In this paper, we propose a new robotic system to assist visually impaired people in unknown indoor and outdoor environments. The robotic system, which is equipped with a visual sensor, laser range finders, speaker, gives visually impaired people information about the environment around them. The laser data are analyzed using the clustering technique, making it possible to detect obstacles, steps and stairs. By using the visual sensor, the system is able to distinguish between objects and humans. The PC analyses the sensors data and send information to the visually impaired people by natural language or beep signal. The usefulness of the proposed system is examined experimentally.

The goal of this work is to create a part mechanical, part biological robot that operates on the basis of the neural activity of rat brain cells. In our method, first the rat learns to move the robot by pressing the right and left lever in order to get food. Then, we utilize the data of multi-electrode recordings to train artificial neural networks, which are later employed to control the robot motion based on the brain activity of rats. The results show a good performance of artificial neural network controlling the real robot.

While learning and evolution have been effectively applied to single task performance, multiple task performance still lacks methods that demonstrated to be both reliable and efficient. This paper introduces a new method for multiple task performance based on multiobjective evolutionary algorithms, where each task is considered as a separate objective function. In order to verify the effectiveness, the proposed method is applied to evolve neural controllers for the Cyber Rodent robot that has to switch properly between two distinctly different tasks: (1) protecting another moving robot by following it closely and (2) collecting objects scattered in the environment. Furthermore, the tasks and neural complexity are analyzed by including the neural structure as a separate objective function. The simulation and experimental results using the Cyber Rodent robot show that the multiobjective-based evolutionary method can be applied effectively for generating neural networks which enable the robot to perform multiple tasks, simultaneously.

Robots operating in everyday life environments are often required to switch between different tasks. While learning and evolution have been effectively applied to single task performance, multiple task performance still lacks methods that have been demonstrated to be both reliable and efficient. This paper introduces a new method for multiple task performance based on multiobjective evolutionary algorithms, where each task is considered as a separate objective function. In order to verify the effectiveness, the proposed method is applied to evolve neural controllers for the Cyber Rodent (CR) robot that has to switch properly between two distinctly different tasks: 1) protecting another moving robot by following it closely and 2) collecting objects scattered in the environment. Furthermore, the tasks and neural complexity are analyzed by including the neural structure as a separate objective function. The simulation and experimental results using the CR robot show that the multiobjective-based evolutionary method can be applied effectively for generating neural networks that enable the robot to perform multiple tasks simultaneously.

Nowadays, miscellaneous real and virtual humanoid robots have been developed as artificial communication partners. However, they have not yet come to understand such a mental function of their human partners as is called Kansei. In this paper, Kansei for a robot, so called, 'Artificial Kansei' is proposed as one of the functions of a multi-agent mind model in the view of artificial or robotic individuality.

M.Yokota et al., have proposed the distributed intelligent robot network (DIRN) as one kind of wireless sensor and actor networks (WSANs) consisting of one brain node and numerous sensor and actor nodes with human-friendly interfaces. In order to realize well-coordinated DIRNs, it is very important to develop a systematically computable knowledge representation language universal for any kind of device as well as efficient networking technologies. As a candidate for this purpose, the multimedia description language L/sub md/ was evaluated by applying it to integrated multimedia understanding and various cross-media operations in simulation of DIRN-world interaction.

This paper proposes a new method for simultaneous acquisition of different robot behaviors. The proposed method is based on multiobjective evolutionary algorithm, where each behavior is considered as separate objective function. Based on the Pareto optimal set of neural controllers the user can select the most appropriate based on his requirements. We considered evolution of a neural controller for the Cyber Rodent robot that has to complete simultaneously two different tasks: (1) protecting another moving robot by trying to keep a fixed short distance and (2) keeping a sufficient energy level by capturing the battery packs distributed in the environment. Results show a good performance of proposed method

The mental image directed semantic theory (MIDST) has proposed an intermediate knowledge representation scheme based on an omnisensual mental image model. This paper presents a formal language for describing multimedia contents, L/sub md/, whose syntax and semantics are based on MIDST and its application to linguistic interpretation of human motion data obtained through a motion capture system, which we think will serve for linguistic summarization of immense amount of time-sequenced non-linguistic data such as movies.

In emergency and hazardous environments, autonomous humanoid robots must make decisions based on the environment conditions. In addition, they must send information to human operator and receive high-level commands. In this paper, we apply intelligent algorithms in order to create an autonomous humanoid robot. In addition, a teleoperation system is developed to communicate with the humanoid robot in a long distance through Internet. The experiments using the 21 degree of freedom "Bonten-Maru" humanoid robot show a good performance of the proposed algorithm.

This paper presents a new method for controlling legged robots during the multi support phase, where the robot may have hand contact with the walls, in addition of feet supported on ground. In our method, we consider the contact condition of each foot or hand separately by the locally defined ZMP. The locally defined ZMP are used to plain the robot motion and guaranty the stability. The proposed control algorithm is verified in the real hardware of prismatic joint biped robot. The experimental results show a good performance of the proposed control method.

Evolution of complex behaviours requires a careful selection of genetic algorithm parameters and a large number of computations. In this paper, we considered evolution of recurrent neural controllers for nonMarkovian sequential tasks using a regional model genetic algorithm. The subpopulations apply different strategies and compete with each other. Simulation and experimental results using cyber rodent robot indicate that regional model outperformed single population genetic algorithm by distributing the genetic resources effectively as different strategies successful during the course of evolution.

A crucial issue in reinforcement learning applications is how to set meta-parameters, such as the learning rate and "temperature" for exploration, to match the demands of the task and the environment. In this paper, we propose a method to adjust meta-parameters of reinforcement learning by real-number genetic algorithm. It was shown in simulations of foraging tasks that appropriate settings of meta-parameters, which are strongly dependent on each other, can be found by evolution. Furthermore, we verified in hardware experiments using cyber rodent (CR) robots that the meta-parameters evolved in simulation are helpful for learning in real hardware.