Multi-objective Behavior Coordination Research Articles

環境センシングのための可変型測域センサアレイの知的制御

Recently, in order to reduce secondary disasters at the disaster site, the expectation of rescue robots has been increasing. In the disaster site, many kinds of environments are mixed, for example flat areas, steps, and rubble areas, etc. Therefore, if robots perform the environmental sensing in the complicated environment, it is necessary to change the measurement area and density according to the environment information. In this paper, we develop a Variable Sokuiki Sensor Array as a 3D-distance measurement system for changing measurement area and density. Next we propose an intelligent control method for the sensor array based on Multi-objective Behavior Coordination. Finally, we show results of proposed method in a simulation experiment.

2A1-D06 バネモデルを利用したロボットパートナーの行動制御(コミュニケーション-ロボット)

This paper discusses intelligent behavior control of robot partner. Robot partner is the robot which lives with a person. This paper mainly discusses the movable robots, like "MOBiMac" we developed. Such movable robot is demanded to control position relations with the person adequately. First, we introduce a method of the position control of the robot using a calculation model imitated a spring. Second, we calculate the output of two DC motor using Fuzzy control. Next, we explain Multi-Objective Behavior Coordination that is a method to calculate robot's output to unify plural behaviors. Finally, we discuss the effectiveness of the proposed method through computer simulation results.

Intelligent control for vision-based soccer robots

This paper proposes multi-objective behavior coordination based on fuzzy control and perceptual system for vision-based mobile robots used as a soccer robot. The perception can be assumed as a searching process of information that can navigate an age

20721 視知覚に基づくサッカーロボットの多目的行動調停((III),OS12 インテリジェントシステムと制御)

This paper discusses the perceptual system and action system of a vision-based mobile robot used as a soccer robot. We propose a time-series of a searching method based on a genetic algorithm for the visual perception and multi-objective behavior coordination (MOBeC) with fuzzy controller. Finally, we show several experimental results of vision-based soccer robots.

Behavior Acquisition of Mobile Robots Based on Multi-Objective Behavior Coordination.

This paper is concerned with behavior acquisition of mobile robots based on multi-objective behavior coordination. Based on the concept of structured intelligence, the intelligence of a robot emerges from the interaction among simple functional mechanisms. The multio-bjective behavior coordination plays a role in integrating behavioral modules. A behavioral weight is assigned to each behavioral module represented by a fuzzy controller. To situate its action to the facing environment, the robot dynamically updates behavioral weights according to spatio-temporal context of the environment. The purpose of this paper is to discuss the effectiveness of the multi-objective behavior coordination through the behavior acquisition from the viewpoint of the structured intelligence.

F-1232 移動ロボットの多目的行動調停のための学習(G15-2 ロボットの知能化制御)(G15 ロボティクス・メカトロニクス部門一般講演)

Recently, intelligent robots have been used in various fields. Therefore, a robot should perform flexible perception and decision making. Based on the concept of the structured intelligence, we have proposed a sensory network for the perception and multi-objective behavior coordination (MOBC) for the decision making of the robot. However, the multi-objective behavior takes much time comparing to subsumption architecture, since the multi-objective behavior coordination makes outputs based on the inference results of multiple behavior rules. From the viewpoint of real-time control, the robot should quickly take feasible actions, not optimal actions. Therefore, this paper proposes a control method of the behavioral dimension in multi-objective behavior coordination of the mobile robot. We discuss the effectiveness of the propose method through several experiments of the mobile robot.