Usability Study of Learning-Based Pose Estimation of Industrial Objects from Synthetic Depth Data

For visual assistance systems deployed in an industrial setting, precise object pose estimation is an important task in order to support scene understanding and to enable subsequent grasping and manipulation. Industrial environments are especially challenging since mesh-models are usually available while physical objects are not or are expensive to model. Manufactured objects are often similar in appearance, have limited to no textural cues and exhibit symmetries. Thus, these are especially challenging for recognizers that are meant to provide detection, classification and pose estimation on instance level. A usability study of a recent synthetically trained learning-based recognizer for these particular challenges is conducted. Experiments are performed on the challenging T-LESS dataset due to its relevance for industry.

Automated Information Supply of Worker Guidance Systems in Smart Assembly Environment

The global megatrends of digitization and individualization substantially affect manufacturing enterprises. Assembly workers are exposed to increased process complexity resulting in physical and cognitive workload. Worker guidance systems (WGS) are used to overcome this challenge through output of information regarding what should be done, how it should be done and why it should be done. An unsolved scientific challenge in this context is efficient information supply of WGS. Information such as worker’s instruction texts, pictures or 3D representations are created by employees of the work preparation department and transferred to the WGS. Manual information supply is a time-consuming and complex process, which requires a high (non-value-adding) effort as well as comprehensive knowledge in handling 3D CAD modelling and software programming. This paper presents a novel approach to reduce the required manual effort in information supply process. A knowledge-based model is proposed that enables an automated information supply of WGS in smart assembly environment by means of algorithms and self-learning expert systems, which pursues a holistic and consistent approach without media breaks. The automated approach assists employees of work preparation department, which means they can concentrate on their essential core competencies instead of being busy, for example, creating assembly plans, instruction texts or pictures for individual WGS. Finally, the technical implementation as a software-based proof-of-concept demonstrator and sub-sequent integration into the IT environment of TU Wien Pilot Factory Industry 4.0 is outlined.

Orchestration and Situation Awareness in an Assistance System for Assembly Tasks

We report on the design, specification and implementation of a situation awareness module used for assistive systems in manufacturing, in the context of Industry 4.0. A recent survey of research done in Germany and Europe, concerning assistive technology in industry shows a very high potential for “intelligent assistance” by combining smart sensors, networking and AI. While the state of the art concerning actual technology in industrial use points more towards user-friendly, speech-based interaction with personal assistants for information retrieval (typically of in-house documentation), the research presented here addresses an enterprise-level assistance system that is supported by a number of specialized Assistance Units that can be customized to the end users’ specifications and that range from tutoring systems to tele-robotics. Key to the approach is situation awareness, which is achieved through a combination of a-priori, task knowledge modelling and dynamic situation assessment on the basis of observation streams coming from sensors, cameras and microphones. The paper describes a working fragment of the industrial task description language and its extensions to cover also the triggering of assistive interventions when the observation modules have sent data that warrants such interventions.

Towards the Automated Coverlay Assembly in FPCB Manufacturing: Concept and Preliminary Tests

In modern electronics, flexible and rigid-flex PCBs are largely used due to their intrinsic versatility and performance, allowing to increase the available volume, or enabling connection between unconstrained components. Rigid-flex PCBs consists of rigid board portions with flexible interconnections and are commonly used in a wide variety of industrial applications. However, the assembly process of these devices still has some bottlenecks. Specifically, they require the application of cover layers (namely, coverlays), to provide insulation and protection of the flexible circuits. Due to the variability in planar shape and dimensions, the coverlay application is still performed manually, requiring troublesome manipulation steps and resulting in undetermined time-cycle and precision.This paper aims at the improvement of the industrial process currently performed, by proposing an approach for the automation of Kapton coverlay manipulation and application. Since these products are commercially provided as a film with a protective layer to be removed, the peeling issue is addressed, representing a challenging step of the automated process; the results of a systematic series of tests, performed in order to validate the peeling strategy, are reported in the paper. The overall assembly strategy relies on the development of a customized multi-hole vacuum gripper, whose concept is presented and contextualized in the proposed assembly process by outlining a suitable workcell architecture.

Augmented Reality in Assembly Systems: State of the Art and Future Perspectives

Assembly represents a fundamental step in manufacturing, being a time-consuming and costly process, on which the final quality of the product mostly depends. Augmented Reality (AR) may represent a key tool to assist workers during assembly, thanks to the possibility to provide the user of real-time instructions and information superimposed on the work environment. Many implementations have been developed by industries and academic institutions for both manual and collaborative assembly. Among the most remarkable examples of the last few years are applications in guidance of complex tasks, training of personnel, quality control and inspection. This keynote paper aims to provide a useful survey by reviewing recent applications of AR in assembly systems, describing potential advantages, as well as current limitations and future perspectives.

Investigation on the Convergence of the Genetic Algorithm of an Aerodynamic Feeding System Due to the Enlargement of the Solution Space

To meet the demands for flexible assembly technology, an aerodynamic feeding system has been developed. The system autonomously finds the optimal configuration of four parameters – two angles of inclination, nozzle pressure and component speed – using a genetic algorithm, which has been presented in earlier work. To increase the flexibility of the feeding system, an actuator was implemented, that enables the variation of the nozzle position orthogonally to the moving direction of the components. This paper investigates the effects of the more flexible flow against the components on their behavior when passing the nozzle. Additionally, the nozzle position was implemented into the genetic algorithm as a fifth parameter. Therefore, the impact of the enlargement of the solution space of the genetic algorithm due to the implementation of a fifth parameter is investigated in this paper as well.

Cognitive Assistance to Support Maintenance and Assembly Tasks: Results on Technology Acceptance of a Head-Mounted Device

This paper presents a study investigating the user acceptance (i.e. the perceived ease of use, willingness to use the system over time, and perceived usefulness) of a smart head-mounted device that can be used as assistive technology for maintenance and assembly. In particular, we focus on the head-mounted display named HMT-1 from RealWear. The uniqueness of this technology is, among other things, that it offers the possibility to fold away the display with the instructions, allowing more control over the appearance of assistive content than in other head-mounted displays. Overall, 48 participants took part in this interview study. They mentioned some advantages (e.g., that the hands are free and that one can see the instructions while working on something else at the same time) and disadvantages of the technology (such as usability issues). They also suggested that the technology is suitable for non-routine tasks and tasks of medium-to-high complexity. Our findings highlight that a cognitive assistive technology is perceived as positive when direct assistance is available (in the visual field of the worker) with a possibility to control the system.

The Consideration of Job Satisfaction in the Design of Assistance Systems in Production

Assistance systems designed to help workers in their jobs are increasingly used in industry. Technological progress makes these systems more powerful and extensive, but often nobody questions the extent to which they actually support the users and do not patronize them. For the development of such systems, we found the requirement analysis to be rather complex because human factors and social constraints are more difficult to determine than technical requirements. To counteract these difficulties, we pursue in our approach the involvement of people as knowledge carriers in the development of new technologies. In this paper we outline our framework how human factors aspects of acceptance and job satisfaction can be taken into account in the conception and design of assistance systems.

Digital Innovation Hubs for Enhancing the Technology Transfer and Digital Transformation of the European Manufacturing Industry

The European manufacturers are dealing with shorter product life-cycles and smaller batch sizes. Especially, the high-value products tend to be fully personalised, which makes the automatisation of the production difficult. However, the trend is that the production needs to be predictable and fully traceable to the process and even to the tool level. This adds pressure to have better data collection methods and also to increase of automation in different levels of production. The emergence of new technologies in the field of robotics allows the utilisation of automation in flexible manner. Within all areas of robotics, the demand for collaborative systems is rising as well. The level of desired collaboration and increased flexibility will only be reached if the systems are developed as whole e.g. perception, reasoning and physical manipulation. However, at the same time there is concerns on how to attract capable personnel to the factories. In order to fully implement and utilise the new robotics technologies the industry needs capable resources. For answering these needs there has been several attempts to build different types of industrial ecosystems to facilitate better the technology and knowledge transfer, and share of expertise. The main aim of the paper is to review recent actions regarding the robotics projects forming industrial ecosystems in the Horizon 2020 framework programme, and then introduce the TRINITY Digital Innovation Hub (DIH) project approach to form an industrial ecosystem in the field of robotics.

Development of a Sensitive Winding Application Based on a Serial Robot and Integrated Torque Sensors

Conventional winding technologies have already been implemented in the electrical and manufacturing industries. However, the adoption of such technology remains a challenge in the rubber industry, as sensitivity perception is required. A solution to this problem can be achieved by making use of robots equipped with additional sensors. Sensitive robotic applications require accurate force/torque data acquisition. The integration of accurate force/torque sensors is unsatisfactory, moreover a novel method for the processing of the measured data is a requisite. In this paper, a concept for the development of a sensitive winding application based on a serial sensitive robot is presented.