中文 English

Set HomePage Favorite

INTL-SENSOR > cases > Intelligent Robotic Sensor Agents for Environment Monitoring

Intelligent Robotic Sensor Agents for Environment Monitoring

http://www.intl-sensor.com Time:2010/8/26 17:12:20 Count : 2140 times

Emil M. Petriu⁽¹⁾, Gilles G. Patry⁽¹⁾, Thom E. Whalen (2)_,

Abdul Al-Dhaher (1), and Voicu Z. Groza⁽¹⁾

(1) University of Ottawa, Ottawa, ON, Canada

(2) Communications Research Centre Canada, Ottawa, ON, Canada

Abstract – This paper discusses development aspects of a wireless

network of mobile autonomous Robotic Intelligent Sensor Agents

deployed in the field for active investigation of multiple environ-

mental parameters. The collected sensor data are fused in a world

model, which is available to remote human supervisors as an in-

teractive virtual Virtualized Reality^TM environment model.

Keywords – intelligent sensors, mobile agents, distributed sensor

networks, wireless sensors, multi-sensor data fusion, behavior-

based robots, Virtualized Reality^TM, human computer interaction.

I. INTRODUCTION

Information appliances are emerging as the new, information-

intensive, evolutionary stage of the pervasive computing

paradigm [1], [2], [3], and [4]. There is also a growing inter-

est in the pervasive, communication and interfacing standard

aspects of distributed sensors and instrumentation [5], [6],

[7], [8], [9], [10], [11], [12], [13], [14], and [15].

Monitoring environment parameters is a complex task of

great importance in many areas such as the natural living

environment, industrial or laboratory hazardous environments

(biologically, radioactively, or chemically contaminated),

polluted/toxic natural environments, water treatment plants,

nuclear stations, war zones, or remote difficult to reach envi-

ronments such as the deep space or underwater, [16], [17],

and [18].

The objective of our project is the development of a new gen-

eration of autonomous wireless Robotic Intelligent Sensor

Agents (R-ISA) for complex environment monitoring. Moni-

toring is done by continuously collecting sensory data from a

distributed network of stationary and mobile Intelligent Sen-

sor Agents (ISA) deployed in the field. These data, which are

of different nature, are then fused in a world mo del, which is

remotely available to human supervisors as an interactive

virtual environment model.

Human operator expertise is still needed to carry out monitor-

ing tasks requiring a higher level of intelligence. A proper

control of these tasks cannot be accomplished without some

telepresence capability allowing the human operator to ex-

perience the feeling that he/she is immersed in the remote,

out of the harm’s way, Virtualized Reality^TM Environment

(VRE), [19]. The VRE is a generalization of the computer-

generated, essentially synthetic, Virtual Environment (VE)

concept. While still being a computer generated multi-media

world model, VRE is based on information about the

real/physical world objects and phenomena as captured by a

variety of sensors. In order to find efficient solutions to the

complex perception tasks, the humans will have to combine

their intrinsic reactive-behavior with higher-order world

model representations of the immersive VRE systems.

The human-computer interface (HCI) should couple the hu-

man operator and the VRE as transparently as possible.

Having a VRE model of the natural environment that is moni-

tored would also allow for the off-line training of the person-

nel and as a virtual prototyping environment for no-penalty

what-if experiments.

II. SYSTEM ARCHITECTURE

Monitoring natural uncertain environments is a task that is

very much dependent of each application. The complexity of

this task is function of the nature of the parameters and the

nature of the environment to be monitored. The type of sen-

sors, their number and their bandwidth, the difficulties en-

countered while deploying the sensors in the field, the reli-

ability of the sensory data and of the data communication

network, are all requirements that have to be considered when

designing the intelligent sensor agents and the distributed

sensor network architecture. Integrating the partial and het-

erogeneous sensor-views of the environment into a coherent

VRE global model, which has to be easy to use by a com-

puter controller as well as by a human operator is another

important aspect to be considered.

The architecture of the distributed intelligent sensor system

for environment monitoring, shown in Fig. 1, consists of both

stationary ISA’s and mobile R-ISA’s, a wireless communica-

tion network, a shared multimedia VRE, and HCI for the hu-

man supervisor.

A multi-sensor fusion framework, [20] and [21], deals in a

consistent way with a diversity of measurement data pro-

duced by ISA’s. Such a multi-sensor fusion system has to (i)

organize data collection and signal processing from different

types of sensor, (ii) produce local and global world models

Keywords:

Intelligent Robotic Sensor Agents for Environment Monitoring

Related Information

Recommended information

INTL-SENSOR CopyRight
© Copyright By WWW.INTL-SENSOR.COM All Right
tel：86 010-67152280/67114885/67124125
E-mail:pcb@intl-sensor.com

京ICP备07000717号
京公网安备110101000113号