High-level programming and control for industrial robotics: using a hand-held accelerometer-based input device for gesture and posture recognition

Abstract

Purpose - Most industrial robots are still programmed using the typical teaching process, through the use of the robot teach pendant. This is a tedious and time-consuming task that requires some technical expertise, and hence new approaches to robot programming are required. The purpose of this paper is to present a robotic system that allows users to instruct and program a robot with a high-level of abstraction from the robot language. Design/methodology/approach - The paper presents in detail a robotic system that allows users, especially non-expert programmers, to instruct and program a robot just showing it what it should do, in an intuitive way. This is done using the two most natural human interfaces (gestures and speech), a force control system and several code generation techniques. Special attention will be given to the recognition of gestures, where the data extracted from a motion sensor (three-axis accelerometer) embedded in the Wii remote controller was used to capture human hand behaviours. Gestures dynamic hand positions) as well as manual postures (static hand positions) are recognized using a statistical approach and artificial neural networks. Findings - It is shown that the robotic system presented is suitable to enable users without programming expertise to rapidly create robot programs. The experimental tests showed that the developed system can be customized for different users and robotic platforms. Research limitations/implications - The propose