Learn More
This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal. We discuss several issues in applying the reinforcement learning method to a real robot with vision sensor by which the robot can obtain information about the changes in an environment. First, we construct a state space in terms of size,(More)
Cognitive developmental robotics (CDR) aims to provide new understanding of how human’s higher cognitive functions develop by means of a synthetic approach that developmentally constructs cognitive functions. The core idea of CDR is “physical embodiment” that enables information structuring through interactions with the environment, including other agents.(More)
This paper presents a constructive model by which a robot acquires the ability of joint attention with a human caregiver based on its embedded mechanisms of visual attention and learning with self-evaluation. The former is to look at a salient object in the robot’s view, and the latter is to learn sensorimotor co-ordination when visual attention has(More)
Coordination of multiple behaviors independently obtained by a reinforcement learning method is one of the issues in order for the method to be scaled to larger and more complex robot learning tasks. Direct combination of all the state spaces for individual modules (subtasks) needs enormous learning time, and it causes hidden states. This paper presents a(More)
A method is proposed which accomplishes a whole task consisting of plural subtasks by coordinating multiple behaviors acquired by a vision-based reinforcement learning. First, individual behaviors which achieve the corresponding subtasks are independently acquired by Q-learning, a widely used reinforcement learning method. Each learned behavior can be(More)
Passive Dynamic Walking (PDW) has been receiving increasing attention as a simple walking method with no or less control, therefore no or less energy consumption. To the best of our knowledge, there are no PDW models with a torso although there have been already many studies on PDW. This paper presents the first step towards applying the PDW principle to(More)
The developmental approach enables us to build adaptive robots, and furthermore, to understand the essence of intelligence from the constructivist viewpoint. In this paper, a new design principle for tactile sensors is proposed to investigate and to utilize developmental processes of robots. Based on the design principle, an anthropomorphic fingertip is(More)