Improving ability of tele‐operators to complete progressively more difficult mobile robot paths using simple expert systems and ultrasonic sensors

Abstract

Purpose-The purpose of this paper is to describe the use of simple expert systems to improve the performance of tele-operated mobile robots and ultrasonic sensor systems. The expert systems interpret data from the joystick and sensors and identify potentially hazardous situations and then recommend safe courses of action so that tele-operated mobile-robot tasks can be completed more quickly. Design/methodology/approach-The speed of a tele-operator in completing progressively more complicated driving tasks is investigated while using a simple expert system. Tele-operators were timed completing a series of tasks using a joystick to control a mobile robot through a simple expert system that assisted them with driving the robot while using ultrasonic sensors to avoid obstacles. They either watched the robot while operating it or sat at a computer and viewed scenes remotely on a screen from a camera mounted on the robot. Tele-operators completed tests with the simple expert system and the sensors connected. The system used an umbilical cable to connect to the robot. Findings-The simple expert systems consistently performed faster than the other systems. Results are compared with the most recently published results and show a significant improvement. In addition, in simple environments, tele-operators performed better without a sensor system to assist them but in more complicated environments than tele-operators performed better with the sensor systems to assist. Research limitations/implications-Simple expert systems are shown to improve the operation of a tele-operated mobile robot with an obstacle avoidance systems fitted. Practical implications-Tele-operated systems rely heavily on visual feedback and experienced operators. This paper investigates how to make tasks easier. Simple expert systems are shown to improve the operation of a tele-operated mobile robot. The paper also suggests that the amount of sensor support should be varied depending on circumstances. Originality/value-The simple expert systems are shown in this paper to improve the operation of a tele-operated mobile robot. Tele-operators completed tests with the simple expert system and the sensors connected. The results are compared with a tele-operator driving a mobile robot without any assistance from the expert systems or sensors and they show a significant improvement.

Improving automatic robotic welding in shipbuilding through the introduction of a corner-finding algorithm to help recognise shipbuilding parts

“…The many different methods of implementing AI each have their own strengths and weaknesses [9][10][11][12][13][14]. Some effort has been made in combining different methods to produce hybrid techniques with more strengths and fewer weaknesses.…”

Fast Transformations to Provide Simple Geometric Models of Moving Objects

“…The method is being successfully used with sensors [15,16] mobile robots [17,18,19,20,21] and wheelchairs [22,23].…”

A Rule-Based Expert System to Decide on Direction and Speed of a Powered Wheelchair

“…Many different sensors can be used to assist a powered wheelchair user to safely avoid obstacles [18]: infrared [21]; ultrasonic [20] or laser or structured light [19]. Global systems are tricky to use inside a building [22] but local sensors have been used such as: gyroscopes, odometers, tilt sensors and ultrasonics [23], [24].…”