• International Journal of Control, Automation, and Systems
• /
• 제6권3호
• /
• pp.401-412
• /
• 2008

This paper discusses a design methodology of cooperative path planning for dynamical multi-agent systems with spatial and temporal constraints. The cooperative behavior of the multi-agent systems is specified in terms of the objective function in an optimization formulation. The path of achieving cooperative tasks is then generated by the optimization formulation constructed based on a differential flatness approach. Three scenarios of multi-agent tasking are proposed at the cooperative task planning framework. Given agent dynamics, both spatial and temporal constraints are considered in the path planning. The path planning algorithm first finds trajectory curves in a lower-dimensional space and then parameterizes the curves by a set of B-spline representations. The coefficients of the B-spline curves are further solved by a sequential quadratic programming solver to achieve the optimization objective and satisfy these constraints. Finally, several illustrative examples of cooperative path/task planning are presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.154-154
• /
• 2000

The cooperative strategy for the teleoperated multi-agent system is presented. And this scheme has been applied to the teleoperated robot soccer system that is newly proposed. For the teleoperated robot soccer system, we made mapping functions to control a 2-wheeled mobile robot using a 2 DoF stickcontroller. The simulation with a real stickcontroller has been evaluated the performance of the proposed mapping function. Then, the basic cooperation strategy has been tested between teleoperated robot and autonomous robot It is shown that the multi-agent system for teleoperation can have a good performance for a job Like a scoring a goal

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.205-211
• /
• 2024

Effective warehouse management requires advanced resource planning to optimize profits and space. Robots offer a promising solution, but their effectiveness relies on embedded artificial intelligence. Multi-agent reinforcement learning (MARL) enhances robot intelligence in these environments. This study explores various MARL algorithms using the Multi-Robot Warehouse Environment (RWARE) to determine their suitability for warehouse resource planning. Our findings show that cooperative MARL is essential for effective warehouse management. IA2C outperforms MAA2C and VDA2C on smaller maps, while VDA2C excels on larger maps. IA2C's decentralized approach, focusing on cooperation over collaboration, allows for higher reward collection in smaller environments. However, as map size increases, reward collection decreases due to the need for extensive exploration. This study highlights the importance of selecting the appropriate MARL algorithm based on the specific warehouse environment's requirements and scale.

• 정보처리학회논문지B
• /
• 제10B권1호
• /
• pp.21-26
• /
• 2003

인간의 협동적인 활동에서 협상은 협동적인 행위를 방해할 수 있는 충돌을 해결하는데 중요한 역할을 담당한다. 이를 위해 멀티 에이전트 시스템에서의 협상이 공통의 에이전트 통신 언어를 사용하는 메시지의 교환을 통해 진행한다고 가정한다. 본 논문에서는 자율적이고, 자기 목표에 충실하면, 한정된 자원을 가진 BDI 에이전트를 위한 합리적인 협상 메타 언어를 가정한다. 또한 에이전트의 정신적인 상태에 바탕을 두고 통신하는 BDI 에이전트를 위한 협상 프로토콜을 제안한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2010년도 춘계학술대회 논문집
• /
• pp.333-334
• /
• 2010

• 한국컴퓨터정보학회논문지
• /
• 제11권2호
• /
• pp.285-294
• /
• 2006

분산 환경에서 다중 사용자간의 협력 작업을 효과적으로 지원하는 협력 작업에 대한 요구가 급격하게 증가하고 있다. 이러한 협력 작업은 그룹 통신 기술, 분산 처리 기술 등의 다양한 기술적 사항들이 해결되어야 하며, 협력 작업 응용이 갖는 공통적인 요구 사항들이 많이 존재하므로 응용을 개발할 때마다 이러한 요구 사항들을 중복하여 개발하는 것은 많은 개발 비용이 소요되며 중복 투자되는 부분이 많게 된다. 따라서, 협력 작업 응용이 공통적인 요구 사항들과 응용을 보다 경제적으로 개발할 수 있는 체계적인 개발 환경이 필요하다. 이 연구에서는 기존의 이동 에이전트의 조정 모델을 협력 작업응용에 적합하도록 개선한 계층형 역할 기반 조정 모델을 제안하고, 이를 이용해서 이동 에이전트 기반 협력 작업 응용을 위한 개발환경을 설계한다. 계층형 역할 기반 조정 모델은 이동 에이전트들의 다층형 그룹 개념을 제공하고, 각각의 그룹별로 효과적인 조정 정책 구현을 가능하게 하며, 그룹 단위 별로 역할을 부여해서 효과적인 협력 작업 응용 개발을 지원할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제29권1호
• /
• pp.11-19
• /
• 2024

멀티에이전트는 전장 교전 상황, 무인 운송 차량 등 다양한 실제 협동 환경에 사용될 수 있다. 전장 교전 상황에서는 도메인 정보의 제한으로 즉각적인 보상(Dense Reward) 설계의 어려움이 있어 명백한 희소 보상(Sparse Reward)으로 학습되는 상황을 고려해야 한다. 본 논문에서는 전장 교전 상황에서의 아군 에이전트 간 협업 가능성을 확인하며, 희소 보상 환경인 Multi-Robot Warehouse Environment(RWARE)를 활용하여 유사한 문제와 평가 기준을 정의하고, 강화학습 라이브러리인 Ray RLlib의 QMIX 알고리즘을 사용하여 학습 환경을 구성한다. 정의한 문제에 대해 QMIX의 Agent Network를 개선하고 Random Network Distillation(RND)을 적용한다. 이를 통해 에이전트의 부분 관측값에 대한 패턴과 시간 특징을 추출하고, 에이전트의 내적 보상(Intrinsic Reward)을 통해 희소 보상 경험 획득 개선이 가능함을 실험을 통해 확인한다.

• International Journal of Aeronautical and Space Sciences
• /
• 제18권3호
• /
• pp.522-534
• /
• 2017

According to the characteristics of salvo attack for the multiple flight vehicles (MFV), the design of cooperative guidance law can be converted into the consensus problem of multi-vehicle system through the concept of multi-agent cooperative control. The flight vehicles can be divided into leader and followers depending on different functions, and the flight conditions of leader are independent of the ones of followers. The consensus problem of leader-follower multi-vehicle system is researched by graph theory, and the consensus protocol is also presented. Meanwhile, the finite time guidance law is designed for the flight vehicles via the finite time control method, and the system stability is also analyzed. Whereby, the guidance law can guarantee the line of sight (LOS) angular rates converge to zero in finite time, and hence the cooperative attack of the MFV can be realized. The effectiveness of the designed cooperative guidance method is validated through the simulation with a stationary target and a moving target, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.507-510
• /
• 1996

In this paper we present the multi-agent robot system developed for participating in micro robot soccer tournament. The multi-agent robot system consists of micro robot, a vision system, a host computer and a communication module. Mcro robot are equipped with two mini DC motors with encoders and gearboxes, a R/F receiver, a CPU and infrared sensors for obstacle detection. A vision system is used to recognize the position of the ball and opponent robots, position and orientation of our robots. The vision system is composed of a color CCD camera and a vision processing unit. Host computer is a Pentium PC, and it receives information from the vision system, generates commands for each robot using a robot management algorithm and transmits commands to the robots by the R/F communication module. And in order to achieve a given mission in micro robot soccer game, cooperative behaviors by robots are essential. Cooperative work between individual agents is achieved by the command of host computer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권6호
• /
• pp.1431-1448
• /
• 2024

Complexity science is a new stage in the development of systems science that is the frontier areas of contemporary scientific development. Complexity science takes complex systems as the research object, which has attracted widespread attention from researchers in the fields of economy, control, management, and society. In recent years, with the rapid development of science and technology and people's deepening understanding for the theory of complex systems, the systems are no longer an object with a single function, but the systems are composed of multiple individuals with autonomous capabilities through cooperative and cooperation, namely multi-agent system (MAS). Currently, MAS is one of the main models for studying such complex systems. The intelligent control is to break the traditional multi-agent fault-tolerant control (FTC) concept and produce a new type of compensation mechanism. In this paper, the applications of fault-tolerant control methods for MASs are presented, and a discussion is given about development and challenges in this field.