10204 動的環境における移動ロボットのSensor-Based Controlに関する研究(OS15 知能ロボット)

Abstract

Acquisition of actions based on prediction, which needs some context information, is important for a robot in dynamic environment. In this paper, task of avoiding moving object is employed first. The appropriate actions for this task are learned based on the combination of neural network and reinforcement learning. Architecture with Elman-type recurrent neural network and that without it are compared. Simulation result is shown the effectivity of recurrent neural network for this task. What is more, task of going to goal avoiding moving object is employed, and effect of learning system with Actor-Q architecture which could choose an action from plural that is verified for this task by simulation.