Options
2018
Poster
Titel
Enhanced robot control based on mental states:Toward full-trust interaction between humans and industrial robots
Titel Supplements
Poster presented at IEEE/RSJ International Conference on Intelligent Robots and Systems, 01.-05.10.2018, Madrid
Abstract
Industrial robots are widespread in today's production facilities. However, strict safety regulations are required to their operation. The robots therefore usually work spatially separated from humans. Only special designs- such as lightweight robots - can currently cooperate directly with humans and actively support them. The using of lightweight robots is nowadays limited in particular assistance tasks. However, the increasing demand for individualized products causes an increasing number of variants and thus increasing demands on flexible production. In the long run, the necessity of certain cooperation especially with heavy-duty robots arises, in which human and robot can exploit their advantages. Another obstacle is the anxiety of humans during the interaction with heavy-duty robots. The robot is a fully dynamic machine that can move in all directions. Furthermore, by implementing intelligent and autonomous robots, human could misinterpret the movements of the robot and act in the heat of the movement. These unforeseen movements could endanger the human. The focus of this project is to analyze the human reaction when a heavy-duty industrial robot is e.g. performing unexpected movements at high speeds (scenario 1), performing an unexpected task autonomously (scenario 2), or changing its motion routine autonomously (scenario 3). The reaction of humans, such as reflex movements, facial expressions, heart frequency and mental states will be measured online and the robot will build a reaction according to the mental states of the human. The main stones of this project are: - Conception and designing of real experimental field for measuring the mental states of humans during interaction with industrial robots. - Development of objective /subjective evaluation methodology for measuring and evaluating the mental states in real time. - Development of a flexible software platform for multi-sensor fusion: heart frequency, skin resistance, reflex motion, facial expressions, gestures etc. - Development of enhanced robot control combined with an interactive user interface in order to improve human confidence in robots. - Development of communication systems to arise full-trust interaction between human and industrial robots. The project consortium is rounded off by Adam OPEL AG as user. OPEL provides two real use cases in automobile sector.