Abstract
WAHIBA JOMAA.”Target Tracking for Robot Collaboration” Research Project Dissertation under the direction of Professor BAUDOIN.
Nowadays robots have reached a level of sophistication such that it is now productive to include robot-assisted search teams in urban search and rescue scenarios.
The perceptual interface to the human operator is often a video display that relays images from a camera on the robot. Research into issues concerned with human-robot interaction has suggested that if more intelligence were placed on the robot, it could lessen the load on the human operator and improve performance in the search task.
Within this thesis we focus on the relative performance in a search task in which the robot is controlled by a remote human operator.
The goal of this thesis is to enable the mobile robot CASTOR to follow an a priori defined target. This target can be any colored object (in the thesis a red one chosen). In the case of this application, the target object will be another (master) robot, called ROBUDEM. By implementing this robot following behavior, further robot collaboration tasks can be achieved.
Chapter 1: Teleoperation Overview
I. Introduction
The major goals of robotics is to realize multipurpose service robots that can solve several complex tasks while acting within changing environments such as home infrastructure or outdoors. However robots still have neither creativity nor the ability to think. Therefore, robots will necessarily need to be supervised or directly teleoperated at some point. Teleoperation of robotic systems in hostile and unknown environment is of particular importance in that it aids or replaces the manipulator in handling difficult and possibly dangerous activities.
II. Definitions
The term teleoperation refers simply to the operation of a vehicle or system over a distance. Broadly, understanding all interaction with a mobile robot is part of this definition. Traditionally, teleoperation is divided into direct teleoperation and supervisory control. In direct teleoperation, the operator closes all control loops himself, where as in supervisory control a remarkable amount of the control is exercised by the teleoperator, i.e., the teleoperator is a robot.
The term teleoperation refers to direct teleoperation, while supervisory control is handled under human - robot interaction. Moreover, the term traditional teleoperation refers to direct teleoperation over a distance without a line of sight, but telepresence equipment is noticeable.
In today’s digital world, one has to note that even in the case of the direct teleoperation there usually exist control loops in the teleoperator. Typically these loops control the position or the velocity of the “directly” controlled actuators.
III. Introducing Teleoperated Robots
Many dangerous tasks are more and more expensive and painful for humans. To get to humans demining for example, it is rather slow, tedious, dangerous and expensive. The detection is not always reliable. Big effort is made to remove a single mine. Robots do not require such a complex infrastructure to perform this task. Indeed, a robot could be cheaper to achieve some messy tasks in more than one dangerous environment than a human being, in space a robot costs less than Human. Once a robotic system is successfully built and tested, it can be duplicated easily at reduced costs. Human, on the other hand, is priceless. Robots can be used to take over the most dangerous jobs. “Time is money”. Therefore Humans need time to be trained to accomplish some tasks and get some rest after wards. Robots are never tired and can be deployed 24 hours a day, provided there is enough energy.
Teleoperation platform allows a user to execute or to control remote tasks, i.e. without being present simultaneously where the action takes place. Tele-operation tries to minimize risks during dangerous works: spatial exploration, toxic device to operate...etc. It could also allow scientists to go where a human cannot: volcanoes, smart caves, mined areas...etc.
To help the user to accomplish such tasks, other users or an autonomous or teleautonomous robot could be used. Assistance robots complete human faculties and allow the system to take advantage over computer capacities to realize repetitive tasks, physically hard work, and to use at its best the expert dexterity to look, fall and react at the right time.
Graduation Project Report (March ‐ June 2008) submitted in the fulfillment of the requirements for the degree of Engineer on Computer Sciences
Promoter: Professor Yvan BAUDOIN Supervisor: Ir. Geert DE CUBBER
No comments:
Post a Comment