• 한국콘텐츠학회논문지
• /
• 제14권9호
• /
• pp.1-13
• /
• 2014

가상 세계의 에이전트의 설계를 위해서 물리적 사실감뿐만 아니라 동적으로 변하는 상황에 대응하는 에이전트의 다양한 물리적 행동들의 구현이 필수적이다. 본 연구는 다양한 행동을 구현하기 위한 기본 동작들을 재활용한 복합적 행동 및 에이전트가 즉시 주위의 환경에 반응할 수 있는 기법을 구현한다. 또한 관절에 대한 에이전트의 신체 구조를 설계하고 기본 동작 또는 복합 동작을 실시간으로 표현한다. 이 기법을 구현하기 위해서, 기본적인 관절 회전을 위한 애니메이션 함수와 기본 동작으로 이루어진 전체적 동작을 구성하는 기능을 구현한다. 이러한 동작들은 에이전트의 목적을 달성하는 계획에 포함될 수 있다. 즉, 재활용된 기본 동작을 이용하여 다양한 행동을 쉽게 생성하는 기법을 개발한다. 본 연구는 '걸으면서 먹다'와 같은 병렬 행동을 구현할 때 뚜렷한 장점을 가진다. 이는 두 개 이상의 행동들은 우선순위에 따라 자연스럽게 병렬 행동으로 조합된다. 이를 증명하기 위해 몇 개의 복합 행동 및 병렬 행동을 구현한다.

• International Journal of Control, Automation, and Systems
• /
• 제6권6호
• /
• pp.904-914
• /
• 2008

An action-selection-mechanism(ASM) has been proposed to work as a fully connected finite state machine to deal with sequential behaviors as well as to allow a state in the task program to migrate to any state in the task, in which a primitive node in association with a state and its transitional conditions can be easily inserted/deleted. Also, such a primitive node can be learned by a shortest path-finding-based reinforcement learning technique. Specifically, we define a behavioral motivation as having state-dependent value as a primitive node for action selection, and then sequentially construct a network of behavioral motivations in such a way that the value of a parent node is allowed to flow into a child node by a releasing mechanism. A vertical path in a network represents a behavioral sequence. Here, such a tree for our proposed ASM can be newly generated and/or updated whenever a new behavior sequence is learned. To show the validity of our proposed ASM, experimental results of a mobile robot performing the task of pushing- a- box-in to- a-goal(PBIG) will be illustrated.

• IEIE Transactions on Smart Processing and Computing
• /
• 제1권3호
• /
• pp.192-200
• /
• 2012

In order for humans and robots to interact in daily life, robots need to understand human speech and link it to their actions. This paper proposes a hierarchical behavior model for robot action control using natural language commands. The model, which consists of episodes, primitive actions and atomic functions, uses a sentential cognitive system that includes multiple modules for perception, action, reasoning and memory. Human speech commands are translated to sentences with a natural language processor that are syntactically parsed. A semantic parsing procedure was applied to human speech by analyzing the verbs and phrases of the sentences and linking them to the cognitive information. The cognitive system performed according to the hierarchical behavior model, which consists of episodes, primitive actions and atomic functions, which are implemented in the system. In the experiments, a possible episode, "Water the pot," was tested and its feasibility was evaluated.

• 한국콘텐츠학회논문지
• /
• 제11권7호
• /
• pp.9-20
• /
• 2011

본 논문은 가상세계속의 가상인간의 다양한 행동들을 제한된 개수의 기본행동들로써 구현하고자 한다. 먼저 객체들의 속성과 행동 등을 통합적으로 나타내주는 지식베이스인 온톨로지를 사용하여 다양한 행동들을 행동계층구조로 조직하고 그 속에서 행동들은 세부 행동들로 구체화한다. 가상인간의 기본행동은 기초 동작들의 조합으로 만들어지고 기본행동들을 최대한 재사용함으로써 다양한 행동들을 효과적으로 구현할 수 있게 설계한다. 이 때 기본행동들을 정밀성이나 사실성보다 간소함과 다양성에 초점을 맞추어 구현하고자 한다. 이를 바탕으로 가상 에이전트들의 특성을 파악하고 특성에 따라 에이전트가 고유의 패턴을 가지고 동작을 생성하는 방법을 개발한다. 또한 가상의 에이전트가 주변의 정성적 변화에 적응하여 동작을 변화하는 방법을 제시한다. 이렇게 제시된 방법들을 인간의 실제 움직임들 즉, 걷기, 달리기, 던지기 등의 동작에 적용해 실현가능성을 검증한다.

• International Journal of Contents
• /
• 제15권4호
• /
• pp.16-26
• /
• 2019

The efficient implementation of various physical actions of agents to respond to dynamically changing situations is essential for the simulation of realistic agents and activities in a cyber world. To achieve a maximum diversity of actions and immediate responsiveness to abrupt changes in situations, we have developed an animation technique in which complex actions are recursively constructed by reusing a set of primitive motions, and agents are designed to react in real-time to abrupt ambient changes by computationally satisfying kinematic constraints on body parts with respect to their goals. Our reusing scheme is extended to visualize the procedure of realistic intricate situations involving many concurring events. Our approach based on motion reuse and recursive assembly has clear advantages in motion variability and action diversity with respect to authoring scalability and motion responsiveness compared to conventional monolithic (static) animation techniques. This diversity also serves to accommodate the characteristic unpredictability of events concurring in a situation due to inherent non-determinism of associated conditions. To demonstrate the viability of our approach, we implement several composite and parallel actions in a dynamically changing example situation involving events that were originally independent until coincidentally inter-coupled therein.

• East Asian mathematical journal
• /
• 제35권3호
• /
• pp.357-363
• /
• 2019

Let the circle act on a compact almost complex manifold M with a non-empty discrete fixed point set. To each fixed point, there are associated non-zero integers called weights. A positive weight w is called primitive if it cannot be written as the sum of positive weights, other than w itself. In this paper, we show that if every weight is primitive, then the Todd genus Todd(M) of M is positive and there are $Todd(M){\cdot}2^n$ fixed points, where dim M = 2n. This generalizes the result for symplectic semi-free actions by Tolman and Weitsman [8], the result for semi-free actions on almost complex manifolds by the author [6], and the result for certain symplectic actions by Godinho [1].

• 대한수학회보
• /
• 제60권4호
• /
• pp.1025-1034
• /
• 2023

Let U be the restricted quantized enveloping algebra Ũ_q(𝖘𝖑₂) over an algebraically closed field of characteristic zero, where q is a primitive 𝑙-th root of unity (with 𝑙 being odd and greater than 1). In this paper we show that any indecomposable submodule of U under the adjoint action is generated by finitely many special elements. Using this result we describe all ideals of U. Moreover, we classify annihilator ideals of simple modules of U by generators.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2027-2032
• /
• 2003

For action selection as well as learning, simple associations between stimulus and response have been employed in most of literatures. But, for a successful task accomplishment, it is required that an animat can learn and express behavioral sequences. In this paper, we propose a novel action-selection-mechanism to deal with sequential behaviors. For this, we define behavioral motivation as a primitive node for action selection, and then hierarchically construct a network with behavioral motivations. The vertical path of the network represents behavioral sequences. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new sequential behaviors is learned. To show the validity of our proposed ASM, three 2-D grid world simulations will be illustrated.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.496-498
• /
• 2004

An action-selection-mechanism is proposed to deal with sequential behaviors, where associations between some of stimulus and behaviors will be learned by a shortest-path-finding-based reinforcement team ins technique. To be specific, we define behavioral motivation as a primitive node for action selection, and then sequentially construct a network with behavioral motivations. The vertical path of the network represents a behavioral sequence. Here, such a tree fur our proposed ASM can be newly generated and/or updated. whenever a new sequential behaviors is learned. To show the validity of our proposed ASM, some experimental results on a "pushing-box-into-a-goal task" of a mobile robot will be illustrated.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.178-182
• /
• 2002

For action selection as well as teaming, simple associations between stimulus and response have been employed in most of literatures. But, for successful task accomplishment, it is required that artificial life system can team and express behavioral sequences. In this paper, we propose a novel action-selection-mechanism to deal with behavioral sequences. For this, we define behavioral motivation as a primitive node for action selection, and then hierarchically construct a tree with behavioral motivations. The vertical path of the tree represents behavioral sequences. Here, such a tree for our proposed ASM can be newly generated and/or updated, whenever a new behavioral sequence is learned. To show the validity of our proposed ASM, three 2-D grid world simulations will be illustrated.