Search

We propose a developmental learning architecture with which a motion-control system learns multiple tasks similar to each other or advanced ones incrementally and efficiently by tuning its behavioral mode. The system is based on a coherent neural network whose carrier frequency works as a mode-tuning parameter. In our experiments, we consider two tasks related to bicycle riding. The first is to ride as temporally long as the system can before it falls down (task 1). The second is an advanced one, i.e., to ride as far as possible in a certain direction (task 2). We compare developmental learning to learn task 2 after task 1 with the direct learning of task 2. We also examine the effect of the mode tuning by comparing variable-mode learning (VML), where the carrier frequency is set free to move, with fixed-mode learning (FML), where the frequency is unchanged. We find that VML developmental learning results in the most efficient learning among the possible combinations. We discuss the effects of the incremental task assignment as well as the behavioral mode tuning in developmental learning.

With remarkable advances of portable computers, users can move around various places with computers in order to achieve their objectives. This paper discusses a dynamic route navigation system which can cope with various kinds of users’ situations, e.g., objectives, profiles, current locations, histories of activities and surrounding status of users. Based on these situations, the system continuously generates users’ action plans in order to navigate to places where the users should visit. In order to obtain the situations effectively, a hierarchical wireless network model is proposed. By utilizing the mobile network, users can acquire information around them and interact with their surroundings. Functions of geographic database systems are employed to visualize the action plans effectively on the small sized display of portable computers. As an example of proposed system, this paper shows navigation system for shopping district where various kinds of shops and many people exist. How to cope with dynamic change of user’s situations in shown for this particular example.