• Journal of Korea Multimedia Society
• /
• v.11 no.3
• /
• pp.353-363
• /
• 2008

A multi-agent system has a longer learning period and larger state-spaces than a sin91e agent system. In this paper, we suggest a new method to reduce the learning time of Nash Q-learning in a multi-agent environment. We apply Macro-actions to Nash Q-learning to improve the teaming speed. In the Nash Q-teaming scheme, when agents select actions, rewards are accumulated like Macro-actions. In the experiments, we compare Nash Q-learning using Macro-actions with general Nash Q-learning. First, we observed how many times the agents achieve their goals. The results of this experiment show that agents using Nash Q-learning and 4 Macro-actions have 9.46% better performance than Nash Q-learning using only 4 primitive actions. Second, when agents use Macro-actions, Q-values are accumulated 2.6 times more. Finally, agents using Macro-actions select less actions about 44%. As a result, agents select fewer actions and Macro-actions improve the Q-value's update. It the agents' learning speeds improve.

• Journal of Korea Game Society
• /
• v.6 no.3
• /
• pp.13-22
• /
• 2006

Games such as sports, RTS, RPG, which teams of players play, require advanced artificial intelligence technology for team management. The existing artificial intelligence enables an intelligent agent to have the autonomy solving problem by itself, but to lack interaction and cooperation between agents. This paper presents "Level Unified Approach Method" with effective role allocation and autonomy in multiagent system. This method allots sub-goals to agents using role information to accomplish a global goal. Each agent makes a decision and takes actions by itself in dynamic environments. Global goal of Team coordinates to allocated role in tactics approach. Each agent leads interactive cooperation by sharing state information with another using Databoard, As each agent has planning capacity, an agent takes appropriate actions for playing allocated roles in dynamic environments. This cooperation and interactive operation between agents causes a collision problem, so it approaches at tactics side for controlling this problem. Our experimental result shows that "Level Unified Approach Method" has better performance than existing rental approach method or de-centralized approach method.

• Advances in robotics research
• /
• v.2 no.3
• /
• pp.201-217
• /
• 2018

Agriculture production is a critical human intensive task, which takes place in all regions of the world. The process to grow and harvest crops is labor intensive in many countries due to the lack of automation and advanced technology. Much of the difficult, dangerous and dirty labor of crop production can be automated with intelligent and robotic platforms. We propose an intelligent, agent-oriented robotic team, which can enable the process of harvesting, gathering and collecting crops and fruits, of many types, from agricultural fields. This paper describes a novel robotic organization enabling humans, robots and agents to work together for automation of gathering and collection functions. The focus of the research is a model, called HARMS, which can enable Humans, software Agents, Robots, Machines and Sensors to work together indistinguishably. With this model, any capability-based human-like organization can be conceived and modeled, such as in manufacturing or agriculture. In this research, we model, design and implement a technology application of knowledge-based robot-to-robot and human-to-robot collaboration for an agricultural gathering and collection function. The gathering and collection functions were chosen as they are some of the most labor intensive and least automated processes in the process acquisition of agricultural products. The use of robotic organizations can reduce human labor and increase efficiency allowing people to focus on higher level tasks and minimizing the backbreaking tasks of agricultural production in the future. In this work, the HARMS model was applied to three different robotic instances and an integrated test was completed with satisfactory results that show the basic promise of this research.

• Journal of Yeungnam Medical Science
• /
• v.2 no.1
• /
• pp.259-264
• /
• 1985

Neuroblastoma is the most common extracranial solid tumor of childhood which presents various clinical symptoms depending on the primary and metastatic sites. However, it has been rarely reported that sudden onset of blindness was the chief complaint of neuroblastoma. A four years old boy was admitted to the Yeungnam University Hospital with the chief complaint of a sudden onset of blindness due to a distant metastasis of abdominal neuroblastoma to the sphenoid sinus. On admission, both side pupils were dilated without light reflex, fundoscopy showed pale optic disk, electroretinogram was subnormal and visual evoked potential showed no response. The liver was palpable in $3{\frac{1}{2}}$ finger breadth from the right costal margin and adult fist sized mass was palpable in the right flank. Skull X-ray showed destructed sphenoid bone and clinoid process and brain CT scan showed tumor mass in the sphenoid sinus and left orbit. Ultrasonogram and CT scan of the abdomen showed large tumor masses around the right kidney and para-aortic and retropancreatic lymph node. IVP showed displaced right calyceal system with preserved contour. Left supraclavicular lymph node which appeared after admission was biopsied and it showed poorly differentiated neuroblasts. He was treated according to the multiagent chemotherapy schedule for stage IV neuroblastoma patient of children's cancer study group. Abdominal tumor masses and sphenoid sinus mass were markedly reduced after 2 courses of the combination chemotherapy of cyclophosphamide, vincristine, DTIC, adriamycin and VM-26. Eventhough the blindness was not improved, the patient has been in good clinical condition.