• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.792-812
• /
• 2022

Multi-agent systems often need to achieve the goal of learning more effectively for a task through coordination. Although the introduction of deep learning has addressed the state space problems, multi-agent learning remains infeasible because of the joint action spaces. Large-scale joint action spaces can be sparse according to implicit or explicit coordination structure, which can ensure reasonable coordination action through the coordination structure. In general, the multi-agent system is dynamic, which makes the relations among agents and the coordination structure are dynamic. Therefore, the explicit coordination structure can better represent the coordinative relationship among agents and achieve better coordination between agents. Inspired by the maximization of social group utility, we dynamically construct a factor graph as an explicit coordination structure to express the coordinative relationship according to the utility among agents and estimate the joint action values based on the local utility transfer among factor graphs. We present the application of such techniques in the scenario of multiple intelligent vehicle systems, where state space and action space are a problem and have too many interactions among agents. The results on the multiple intelligent vehicle systems demonstrate the efficiency and effectiveness of our proposed methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.61-77
• /
• 2017

The most challenging issues in the multi-channel MAC of the IEEE 1609.4 standard is how to handle the dynamic vehicular traffic condition with a high mobility, dynamic topology, and a trajectory change. Therefore, dynamic channel coordination schemes between CCH and SCH are required to provide the proper bandwidth for CCH/SCH intervals and to improve the quality of service (QoS). In this paper, we use a Markov model to optimize the interval based on the dynamic vehicular traffic condition with high mobility nodes in the multi-channel MAC of the IEEE 1609.4 standard. We evaluate the performance of the three-dimensional Markov chain based on the Poisson distribution for the node distribution and velocity. We also evaluate the additive white Gaussian noise (AWGN) effect for the multi-channel MAC coordination scheme of the IEEE 1609.4 standard. The result of simulation proves that the performance of the dynamic channel coordination scheme is affected by the high node mobility and the AWGN. In this research, we evaluate the model analytically for the average delay on CCHs and SCHs and also the saturated throughput on SCHs.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.925-926
• /
• 2006

In the multi-agent system for a single task, the action selection can be made for the real-time environment by using the global coordination space, global coordination graph and MAX-PLUS algorithm. However, there are some difficulties in multi-agent system for multi-tasking. In this paper, a real-time decision making method is suggested by using coordination space, coordination graph and dynamic coordinated state of multi-agent system including many agents and multiple tasks. Specifically, we propose locally dynamic coordinated state to effectively use MAX-PLUS algorithm for multiple tasks completion. Our technique is shown to be valid in the box pushing simulation of a multi-agent system.

• Journal of the Korean Society of Physical Medicine
• /
• v.14 no.4
• /
• pp.37-44
• /
• 2019

PURPOSE: The purpose of this study was to compare sitting balance and coordination spastic cerebral palsy in children using the Korean version of Trunk Impairment Scale (K-TIS) as well as to provide basic data about effective postural control treatment for clinicians handling these two types. METHODS: The K-TIS was measured in 29 children diagnosed with diplegic and quadriplegic cerebral palsy (18 with diplegia and 11 with quadriplegia). The average and standard scores of the children's K-TIS subscales and items of the two groups were measured. The two groups' subscales and items were analyzed by using the Mann-Whitney U test. RESULTS: Static sitting balance, dynamic sitting balance, coordination, and total score for children with diplegia were statistically high (p<.05). For all items under static sitting balance, the score for children with diplegia was higher. The first differences in the repeated items of dynamic sitting balance and coordination area that rotates between the upper and lower body were presented. CONCLUSION: The difference in balance and coordination in sitting positions is exhibited in children with diplegia and quadriplegia. For children with spastic quadriplegia, treatments should focus on static sitting balance and coordination, together with a focus on dynamic sitting balance and coordination.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.668-680
• /
• 2006

Web services on the Internet are not always reliable in terms of service availability and performance. Dynamic service coordination capability of a system or an application invoking Web services is essential to cope with such unreliable situations. In dynamic service coordination, if a Web service does not respond within a specific time constraint, it is replaced with another Web service at run time for reliable invocation of Web services. In this paper, we develop an exception based dynamic service coordination framework for Web services. In the framework, all necessary information for dynamic service coordination is explicitly specified and summarized as a set of attributes. Then classes and workflows, supporting dynamic service coordination and invoking Web services, are automatically created based on these attributes. Developers of Web services client programs can make the invocations of Web services reliable by calling the methods of the classes. Some performance loss has been observed in the indirect invocation of a Web service. However, when we consider the flexibility and reliability gained from the method, the performance loss would be acceptable in many cases.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.4
• /
• pp.116-125
• /
• 2019

The Dynamic Vehicle Routing Problem (DVRP) involves a combinatorial optimization problem where new customer demands become known over time, and old routes must be reconfigured to generate new routes while executing the current solution. We consider the high level of dynamism problem. An application of highly dynamic DVRP is the ambulance service where a patient contacts the service center, followed by an evaluation of case severity, and a visit by a practitioner/ ambulance is scheduled accordingly. This paper considers a variant of the DVRP and proposes a decentralized algorithm in which collaborators (Depot and Vehicle), both have only partial information about the entire system. The DVRP is modeled as a periodic re optimization of VRP using the proposed decentralized algorithm where collaborators exchange local information to achieve the best global objective for the current state of the system. We assume the existence of a dispatcher e.g., headquarter of the company who can communicate to vehicles in order to gather information and assigns the new visits to them. The effectiveness of the proposed decentralized coordination algorithm is further evaluated using benchmark data given in literature. The results show that the proposed method performed better than the compared algorithms which utilize the centralized coordination in 12 out of 21 benchmark problems.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.587-594
• /
• 2001

Multi-agent system fits to the distributed and open internet environments. In a multi-agent system, agents must cooperate with each other through a coordination procedure, when the conflicts between agents arise. Where those are caused by the point that each action acts for a purpose separately without coordination. But previous researches for coordination methods in multi-agent system have a deficiency that they cannot solve correctly the cooperation problem between agents, which have different goals in dynamic environment. In this paper, we suggest the automatic coordination model for multi-agent system using neural network and reinforcement learning in dynamic environment. We have competitive experiment between multi-agents that have complexity environment and diverse activity. And we analysis and evaluate effect of activity of multi-agents. The results show that the proposed method is proper.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.11
• /
• pp.36-45
• /
• 1992

A numerical trajectory planning method for path-constrained trajectory planning is proposed which ensures collision-free and time-optimal motions for two robotic manipulators with limited actuator torques and velocities. For each robot, physical constraints of the robots such as limited torques or limited rotational velocities of the actuators are converted to the constraints on velocity and acceleration along the path, which is described by a scalar variable denoting the traveled distance from starting point. Collision region is determined on the coordination space according to the kinematic structures and the geometry of the paths of the robots. An Extended Coordination Space is then constructed` an element of the space determines the postures and the velocities of the robots, and all the constraints described before are transformed to some constraints on the behaviour of the coordination-velocity curves in the space. A dynamic programming technique is them provided with on the discretized Extended Coordination Space to derive a collision-free and time-optimal trajectory pair. Numerical example is included.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.9A
• /
• pp.1075-1082
• /
• 2004

Wireless LAN is a rather mature communication technology connecting mobile terminals. IEEE 802.11 is a representative protocol among Wireless LAN technologies. The basic medium access control (MAC) mechanism of IEEE 802.11 is called distnbuted coordination function (DCF). DCF shows poor throughput and high drop rate as the number of stations and offered traffic load increase. In this paper we propose an effective mechanism using dynamic mimmum contention window(CWmin) in wireless LAN~ and show that performance improves via simulations. Proposed dynamic CWmin scheme exhibits superior performance as the number of stations and offered load grow. As, our proposed scheme is expected to be more effective in highly densed wireless LAN environment.

• Korean Journal of Cognitive Science
• /
• v.10 no.1
• /
• pp.1-11
• /
• 1999

Agent-based systems technology has generated lots of excitement in these years because of its promise as a new paradigm for conceptualizing. designing. and l implementing software systems Especially, there has been many researches for multi agent system because of the characteristics that it fits to the distributed and open Internet environments. In a multiagent system. agents must cooperate with each other through a Coordination procedure. when the conflicts between agents arise. where those are caused b by the point that each action acts for a purpose separately without coordination. But P previous researches for coordination methods in multi agent system have a deficiency that they can not solve correctly the cooperation problem between agents which have different goals in dynamic environment. In this paper. we solve the cooperation problem of multiagent that has multiple goals in a dynamic environment. with an automatic cooperative coordination model using I reinforcement learning. We will show the two pursuit problems that we extend a traditional problem in multi agent systems area for modeling the restriction in the multiple goals in a dynamic environment. and we have verified the validity of the proposed model with an experiment.