Multi-agent Robot Research Articles

An AIS-based optimal control framework for longevity and task achievement of multi-robot systems

Extending the longevity of autonomous agent system in real life application is a difficult task, especially in applications which require continuous high system performance. This paper presents a novel decentralized balancing controlling architecture for longevity and achievement in multi-agent robot systems based on several artificial immune systems (AIS) designs and principles. Simulation experiments have verified the proposed architecture has good capability to efficiently minimize the trade-off in system achievement while maintaining system sustainability, even in very demanding situations.

Non-Collision Conditions in Multi-Agent Virtual Leader-Based Formation Control

Formation control is one of the most important issues of group coordination for multi-agent robots systems. Some schemes are based on the leader-followers approach where some robots are considered as group leaders which influence the group behaviour. In this work, we address a formation strategy using a virtual leader which has communication with the rest of the follower robots, considered as omnidirectional robots. The virtual leader approach presents advantages such as analysis simplification and fewer sensing requirements in the control law implementation. The formation control is based on attractive potential functions only. The control law guarantees the convergence to the desired formation but, in principle, does not avoid inter-agent collisions. A set of necessary and sufficient non-collision conditions based on the explicit solution of the closed-loop system is derived. The conditions allow concluding from the initial conditions whether or not the agents will collide. The results are extended to the case of unicycle-type robots.

Selected Papers from SCIS & ISIS 2010 – No.1

SCIS & ISIS is a biennial international joint conference on soft computing and intelligent systems, with research ranging from fuzzy systems, neural networks, and evolutionary computation to multi-agent systems, artificial intelligence, and robotics. SCIS & ISIS 2010 consisted of the 5th International Conference on Soft Computing and Intelligent Systems (SCIS) and the 11th International Symposium on Advanced Intelligent Systems (ISIS), held at Okayama Convention Center on December 8-12, 2010. Original presentations numbered 302 and participants 322. After preliminary selection by SCIS & ISIS 2010 session chairs, we listed over 70 papers to be published in extended form in the Special Issue of the Journal of Advanced Computational Intelligence and Intelligent Informatics. After inviting these authors to submit papers for this special issue, we had two referees to review them and accepted 27 for publication in Vol.15, Nos.7 and 8 in 2011. This special issue presents 15 of these papers covering most conference topics, including fuzzy theory, learning methods, neural networks, and evolutionary computation, with a focus on reinforcement learning, multi-agent system, nonlinear estimation, and real-world applications to visual system, robotics and energy. We thank the authors and reviewers for their invaluable contributions toward making this special issue possible. We are also grateful to Editors-in-chief Prof. Toshio Fukuda of Nagoya University and Prof. Kaoru Hirota of the Tokyo Institute of Technology for inviting us to serve as Guest Editors.

A Novel Method for Controlling Multi-agent Robot

A Novel Method for Controlling Multi-agent Robot

Biologically inspired confinement of multi-robot systems

Confinement of a group of mobile robots is of significant interest to the multi-agent robotics community. We develop confinement strategies through simple biological models; in particular, we draw inspiration from the foraging techniques used by bottlenose dolphins to catch fish. For a multi-agent system, we achieve the following goals: 1) provide an algorithm for one group of agents to perpetually confine the other group; 2) characterise the regions from which the herded agents are guaranteed to be captured. The simplicity of the model allows easy implementation in engineered devices (e.g., exploiting the collision avoidance modules already embedded in unmanned air and ground vehicles) and the richness of the model allows replication of a complex biological phenomenon, such as capturing of prey.

An artificial neural network based dynamic controller for a robot in a multi-agent system

This paper proposes the modelling and simulation of an artificial neural network based computed torque controller for the trajectory planning of a robot in a multi-agent robot soccer system. The controller is designed for the tracking of the soccer robot along a dynamic Bezier path. Dynamics of the robot is formulated directly in terms of the motor torque which is more realistic than the conventional methods that are based on heading velocities. The primary feedback loop of the proposed scheme includes a kinematic controller, which generates an appropriate heading velocity command. A dynamic controller included in the inner feedforward path generates a control torque for minimizing the tracking velocity error. Another artificial neural network controller, included in a separate feedforward path, compensates for the deficiencies in the control torque due to the unknown robot dynamics. The on-line learning rules are formulated by ensuring the stability of the entire system using the Lyapunov criterion.

Selected Papers from SCIS & ISIS 2008 – No.1

Welcome to this special issue of the Journal of Advanced Computational Intelligence and Intelligent Informatics (JACIII). I am pleased to introduce 41 selected papers presented at the 3rd International Conference on Soft Computing and Intelligent Systems (SCIS) and the 7th International Symposium on Advanced Intelligent Systems (ISIS) held on September 17-21, 2008, at Nagoya University in Nagoya, Japan. This conference featured 401 original papers in presentations attended by some 500 participants. SCIS & ISIS is a biennial international joint conference in the field of soft computing and intelligent systems, including branches of research ranging from fuzzy systems, neural networks, and evolutionary computation to multiagent systems, artificial intelligence, and robotics. This current issue presents 20 papers covering most of the conference topics including fuzzy theory, self-organizing maps, robotics, computer vision, and optimization algorithms. I would like to thank the authors and reviewers and SCIS & ISIS 2008 for making this special issue possible. I am also grateful to Prof. Toshio Fukuda, Nagoya University, and Prof. Kaoru Hirota, Tokyo Institute of Technology, the editors-in-chief, and the SCIS & ISIS 2008 conference staff for inviting me to guest-edit this Journal.

1A1-A18 人間の運搬作業を補助する自律分散型多脚ロボットシステムに関する研究

In this paper, authors proposed a novel multi-legged object transporting system by a herd of autonomous robot agents that can cooperate with human operator. The system is named as "Universal Unipods" ,which consists of a lot of unipod robots to be attached on a single load as a body. A unipod robot is simple in mechanism and it doesn't communicate each other unlike many other multi-agent robot system. The system is designed for not only universal use but also all kinds of users which include aged or handicapped people.

SOCIAL POTENTIAL MODEL TO SIMULATE EMERGENT BEHAVIOUR FOR SWARM ROBOTS

Swarm robotics has a wide range of applications in numerous fields from space and sub-sea exploration to the deployment of teams of interacting artificial agents in disposal systems. In this paper, we introduce a model to simulate the emergent behaviour of multi-agent robot systems, based on principles from physical mechanics. The model is based on mutual interactions among the swarm individuals. The main elements of these interactions are repulsion forces, attraction forces, alignment forces and dissipative forces generated by the swarm members. Using statistical tools, which are used to investigate simulated group behaviour, we discuss the importance of introducing some dissipation to the system as well as the effect of the interaction parameters on various components of the model.

A Bezier curve based path planning in a multi-agent robot soccer system without violating the acceleration limits

This paper proposes an efficient, Bezier curve based approach for the path planning of a mobile robot in a multi-agent robot soccer system. The boundary conditions required for defining the Bezier curve are compatible with the estimated initial state of the robot and the ball. The velocity of the robot along the path is varied continuously to its maximum allowable levels by keeping its acceleration within the safe limits. An obstacle avoidance scheme is incorporated for dealing with the stationary and moving obstacles. When the robot is approaching a moving obstacle in the field, it is decelerated and deviated to another Bezier path leading to the estimated target position. The radius of curvature of the path at its end points is determined from the known terminal velocity constraint of the robot.

Multiagent robotics: toward energy autonomy

In this paper, we propose a novel trend in multiagent robotics: energy autonomy. A definition of energy autonomy is developed from an original concept, “potential energy,” that is under the constraints of remaining energy capacity and the relative distance among robotic agents. Toward energy autonomy, we initially present a simulation of a multiagent robotic system in which each robot is capable of exchanging energy cells with other robots. Our simulation points out that: (1) each robot is able not only to act as an autonomous agent, but also to interact with others to be beyond the individual capabilities; (2) in order to adapt to changes in the environment, each robot is situated as an adaptive agent in a network of neighboring robots, which leads to a state of energy autonomy. Finally, based on the results of the simulation, we adjust the rules for our real multirobot system.

Robot team coordination for target tracking using fuzzy logic controller in game theoretic framework

This paper involves a collision free target tracking problem of multi-agent robot system. Target tracking requires team coordination to maintain a desired formation and to keep team-mates and target together. Every team-mate makes decisions on their moving direction that may spoil the tactical position of others and makes the global coordination task nontrivial. The contribution of the paper is twofold. First, the convergence of target tracking is improved by a new game theoretic concept using a semi-cooperative Stackelberg equilibrium point and a new formation component in the individual cost functions. To enhance the robustness, a PD like fuzzy controller tunes the cost function weights directly for the game theoretic solution and helps to achieve a prescribed value of cost function components. Simulation result for target tracking by a three-member robot team is presented.

Multi Agent Robot System(MARS)의 Robot Agent 간 정보교환을 위한 네트워크 프로그램 구현

홈 서버와 가정용서비스 로봇, 다양한 Device를 포함하는 홈 네트워크 시스템을 이용하여 가정환경 내에서 발생 가능한 다양하게 분산된 임무들을 수행하는데 있어서 Multi-Agent 시스템을 응용하는 것은 효율적이라고 알려져 있다. 이러한 시스템에서 휴먼 인터페이스와 물리적 서비스 제공의 중추 역할을 하는 것은 바로 지능형 서비스 로봇이다. 따라서, 기존의 Multi Agent System을 응용하여 Multi Agent Robot System을 정의할 수 있다. 가정이라는 'open'된 특성의 환경에서 Multi Agent Robot System이 사용자에게 좀 더 효율적인 서비스를 제공하기 위해서는 존재하는 모든 Agent 간의 유기적인 정보교환과 협력이 필요하다. 이것을 위하여 자율구동하며 사용자에게 물리적 서비스를 제공할 수 있는 다수의 로봇들을 Agent로 정의하고, 로봇 Agent간의 통신과, 로봇 이외의 Agent로써의 역할을 감당할 수 있는 홈 서버 등의 Agent와 로봇 Agent들의 통신을 사용자 interface에 직접 표현할 수 있는 시뮬레이터를 설계, 제시한다. Using home network system including home server, home service robot, a variety of device, it is generally known that application of Multi Agent System for performing variously distributed process that can be occur in home environment, is efficient method. In this system, it is intelligent service robot that a key of human interface and physical service offer Therefore, using application of established multi agent system, we can defined Multi Agent Robot System. In 'open' home environment, between all agent data interaction and cooperation are needed for Multi Agent System offer to user that more efficient service. For this, we focus our attention on define as agent that can autonomic drive and offer to user that physical service robots and, design, suggest the simulator can display that between robot agents communication or between other agents, like home server, and robot agents communication information to user interface.

Adaptive and cooperative mobile robots

This paper focuses on the development of intelligent multiagent robot teams capable of acting autonomously and of collaborating in a dynamic environment to reach team objectives. The paper proposes a new adaptive action selection architecture that enables a team of robot agents to achieve adaptive cooperative control and modify their performance during the specified time of the mission. These abilities are important because of uncertainty in the environmental conditions and because of possible functional failures in some team members. The improvement in team performance is achieved by updating the control parameters of the robots based on knowledge acquired on-line. Experiments have been conducted on teams of mobile robots performing a cooperative box-pushing task. The results show that the robot teams were able to achieve adaptive cooperative control despite dynamic changes in the environment and variations in the capabilities of the team members.

Intelligent decision making in multi-agent robot soccer system through compounded artificial neural networks

This paper proposes a two-stage approach using artificial neural networks for the intelligent decision-making by the robots in a MiroSot small league. The first stage involves the use of an evolutionary algorithm for getting a rough estimate of the neural network weight matrices. The proposed approach is then generalized to the case of quick, intelligent and accurate decision-making in the case of a robot soccer system with robots utilizing the concept of compounded artificial neural networks. In the proposed approach a soccer field is divided into three zones so that the decision of the robots depends on the zone of the ball at any instant. The concept of a forward robot is also introduced in this paper to enhance the accuracy of the decision-making with the global strategy of advancing towards the goal area of the opponent for scoring a goal. Simulation results indicate that the proposed techniques are very effective in taking intelligent decision-making in a multi-agent robot soccer system in MiroSot small league as well as middle league.

Consensus Based Formation Control and Trajectory Tracing of Multi-Agent Robot Systems

Multi-Agent Robot Systems (MARS) are, nowadays, an important research area within robotics and Artificial Intelligence. A growing number of systems have been presented in the literature recently. This paper develops a general method of controller design for formation keeping and motion trajectory tracing of the MARS. A novel motion model about the motion trajectory tracing and group formation control of MARS for fixed and changing interaction is presented. Based on this model and the consensus theory, two theorems about the condition of mobile stability properties of the system are analyzed and proved. Finally, the validity of this scheme is supported by computer simulation.

Multi-agent robot systems as distributed autonomous systems

In the numerous existing studies dealing with multi-agent robot systems, the systems are positioned on the crossover area of robotics and distributed autonomous systems. Multi-agent robots perform many tasks, which are classified into six types according to the dimension of the goal state and the number of iterations of the tasks. This paper surveys earlier studies on multi-agent robots for each type, such as multi-robot motion-planning algorithms and exploration algorithms of multiple robots. The tasks that multi-agent robots can perform are becoming increasingly more complex as they move from single, one-time tasks to those involving many iterations. This study is an investigation of the current trends and the potentials for multi-agent robot systems.

変形ロジスティック写像による間欠性カオスを用いたマルチエージェントロボットのデッドロック回避手法

変形ロジスティック写像による間欠性カオスを用いたマルチエージェントロボットのデッドロック回避手法

1A1-N-029 自律分散ロボットによる任意編隊形成と適応移動制御(マルチエージェントロボットシステム,生活を支援するロボメカ技術のメガインテグレーション)

1A1-N-029 自律分散ロボットによる任意編隊形成と適応移動制御(マルチエージェントロボットシステム,生活を支援するロボメカ技術のメガインテグレーション)

1A1-N-028 方策勾配法を用いた運動方程式中のパラメータ学習 : 2ストーン系のカーリングゲーム(マルチエージェントロボットシステム,生活を支援するロボメカ技術のメガインテグレーション)

1A1-N-028 方策勾配法を用いた運動方程式中のパラメータ学習 : 2ストーン系のカーリングゲーム(マルチエージェントロボットシステム,生活を支援するロボメカ技術のメガインテグレーション)