Page - 146 - in Proceedings - OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“

accept or reject robotic assistance (e.g. [2]). Similarly, little is known about best practices of user- centered development in the industrial context [3] [4]. Up to now, robot-based assistive systems are not widely spread in the manufacturing industry, as there is still research missing to uncover their full potential, and room for improvement in terms of usability, user experience, and subsequently user acceptance. Assigned purpose of the project AssistMe is the user-centered development and evaluation of innovative means of interaction for human-robot cooperation to improve usability and user experience of robot-based assistive systems in order to flexibly automatize selected production steps in an economically viable way. The aim of the AssistMe project is to develop innovative haptic and optic concepts for human-robot cooperation in two different applications contexts, namely the assembly of automotive combustion engines while the other one treats the machining (polishing) of casting moulds. These concepts can be used during set up and interaction with a robot-based assistive system. The project consists of three major development cycles. In a first iteration an assistive robot system, more or less out of the box is implemented for the use cases by application of process equipment. User studies regarding teaching and use of the systems are carried out. User-centred improvements in terms of usability and programmability are implemented as technical components in order to reduce programming complexity and programming duration as well as to improve system reliability and process quality. Therefore different technology options are foreseen by the project frame. Force feedback technology will support programming and the usage of robot programs in order to make better use of robot articulated machining tools supporting the navigation through the real world by position-based haptic force feedback. Optic interaction technology, 2D and 3D sensors (and the corresponding machine vision algorithms) integrated with projection devices will render spatial augmented interaction e.g. textual feedback – instructions and explanations, during use. Apart from visualization, spatial augmented reality concepts with position and object-based projected information will be developed in order to be able to define virtual light barriers and projected buttons. Tools will be automatically positioned relative to objects (due to object pose recognition technology). In combination with haptic interaction technology interaction concepts will be evaluated that prevent users from the violation of 3D collision contours that have been captured and automatically interpreted as such by optical reconstruction technology beforehand. These interaction paradigms will be developed in a multi- stage process, together with operators in the two different testbeds and subsequently they will be evaluated in different expansion stages of the interaction technologies. 2. User-centered Design Approach The two-years project is based on the concept of iteratively evaluating the same robotic assistance in different stages of expansions for the two different use cases. Stage 1 is an off-the-shelf robotic arm from Universal Robotics . Stage 2 will be further enhanced with a 3D sensor and Stage 3 with force feedback. Every stage of expansion will be evaluated together with representative target users from our industrial partners with respect to usability, user experience, and acceptance. After every evaluation implications for improvement for the next expansion stage will be derived to keep the operators’ point of view in the development process. The AssistMe project thereby follows a very similar user-centered design approach as presented in [3] and the evaluation activities are methodologically grounded in the USUS evaluation framework [5]. The work presented in this paper are the general use cases for both application contexts, as well as the first expansion stage and its evaluation. Before we go on detail with our use case implementation, we will give a short overview on related state-of-the-art assistive robot systems. 146