Hostname: page-component-cd9895bd7-lnqnp Total loading time: 0 Render date: 2024-12-25T07:30:00.214Z Has data issue: false hasContentIssue false

Multiagent cooperation based entertainment robot

Published online by Cambridge University Press:  04 May 2006

Huang Yanwen
Affiliation:
Research Institute of Robotics, School of Mechanical Engineering, Shanghai Jiao Tong University, 1954 Huashan Road, Shanghai 200030 (P.R. China)
Cao Qixin
Affiliation:
Research Institute of Robotics, School of Mechanical Engineering, Shanghai Jiao Tong University, 1954 Huashan Road, Shanghai 200030 (P.R. China)
Zhou Jingliang
Affiliation:
Research Institute of Robotics, School of Mechanical Engineering, Shanghai Jiao Tong University, 1954 Huashan Road, Shanghai 200030 (P.R. China)
Huang Yi
Affiliation:
Research Institute of Robotics, School of Mechanical Engineering, Shanghai Jiao Tong University, 1954 Huashan Road, Shanghai 200030 (P.R. China)
Frank L. Lewis
Affiliation:
Automation and Robotics Research Institute, The University of Texas at Arlington, 7300 Jack Newell Blvd. S, Ft. Worth, Texas 76118 (USA)

Abstract

In recent years, cooperation of heterogeneous multiagents (HMAs) has achieved formidable results and gained an increasing attention by researchers. This paper presents an entertainment robot system based on the HMAs' cooperation. This robot is used to distinguish the basic information of a person from the audience and entertain him in the exhibition hall. The main agents include the Arbitration System (AS), the Face Recognition System (FRS), the Position Cognition System (PCS), and the Behavior Planner (BP), which are carved up according to their respective functions. Each agent completes its own task independently and the robot finishes the whole mission through their cooperation. The hybrid control architecture and the data-fusion algorithm based on Bayesian Belief Network are also discussed in this paper.

Type
Article
Copyright
2006 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)