Visual motor control of a 7 DOF robot manipulator using a fuzzy SOM network

Abstract

A fuzzy self-organizing map (SOM) network is proposed in this paper for visual motor control of a 7 degrees of freedom (DOF) robot manipulator. The inverse kinematic map from the image plane to joint angle space of a redundant manipulator is highly nonlinear and ill-posed in the sense that a typical end-effector position is associated with several joint angle vectors. In the proposed approach, the robot workspace in image plane is discretized into a number of fuzzy regions whose center locations and fuzzy membership values are determined using a Fuzzy C-Mean (FCM) clustering algorithm. SOM network then learns the inverse kinematics by on-line by associating a local linear map for each cluster. A novel learning algorithm has been proposed to make the robot manipulator to reach a target position. Any arbitrary level of accuracy can be achieved with a number of fine movements of the manipulator tip. These fine movements depend on the error between the target position and the current manipulator position. In particular, the fuzzy model is found to be better as compared to Kohonen self-organizing map (KSOM) based learning scheme proposed for visual motor control. Like existing KSOM learning schemes, the proposed scheme leads to a unique inverse kinematic solution even for a redundant manipulator. The proposed algorithms have been successfully implemented in real-time on a 7 DOF PowerCube robot manipulator, and results are found to concur with the theoretical findings.

Kinematic control of a redundant manipulator using an inverse-forward adaptive scheme with a KSOM based hint generator

“…Note that, we are talking about an accuracy of 1 mm to be obtained through our scheme. It is possible to get a positioning accuracy of about 1 cm by using the KSOM-SC architecture as shown in [22,24]. Hence in moving from 1 cm to 1 mm accuracy, it can be safely assumed that one can obtain a collision-free motion in a workspace whose overall dimension is in meters.…”

“…In other words, this architecture facilitates redundancy resolution at the position level without any cumbersome optimization process. An overview of this architecture is provided in Section 3 and the readers are referred to [22,24] for a detailed treatment on the topic. (iii) For a given target position x d , update the input vector of the RBF network so as to reduce the error function given by…”

“…It is seen that the number of solutions decreases towards the boundary of the workspace as expected. A detailed treatment on this architecture is provided in [24] where it is shown through simulations as well as experiments that, the joint angle vectors remain bounded for all points in the workspace.…”

“…The KSOM-SC network architecture was introduced in [22] where it was shown to provide high accuracy in a pick-and-place kind of task. The theories related to KSOM-SC network were further developed in [24] where it was applied to solve the redundancy resolution problem while tracking a trajectory. It was shown to preserve all the desirable qualities of inverse kinematic solutions like, the conservative property, the joint angle boundedness and high positioning accuracy.…”

“…Unlike conventional techniques, changing the redundancy resolution criterion does not require re-training of the network and hence this redundancy resolution scheme is far simpler than those existing in the current literature. Readers are referred to [24] for an in-depth study of this architecture.…”