SPT: Hierarchical Agent Control: A Framework For Defining Agent Behavior

ثبت نشده
چکیده

The Hierarchical Agent Control Architecture (HAC) is a general toolkit for specifying an agent's behavior. HAC supports action abstraction, resource management, sensor integration, and is well suited to controlling large numbers of agents in dynamic environments. It relies on three hierarchies: action, sensor, and context. The action hierarchy controls the agent's behavior. It is organized around tasks to be accomplished, not the agents themselves. This facilitates the integration of multi-agent actions and planning into the architecture. The sensor hierarchy provides a principled means for structuring the complexity of reading and transforming sensor information. Each level of the hierarchy integrates the data coming in from the environment into conceptual chunks appropriate for use by actions at this level. Actions and sensors are written using the same formalism. The context hierarchy is a hierarchy of goals. In addition to their primary goals, most actions are simultaneously trying to achieve a set of implicit assumptions. These assumptions are made explicit through the context hierarchy and provide the context under which the agent operates. We have developed a planner, GRASP, implemented within HAC, which is capable of resolving multiple goals in real time. HAC was intended to have wide applicability. It has been used to control agents in commercial computer games and physical robots. Our primary application domain is a simulator of land-based military engagements called "Capture the Flag". HAC's simulation substrate models physics at an abstract level. HAC supports any domain in which behaviors can be reduced to a small set of primitive e ectors such as move and apply-force. At this time de ning agent behavior requires Lisp programming skills; we are moving towards more graphical programming languages. Figure 1: The Capture the Flag domain (CtF). There are two teams; each has a number of movable units and ags to protect. They operate on a map which has di erent types of terrain. Terrain in uences movement speed and forms barriers; terrain also a ects unit visibility. A team wins when it captures all its opponent's ags.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Load-Frequency Control: a GA based Bayesian Networks Multi-agent System

Bayesian Networks (BN) provides a robust probabilistic method of reasoning under uncertainty. They have been successfully applied in a variety of real-world tasks but they have received little attention in the area of load-frequency control (LFC). In practice, LFC systems use proportional-integral controllers. However since these controllers are designed using a linear model, the nonlinearities...

متن کامل

DALI: An Architecture for Intelligent Logical Agents

Many interesting architectures for defining intelligent agents have been proposed in the last years. Logic-based architectures have proved effective for reproducing “intelligent” behavior while staying within a rigorous formal setting. In this paper, we present the DALI multi-agent architecture, a logic framework for defining intelligent agents and multi-

متن کامل

Un modèle dynamique de comportement agent à base de besoins (poster)

The modeling of agents’ behavior is always a significant aspect in multiagents systems’ design. Our approach in this paper consists on proposing a model which, instead of directly defining a hierarchy of actions, specifies a set of needs. This model is inspired from the work of the psychologist Abraham Maslow, about the hierarchical human (but also animals) needs. We show that this structure is...

متن کامل

An Agent-based Framework for Control of Reactor Networks with Autocatalytic Replicators

Several recent studies on autocatalytic reactions in single and coupled continuous stirred-tank reactor (CSTR) networks have demonstrated a rich spectrum of complex behavior. From a control systems perspective, the operating regime of a CSTR network can be manipulated by changing the flow rates between the reactors. Systems of more than one CSTR require multiple controllers and may need transie...

متن کامل

Robust Agent Based Distribution System Restoration with Uncertainty in Loads in Smart Grids

This paper presents a comprehensive robust distributed intelligent control for optimum self-healing activities in smart distribution systems considering the uncertainty in loads. The presented agent based framework obviates the requirements for a central control method and improves the reliability of the self-healing mechanism. Agents possess three characteristics including local views, decentr...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2000