Modeling and simulation of cooperative transport of an object by two mobile manipulators on an uneven terrain using KSOM network

Abstract

ABSTRACT In this paper, a learning-based method for cooperative load transport by two 16 DOF wheeled mobile manipulators (MM) on a rough surface is proposed. Each MM has a 10 DOF mobile platform with a six DOF manipulator on top of it. As the MM system is redundant, the standard pseudo inverse or Jacobian methods for finding the inverse kinematics solution cannot be used in real time. Thus, an advanced Kohonen self-organizing map (KSOM) network is used to learn the inverse kinematic mapping and resolve the redundancy of the MMs. Considering the nonholonomic constraints of the vehicle and manipulability measure of the manipulator, the forward kinematic model of the MM system is used to train the network. A user defined object path governs the end effector paths of the two MMs for carrying the object and the trained network resolves the redundancy of the MMs to follow the respective end effector paths. The advantage of the proposed method is that once a terrain is learned, multiple MMs can be simulated to carry an object together in real time, without complex inverse kinematics. Simulation results show the usefulness of the proposed method.