Kazutaka Yokota

Synchronized motion by multiple mobile robots using communication

This paper addresses a method for synchronizing motion by multiple autonomous mobile robots using radio communication. The autonomous and decentralized robot system, ACTRESS, is a multi-agent robotic system including multiple autonomous mobile robots. The autonomous mobile robots are developed so as not only to act individually, but also to cooperate with the other robots if they cannot accomplish the task alone. The synchronized motion is sometimes required to execute such cooperative tasks. Every agent of ACTRESS is equipped with the communication system, which enables a message passing between any robotic agents. The prototype ACTRESS system is introduced, and cooperation among multiple robotic agents is discussed. A method for synchronization using the communication system is proposed. The method is applied to the prototype system, and side-by-side motion on the actual mobile robots is implemented as a example of synchronized motion.

Negotiation Method for Collaborating Team Organization among Multiple Robots

In this paper, an organization method for a collaborating team in a multi-agent robotic system is discussed. In order to realize a flexible and robust intelligent robotic system, we have been developing a distributed autonomous robotic system, ACTRESS, which is composed of multiple and heterogeneous robotic agents. In ACTRESS, every robotic agent aids other agents to achieve a common target, which cannot be carried out by a single agent. The agent requiring the collaboration organizes a collaborating team using communication, which consists of a leader agent (called coordinator) and some follower agents (called cooperators). For organizing the collaborating team, we developed an efficient negotiation method with a learning mechanism based on histories of past negotiations, and evaluated the method by an implemented simulator. Firstly, this paper presents teams and negotiation for organization in distributed autonomous robotic systems. Secondly, an organization strategy using negotiation with learning mechanism is discussed. Finally, the implementation and evaluation of this method are described, and experimental results are shown.

Collaborative team organization using communication in a decentralized robotic system

As a flexible and robust intelligent robot system, we have been developing an autonomous and decentralized robot system called ACTRESS, which is composed of multiple robotic agents. In this paper, introducing an idea of cooperative action with group organization and a strategy for cooperative task processing using communication, a method for team organization by efficient negotiation is presented. The efficient negotiation is realized by a newly developed communication functionality called groupcast and a learning mechanism utilizing historical records on past negotiation. The negotiation procedures for team organization are implemented, and as a result of simulation experiments, the efficiency of the learning mechanism is verified.<<ETX>>

Cooperation between the human operator and the multi-agent robotic system: evaluation of agent monitoring methods for the human interface system

This paper first discusses the relation between the human operator and the decentralized autonomous robotic system. The operator relates himself to the system loosely in the decentralized autonomous system. The authors position the operator as a problem solver and a monitor of the system. The human operator is regarded as an agent in the decentralized autonomous robotic system. Then strategies of communication between the human operator and agents are discussed. The authors propose explicit and implicit communication strategies to monitor the system, and several monitoring methods to implement them: time-based and event-based monitoring for explicit communication and eavesdropping messages for implicit communication. The authors compare the monitoring methods in order to ascertain how much information the human operator can gather in each method using simulation. Finally, the characteristics of each monitoring method are analyzed.

Cooperation between a Human Operator and Multiple Robots for Maintenance Tasks at a Distance

A novel concept of the integrated plant system is proposed where multiple robots work together with human operators. We have principally studied how to issue operation commands effectively through a human interface to let multiple robots work in the plant. A human interface system for multi-robot operation is constructed utilizing the WWW system. It is confirmed that multiple robots can actually be operated by the system from a distant place. By applying this system to a nuclear power plant model, we have been examining the performance of the cooperative work with human operators and multiple robots.

A multi-robot teleoperation system utilizing the Internet

The paper describes a human interface system for multi-robot teleoperation using the WWW system. We discuss how to issue operation commands effectively through a human interface to let multiple robots work for plant maintenance tasks. Based on the discussions, an interface system utilizing WWW technology is constructed on the workstation on which our WWW server runs. When the WWW clients require tasks to the robot, the WWW server calls up the interface programs by using Common Gateway Interface scripts. It is confirmed that the operator can carry out inspection tasks from a distant place by teleoperating actual mobile robots using this system.

Omni-directional Autonomous Robots Cooperating for Team Play

In order for multiple robots to accomplish a required task together, they need to communicate, organize themselves and cooperate. We have discussed these issues for the distribute autonomous robot system. The developed technologies are applied to the football game, in which the multiple mobile robots will maneuver and handle the ball towards the goal. The robots we use are holonomic, omni-directional mobile robots with vision and various sensors. They also have wireless LAN devices for communication. They can perform cooperation based on negotiation.

Modeling Environment and Tasks for Cooperative Team Play

In order for multiple robots to accomplish a required task together, they need to communicate information, organize themselves and cooperate. To this end, appropriate models of environment and tasks are essential. However, it is often difficult to prepare a complete system for application in order to prove the feasibility of newly developed technology because the targeted application is too complicated. The robotic football game offers a simple multi-agent environment for which it is not impossible to develop a complete set of models while there is infinite possibilities to introduce sophisticated models and methods. The paper discusses software design of football playing robots, focusing on environment and task modeling which enables communication and cooperation among the robots.

A Human Interface for Interacting with and Monitoring the Multi-Agent Robotic System

We are developing an autonomous and decentralized robot system ACTRESS. There are two classes of humans who deal with ACTRESS. One is the developer who develops robotic agents of the system, and the other is the operator who runs the system for specific tasks. We have developed a human interface system for the multi-agent robotic system to be used in both development and run-time environments.

An environmental visual features based navigation for mobile robot in a corridor environment

This paper presents a navigation method that enables an autonomous mobile robot to localize itself and identify its own orientation in order to follow a path in the environment. Both tasks use the same recognition method. The method is based on features data provided through an image captured by a single camera, which is trained by a neural network. No precise and accurate measurement is used in the proposed navigation method, but the experiment results showed that the proposed method is competent to work in actual environments.