This paper presents an anthropomorphic robot hand called Osaka-City-University-Hand II, which is an improved version of Osaka-City-University-Hand I. The cosmetic and the function of our proposed hand allow us to use the hand as a prosthetic hand in addition to as an open platform of robot hands for robotics research. Distributed tactile and force sensors are appended to the OCU-Hand II as a feedback system in order to grasp an object firmly. A new control strategy is to be adopted, in which a master light-weight glove is to be used to drive the OCU-Hand II as a slave. In the tele-operating task, arithmetic operations are to be done to the outputs of the feedback sensors in order to increase the resolution of the master-slave driving technique as well as to overcome the hardware amplification defects. In order to use OCU-Hand II as a helper equipment, a novel and unique assistive mode is included within master-slave control strategy, where the OCU-Hand II is assisting and helping its operators in order to reduce the load on the operator and perform the usual operations in a better manner or even faster than the usual. During the assistive mode the operator is enabled to perform different tasks other than the master-slave driving while he is still putting on the master-glove.

Here, we describe a method to detect mura during the display devices manufacturing process on a uniformly coated thin photoresist layer. A mura is an irregular variation of lightness on a uniformly manufactured surface. Display devices are manufactured through photolithographic process, and every imaging process requires a uniformly coated photo resist layer. Mura detection on the layer is necessary to keep the device quality high. The mura has been visually inspected by tilting a glass under a sodium lamp in order to create the largest amount of interference. However, tilting the glass is difficult due to the growing device size currently four square-meters in the latest line. Rather than tilting the glass, we have developed an apparatus which illuminates the glass via a set of narrow bandpass filtered light of different wavelength. The apparatus observes the interference of light reflected from the surface and from the bottom of the thin layer in order to inspect the mura on the glass. The reflection intensity as a function of the layer thickness shows a sinusoidal periodic characteristic, which means that the mura detection sensitivity depends strongly on the optical path length in the layer. We have developed a method to compensate the periodic sensitivity fluctuation by employing a reflection ratio that enables us to detect the local thickness fluctuation with an accuracy of one nanometer.

For the task under Markov Decision Process, this paper presents a novel multiagent Reinforcement Learning (RL) with perception and conversion action mechanism that learning agents observe adversary agent and convert adversarial action to learning agents' corresponding action as observing state variation incurred by the adversary agent in the task environment during learning processes. Meanwhile, this paper surveys inexpensive communication ways among learning agents utilizing both the direct communication and the indirect media communication to realize agents' cooperation. The direct communication is realized by sharing sensation; the indirect media communication is realized by updating reinforcement values on the common environment observation. Then, a multiagent RL algorithm, Q-ac multiagent RL method, is proposed. By perception and conversion action, the learning agents extend learning episodes and derive more observation by less action. The direct communication enhances agents' observation ability to the environment, and the indirect media communication improves agents' ability deriving the optimal action policy. The simulation results on hunter game demonstrate the efficiency of the proposed method.

In this paper we will propose a novel artificial immune model based on error correcting code in the communication engineering. Here, both an antigen and an antibody are assumed to be binary digit strings, and an antigen is defined to correspond to the information bits and an antibody is to the check bits of a codeword in the error correcting code. For any antigen, its antibody is produced through generating check bits. But, unlike the coding theory in the communication engineering, in this paper, codewords to be able to correct error bits are produced by combinational method. In the primary stage antibodies are produced and pooled in the immune system. The clonal selection principle is computationally realized with finding check bits(Ab) specific to the information bits(Ag). At last it is shown that this system can be applied to the pattern recognition tasks and have the associative property.

This paper proposes a fair allocation method of the job in a call center adapting the multiagent system with self-interested agents on the basis of the theory of fair allocation to the market economy for realizing fairness to the job of the agent who works in a call center. This method leads to a problem solving of the burnout, and it is one of the subjects in a call center. Fair allocation is one of desirable allocation from viewpoint of individual rationality and social welfare, because it is considered as an allocation, which fills envy-free and Pareto efficiency.

Multiagent reinforcement learning has gained increasing attention in recent years. The authors discuss coordination means for sharing episodes and sharing policies in the field of multiagent reinforcement learning. From the point of the view of reinforcement learning, we analyse the performance of indirect media communication among multi-agents on an ant colony system which is an efficient method that uses pheromones to solve optimization problems. Based on the above, we propose the Q-ACS method, modifying the global updating rule in ACS for learning agents to share better episodes benefited from the exploitation of accumulated knowledge. Meanwhile, taking the visited times into account, we propose T-ACS by presenting a state transition policy for learning agents to share better policies, benefiting from biased exploration. To demonstrate the coordination performance of learning agents in our methods, we conducted experiments on an optimization problem, the traveling salesman problem. Comparison of results with ACS, Q-ACS and T-ACS show that the improved methods are efficient for solving the optimization problem.

Reinforcement learning (RL) is an efficient method for solving Markov decision processes (MDPs) without any priori knowledge about an environment. Q-learning is a representative RL. Though it is guaranteed to derive the optimal policy, Q-learning needs numerous trials to learn the optimal policy. By the use of the feature of Q value, this paper presents an accelerated RL method, the Q-ae learning. Further, utilizing the dynamic programming principle, this paper proves the convergence to the optimal policy of the Q-ae learning under deterministic MDPs. The analytical and simulation results illustrate the efficiencies of the Q-ae learning under deterministic and stochastic MDPs.

For solving Markov decision processes with incomplete information on robot learning tasks, model-based algorithm makes effective use of gathered data, but usually requires extreme computation. Dyna-Q is an architecture that uses experiences to build a model and uses the model to adjust the policy simultaneously, however, it does not help an agent to explore an environment actively. In, this paper, we present an Exa-Q architecture which learns models and makes plans using learned models to help the reinforcement learning agent explore an environment actively and improve the reinforcement function estimate. As a result, the Exa-Q architecture can identify an environment fully and speed up the learning rate for deriving the optimal policy. Experimental results demonstrate that the proposed method is efficient.

We propose the multi-state commitment (MSC) method to speed-up heuristic search algorithms for semi-optimal solutions. The real-time A* (RTA*) and the weighted A* (WA*) are representative heuristic search algorithms for semi-optimal solutions and can be viewed as single-state and an all-state commitment search algorithms respectively. In these algorithms, there is a tradeoff between the risk of making wrong choices in search process and the amount of memory for the recovery, with RTA* and WA* being the extremes. The MSC method introduces a moderate and flexible characteristic into these algorithms and can increase the performance dramatically in problems such as the N-puzzle. In this paper, by introducing a commitment-list, we show a modification of RTA* and WA* to their MSC versions without violating their completeness. Then, we experiment with their performance in maze and N-puzzle problems, and discuss conditions that the MSC method is effective.