Shotaro Kamio

Learn More
The cooperation of several robots is needed for complex tasks. The cooperation methods for multiple robots generally require exact goal or sub-goal positions. However, it is difficult to direct the goal or sub-goal positions to multiple robots for the sake of cooperation with each other. Planning algorithms reduce the burden for this purpose. In this paper,(More)
We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) that allows a real robot to execute real-time learning. Our technique does not need a precise simulator because learning is done with a real robot. Moreover, our technique makes it possible to learn optimal actions in real robots. We show the result of an(More)
The multi-agent cooperation has been proved useful in executing many complex tasks. In our previous paper, we proposed a path planning algorithm based on a random sampling for the sake of the multi-agent cooperation. However, the action path of the robots is liable to be deviated by the noise in the real world. Thus, some correction mechanism is required to(More)
The driving and damping mechanism of plasma flow is an important issue because flow shear has a significant impact on turbulence in a plasma, which determines the transport in the magnetized plasma. Here we report clear evidence of the flow damping due to stochastization of the magnetic field. Abrupt damping of the toroidal flow associated with a transition(More)
To execute a task consisting of multiple subtasks using a robot, we need to determine the subtask execution order. We investigated the problem of cooperative object transport by multiple robots in a previous study. This is a task in which multiple robots carry an object to a specified goal by passing the object between each other. This paper proposes two(More)
In order to evaluate the electron cyclotron (EC) heating power inside the Large Helical Device vacuum vessel and to investigate the physics of the interaction between the EC beam and the plasma, a direct measurement system for the EC beam transmitted through the plasma column was developed. The system consists of an EC beam target plate, which is made of(More)
We introduce a technique that allows a real robot to execute real-time learning, in which GP and RL are integrated. In our former research, we showed the result of an experiment with a real robot " AIBO " and proved the technique performed better than the traditional Q-learning method. Based on the proposed technique , we can acquire the common programs(More)