GLUE - A Component Connecting Schema-based Reactive to Higher-level Deliberative Layers for Autonomous Agents

ثبت نشده
چکیده

Several problems need to be addressed when integrating reactive and deliberative layers in a hybrid architecture, most importantly the different time scales of operation and (possibly) different data representations of the individual layers. This paper proposes an interface component called GLUE that is designed to mediate between a schema-based reactive and higher-level deliberative layer. We demonstrate the viability of the conceptual architectural design by defining and implementing a schema-based reactive architecture for a ball following task on an autonomous agent, which is then extended by the GLUE component to interface with a simple deliberative layer.

برای دانلود رایگان 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

GLUE - A Component Connecting Schema-based Reactive to Higher-level Deliberative Layers for Autonomous Agents

Several problems need to be addressed when integrating reactive and deliberative layers in a hybrid architecture, most importantly the different time scales of operation and (possibly) different data representations of the individual layers. This paper proposes an interface component called GLUE that is designed to mediate between a schema-based reactive and higher-level deliberative layer. We ...

متن کامل

Clay: Integrating Motor Schemas and Reinforcement Learning 1 Background and Related Work 1.1 Motor Schemas

Clay is an evolutionary architecture for autonomous robots that integrates motor schema-based control and reinforcement learning. Robots utilizing Clay beneet from the real-time performance of motor schemas in continuous and dynamic environments while taking advantage of adaptive reinforcement learning. Clay coordinates assemblages (groups of motor schemas) using embedded reinforcement learning...

متن کامل

The Cognitive Controller: A Hybrid, Deliberative/Reactive Control Architecture for Autonomous Robots

The Cognitive Controller (CoCo) is a new, three-tiered control architecture for autonomous agents that combines reactive and deliberative components. A behaviour-based reactive module ensures that the agent can gracefully handle the various real-time challenges of its environment, while a logic-based deliberative module endows the agent with the ability to “think ahead”, performing more complex...

متن کامل

Robots as Responsible Agents

The quest for real autonomous robots leads us to discuss the problem about the best possible control architecture enabling that important characteristic. It has been broadly accepted that an hybrid architecture, i.e. putting together both reactive and deliberative paradigmes is needed to efficiently execute tasks in realistic dynamic environments. Our proposal, which is being implemented to con...

متن کامل

Interaction between reactive and deliberative tasks for on-line decision-making

To get actual autonomous engines or systems, it is necessary to equip them with on-line decision-making mechanisms: computation of decisions that fit the current situation, performed in parallel with real execution. However, such a computation introduces a contradiction between requirements on the quality of the decision and on the time at which it will be delivered. This contradiction is all t...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002