Jian Huang

Position / Force Hybrid Control of a Manipulator with a Flexible Tool Using Visual and Force Information

Robots used for industrial applications such as welding, painting and object handling have been common for many years. In recent years, the development of domestic robots has become more and more important because of the large and growing population of aged people, especially in Japan. To assist people in their daily lives, a robot must have the ability to deal with not only rigid objects but also the deformable and fragile objects usually encountered in our daily life. Many control algorithms have been developed for the manipulation of rigid objects, and in the recent past many studies related to robotic manipulation of deformable objects have also been reported (Hirai, 1998).

Characterization of Motion Forms of Mobile Robots Generated in Q-Learning Process

Acquisition of unique robotic motions by machine learning is a very attractive research theme in the field of robotics. So far, various learning algorithms—e.g., adaptive learning, neural network (NN) system, genetic algorithm (GA), etc.—have been proposed and applied to the robot to achieve a target. It depends on the persons, but the learning method can be classified roughly into supervised and unsupervised learning (Mitchell, 1997). In supervised learning, the ideal output for target task is available as a teacher signal, and the learning basically proceeds to produce a function that gives an optimal output to the input; the abovementioned learning methods belong to supervised learning. Thus, the learning results should be always within the scope of our expectation. While, the teacher signal is not specifically given in unsupervised learning. Since the designers do not need to know the optimal (or desired) solution, there is a possibility that unexpected solution can be found in the learning process. This article especially discusses the application of unsupervised learning to produce robotic motions. One of the most typical unsupervised learning is reinforcement learning that is a evolutionary computation (Kaelbling et al., 1996; Sutton & Barto, 1998). The concept of this learning method originally comes from the behavioral psychology (Skinner, 1968). As seen in animal evolution, it is expecting that applying this learning method to the robot would have a tremendous potential to find unique robotic motions beyond our expectation. In fact, many reports related to the application of reinforcement learning can be found in the field of robotics (Mahadevan & Conell, 1992; Doya, 1996; Asada et al, 1996; Mataric, 1997; Kalmar et al., 1998; Kimura & Kobayashi, 1999; Kimura et al., 2001, Peters et al., 2003; Nishimura et al., 2005). For example, Doya has succeeded in the acquistion of robotic walking (Doya, 1996). Kimura et al. have demonstrated that reinforcement learning enables the effective advancement motions of mobile robots with several degrees of freedom (Kimura & Kobayashi, 1999; Kimura et al., 2001). As a unique challenge, Nishimura et al. achieved a swing-up control of a real Acrobot—a two-link robot with a single actuator between the links—due to the switching rules of multiple controllers obtained by reinforcement learning (Nishimura et al., 2005). Among these studies, Q-learning, which is a method of

1A2-F01 Measurement and Analysis of Motion Cognition of Human Upper Limb by using Motion Capture

Sho KOSAKA, (Yokohama National University) Yuuki IMAMURA, (Yokohama National University) Jian HUANG, (Yokohama National University) Tetsuro YABUTA, (Yokohama National University) It is generally thought that human beings have high-performance system in body movement. However, mechanisms of the body movement have not been clarified. In this paper, a kinematical model of a human upper limb is proposed to simulate of human upper limb, and a new technique of measurement is developed. Moreover, a motion capture system with this new technique of measurement is utilized in order to measure and analyze the motion cognition of human upper limb in velocity and manipulability. Finally, discussions of mechanisms between human motion and the human cognition are made.

A Human-Safe Control for Collision Avoidance by a Redundant Robot Using Visual Information

Publisher Summary With the rapid development of service robots, avoiding collisions with human beings is a most important requirement of robot control. This chapter proposes a control method by establishing a virtual potential field around a robot to avoid collisions between a human being and the robot by the redundant joints of the robot. The greatest advantage of the proposed method is that a possible collision can be avoided automatically without requiring any action by nearby human beings. A control method is also proposed for a redundant robot to simultaneously carry out a contact task with its hand and perform collision avoidance with its redundant joints. The effectiveness of the proposed method has been demonstrated by experiments.