Title: A neural network-based methodology for inverse kinematics of a multi-finger robotic hand for gripping
Authors: Abhijit Das; Sankha Deb
Addresses: Surface Robotics Lab, Central Mechanical Engineering Research Institute, Durgapur, 721309, India ' FMS and Computer Integrated Manufacturing Lab, Department of Mechanical Engineering, IIT Kharagpur, Kharagpur, 721302, India
Abstract: Robotic grasping and manipulation require controlling the gripper movement through different points in its work volume, necessitating inverse kinematics computations to determine joint angles. In the present work, a novel methodology, based on a radial basis function neural network, has been proposed for the inverse kinematics solution and a genetic algorithm-based approach for optimising the neural network parameters. Instead of taking the entire work volume of the hand for neural network training, a subspace of points is created in close vicinity of the given destination point. The joint variables corresponding to a destination point are obtained using a random walk algorithm that uses the forward kinematics model of the hand. Then, the subspace of points and the corresponding joint variables obtained above are used to train the neural network. This approach can provide an approximate yet fairly quick and effective solution to the inverse kinematics problem of multi-finger robot hands.
Keywords: multi-finger robots; robot grippers; multi-finger grasping; inverse kinematics; artificial neural networks; ANNs; genetic algorithms; robot hands; robot gripping; robot control; random walk; robot kinematics; multi-finger grippers; robot grasping; robot manipulation.
International Journal of Intelligent Systems Technologies and Applications, 2016 Vol.15 No.4, pp.281 - 294
Available online: 26 Oct 2016 *Full-text access for editors Access for subscribers Purchase this article Comment on this article