Abstract: A concept named “common reference object” is proposed for a cooperative transportation using multiple nonholonomic mobile robots and a decentralized system is constructed to demonstrate the present concept. In this system, one agent acts as the leader which is able to plan and manipulate the omnidirectional motion of an object. Other agents referred to as followers cooperatively transport the object by keeping a constant position relative to the object. During the transportation operation, the leader robot can not only plan the motion of the object but also broadcast the local velocity of the object to other agents. Then, each follower…receives such information and generates its own velocity in the local coordinate using a mapping process. In this paper, neural network (NN) and genetic algorithm (GA) are tested in identifying the mapping process. Simulation results show an acceptable performance of the present concept.
Show more
Abstract: In this paper, the concept of fuzzy behavior-based control is used to construct a fuzzy generator that generates the desired positions and orientations of a robot manipulator in the Cartesian space. A servo controller is introduced between the fuzzy trajectory generator and the robot. This method is proposed to minimize the drawbacks in extending a fuzzy behavior-based control used previously, while keeping the advantages of the fuzzy behavior-based strategy. For the PUMA robot, the direct extended version of the control system applied to a three-link manipulator in a previous work, is compared with the proposed method. Two methods are first…applied for two behavior groups without any obstacle, in which fuzzy behavioral elements in each method are trained by a genetic algorithm. It is proved that a desired result is not possible within a few numbers of generations for the extended method, whereas the proposed method is able to achieve good results. Moreover, the proposed method is simulated to prove the benefit of the method for three behavior groups with an obstacle. Therefore, it can be concluded that the present approach is suitable in task control of high degree-of-freedom multi-link manipulators while avoiding obstacles for manipulators similar to PUMA robot.
Show more