A novel algorithm, the immune genetic algorithm based on multi-agent, isproposed for the path planning of tightly coordinated two-robot manipulators, which constructsmainly immune operators accomplished by three steps...A novel algorithm, the immune genetic algorithm based on multi-agent, isproposed for the path planning of tightly coordinated two-robot manipulators, which constructsmainly immune operators accomplished by three steps: defining strategies and methods of multi-agent,calculating virtual forces acting on an agent, and constructing immune operators and performingimmunization during the evolutionary process. It is illustrated to be able to restrain thedegenerate phenomenon effectively and improve the searching ability with high converging speed.展开更多
In this paper, a method to posture maintenance control of 2-link object by nonprehensile two-cooperative-arm robot without compensating friction is proposed. In details, a mathematical model of the 2-link object is fi...In this paper, a method to posture maintenance control of 2-link object by nonprehensile two-cooperative-arm robot without compensating friction is proposed. In details, a mathematical model of the 2-link object is firstly built. Based on the model, stable regions for holding motion of nonprehensile two-cooperative-arm robot are obtained while the 2-link object is kept stable on the robot arms with static friction. Among the obtained stable regions, the robust pairs of orientation angles of the 2-link object are found. Under the robust orientation angles, a feedback control system is designed to control the arms to maintain the 2-link object's posture while it is being held or lifted up. Finally, experimental results are shown to verify the effectiveness of the proposed method.展开更多
A novel motor learning method is present based on the cooperation of the cerebellum and basal ganglia for the behavior learning of agent. The motor learning method derives from the principle of CNS and operant learnin...A novel motor learning method is present based on the cooperation of the cerebellum and basal ganglia for the behavior learning of agent. The motor learning method derives from the principle of CNS and operant learning mechanism and it depends on the interactions between the basal ganglia and cerebellum. The whole learning system is composed of evaluation mechanism, action selection mechanism, tropism mechanism. The learning signals come from not only the Inferior Olive but also the Substantia Nigra in the beginning. The speed of learning is increased as well as the failure time is reduced with the cerebellum as a supervisor. Convergence can be guaranteed in the sense of entropy. With the proposed motor learning method, a motor learning system for the self-balancing two-wheeled robot has been built using the RBF neural networks as the actor and evaluation function approximator. The simulation experiments showed that the proposed motor learning system achieved a better learning effect, so the motor learning based on the coordination of cerebellum and basal ganglia is effective.展开更多
A wall climbing robot with two driven wheels and single adhering disk is introduced in this paper. The robot has a compact structure and can be controlled flexibly. This kind of robot will have a wide prospect for app...A wall climbing robot with two driven wheels and single adhering disk is introduced in this paper. The robot has a compact structure and can be controlled flexibly. This kind of robot will have a wide prospect for application.展开更多
A Robot wrist made of a planar step motor with two-degree-of-freedom has been developed recently for a general robot manipulator used in assembly operation.Mechanism design and the magnetic theory of the motor and the...A Robot wrist made of a planar step motor with two-degree-of-freedom has been developed recently for a general robot manipulator used in assembly operation.Mechanism design and the magnetic theory of the motor and the driving system are discussed. The paper also presents several stecial characteritics in designing general step motor (SM) driver This robot end-effector successfully improves the PUMA562 robot's response and locating accuracy.展开更多
文摘A novel algorithm, the immune genetic algorithm based on multi-agent, isproposed for the path planning of tightly coordinated two-robot manipulators, which constructsmainly immune operators accomplished by three steps: defining strategies and methods of multi-agent,calculating virtual forces acting on an agent, and constructing immune operators and performingimmunization during the evolutionary process. It is illustrated to be able to restrain thedegenerate phenomenon effectively and improve the searching ability with high converging speed.
文摘In this paper, a method to posture maintenance control of 2-link object by nonprehensile two-cooperative-arm robot without compensating friction is proposed. In details, a mathematical model of the 2-link object is firstly built. Based on the model, stable regions for holding motion of nonprehensile two-cooperative-arm robot are obtained while the 2-link object is kept stable on the robot arms with static friction. Among the obtained stable regions, the robust pairs of orientation angles of the 2-link object are found. Under the robust orientation angles, a feedback control system is designed to control the arms to maintain the 2-link object's posture while it is being held or lifted up. Finally, experimental results are shown to verify the effectiveness of the proposed method.
文摘A novel motor learning method is present based on the cooperation of the cerebellum and basal ganglia for the behavior learning of agent. The motor learning method derives from the principle of CNS and operant learning mechanism and it depends on the interactions between the basal ganglia and cerebellum. The whole learning system is composed of evaluation mechanism, action selection mechanism, tropism mechanism. The learning signals come from not only the Inferior Olive but also the Substantia Nigra in the beginning. The speed of learning is increased as well as the failure time is reduced with the cerebellum as a supervisor. Convergence can be guaranteed in the sense of entropy. With the proposed motor learning method, a motor learning system for the self-balancing two-wheeled robot has been built using the RBF neural networks as the actor and evaluation function approximator. The simulation experiments showed that the proposed motor learning system achieved a better learning effect, so the motor learning based on the coordination of cerebellum and basal ganglia is effective.
基金Supportedby the High Technology Research and Development Programme of China
文摘A wall climbing robot with two driven wheels and single adhering disk is introduced in this paper. The robot has a compact structure and can be controlled flexibly. This kind of robot will have a wide prospect for application.
文摘A Robot wrist made of a planar step motor with two-degree-of-freedom has been developed recently for a general robot manipulator used in assembly operation.Mechanism design and the magnetic theory of the motor and the driving system are discussed. The paper also presents several stecial characteritics in designing general step motor (SM) driver This robot end-effector successfully improves the PUMA562 robot's response and locating accuracy.
