽  
Redundant Robot ◽  
Singular Configurations ◽  
Motion Vector Field ◽  
Self Motion

SummaryFor redundant robot kinematics with a degree of redundancy 1 a self-motion vector field is examined whose equilibrium points lie at singular configurations of the kinematics, and whose orbits determine the self-motion manifolds. It is proved that the self-motion vector field is divergence-free. Locally, around singular configurations of corank 1, the self-motion vector field defines a 2-dimensional Hamiltonian dynamical system. An analysis of the phase portrait of this system in a neighbourhood of a singular configuration solves completely the question of avoidability or unavoidability of this configuration. Complementarily, sufficient conditions for avoidability and unavoidability are proposed in an analytic form involving the self-motion Hamilton function. The approach is illustrated with examples. A connection with normal forms of kinematics is established.

Sign in / Sign up

Export Citation Format

Share Document