Smart office robot collaboration based on multi-agent programming

As a new Artificial Intelligence (AI) application to our everyday life, we designed and implemented a smart office environment in which various information appliances work collaboratively to support our office activities. In this environment, many cameras and infrared sensors allow handling robots a...

Full description

Saved in:
Bibliographic Details
Published in:Artificial intelligence 1999-10, Vol.114 (1), p.57-94
Main Authors: Mizoguchi, F., Nishiyama, H., Ohwada, H., Hiraishi, H.
Format: Article
Language:English
Subjects:
Agent architecture
Artificial intelligence
Information appliance
Multi-agent programming
Robot collaboration
Smart office
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a new Artificial Intelligence (AI) application to our everyday life, we designed and implemented a smart office environment in which various information appliances work collaboratively to support our office activities. In this environment, many cameras and infrared sensors allow handling robots and mobile robots to perform complex tasks such as printing and delivering document. The delivery task is a typical example of an important class of tasks supporting humans in the smart office. In this paper, such robots are modeled as robotic agents, and collaboration between the agents is realized using multi-agent programming. We have developed a multi-agent robot language (MRL) as an evolution of concurrent logic programming. MRL provides synchronous and asynchronous control of agents based on guarded Horn clauses. It also supports describing an advanced negotiation protocol using broadcast and incomplete messages, and making decisions using a set of logical rules. These features are unified within an MRL framework, yielding an intelligent integration of the robotic agents. We view the smart office environment as a human assistant system through agent collaboration, and this view is novel and extendable as AI for everyday functions.
ISSN:0004-3702
1872-7921
DOI:10.1016/S0004-3702(99)00068-5