Browsing by Author "Yang, Hsiang-Yu"
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
Item type:Item, A Framework for Simulating Agent-Based Cooperative Tasks in Crowd Simulation(2018-01-01) ;Wong, Sai-Keung ;Chou, Yi-Hung ;Yang, Hsiang-Yu ;資訊工程學系Department of Computer ScienceThis paper presents a novel agent-based approach to simulate cooperative tasks in crowd simulation. Our framework consists of two kinds of agents: pedestrians and workers. A cooperative task requires two or more workers to simultaneously perform actions on objects. The workers should cooperate with each other to finish tasks. This framework considers several basic cooperative behaviors including pushing obstacles away from blocked exits, lifting cargos and carrying them to a destination, and pulling objects using ropes. A complex task can be decomposed into several simple tasks and the simple tasks are finished either in a sequential or parallel order. Our framework also simulates crowd behaviors such as workers joining and leaving cooperative tasks, moving objects around obstacles, collision avoidance for agents, and way giving. We demonstrate examples for simulating different cooperative behaviors. Our framework can be applied to movies, crowd evacuation, narrative systems, task planning simulation, and games.Item type:Item, Effects of Reward Terms in Agent-Based Box-Manipulation Animation Using Deep Reinforcement Learning(2019-01-01) ;Yang, Hsiang-Yu ;Wong, Chien-Chou ;Wong, Sai-Keung ;資訊工程學系電機學院Agent-based box manipulation has wide applications in computer animation and robotics. Deep reinforcement learning can be applied to generate animations of agent-based box manipulation. This paper focuses on push-manipulation in an agent-based animation. A policy is learned in a learning session in which an agent receives a reward that is a combination of different types of reward terms. Based on the received reward, the policy is improved gradually. In this paper, we investigate the effects of each reward term in-depth in a framework that is integrated with deep reinforcement learning. We also propose a simple way to produce different animation types. We performed several examples and analyzed our findings in details.Item type:Item, New vascular ring connectors in surgery for intramural haematoma of the abdominal aorta progressing to rupture(2013-07-01) ;Lee, Chih-Hsien ;Ko, Li-Wei ;Lin, Yi-Chang ;Yen, Chih-ChienYang, Hsiang-YuAortic intramural haematoma is similar to classic aortic dissection, which causes a life-threatening medical condition, and immediate diagnosis and treatment are crucial. The optimal therapy for intramural haematoma of the abdominal aorta remains controversial. Conservative medical management is usually the first choice of treatment for uncomplicated cases. Surgical intervention is usually required for complicated intramural haematomas of the abdominal aorta, including conventional open repair and endovascular treatment with stent-grafts. A new vascular ring connector that achieves a quick, blood-sealed and sutureless anastomosis has been designed for aortic dissection. We herein report a case of intramural haematoma of the abdominal aorta, progressing to rupture on day 14 after onset, which had successful aortic repair with the new vascular ring connector. The new vascular ring connector could be an alternative method for the treatment of complicated intramural haematomas of the abdominal aorta.