Workshop

Title:
Robotics in Future Manufacturing: Going from Individual Robots to Integrated Manufacturing Concepts

Abstract:
Industry 4.0 stays for a manufacturing concept which fully exploits the online digital interconnection between all participants in the manufacturing process, from supplier over CAD developer to the production work-floor, including product components and machines.
In this context it is expected that robots, which can directly exploit the digital data, will play an increasingly large role. However, automation alone still lacks flexibility in complex manufacturing processes such as the final assembly in automotive industries. Therefore, human-robot collaboration is currently an alternative of continuously increasing importance.
However, today we need to think manufacturing in an integrated way, from the customer interface for ordering personalized products, over planning and robotic logistics, fully automated, reconfigurable and interactive work-cells. In this context I will present the goals and current results of the DLR Factory of the Future project. Here, advanced mechatronics meets the newest AI developments.

Title:
Automated design of adaptable grasping and part feeding solutions for robot based industrial assembly.

Abstract:
Highly adaptable and flexible automation systems are more and more adopted in the modern manufacturing processes. In recent years there is a noticeable shift in the production domain from mass to low volume high customization production of products mainly found in small and medium enterprises. Therefore, specialized automation technologies have been developed, with focus on reconfigurability and high adaptability to cope with manufacturing demands. In this talk we will present an approach focusing on automated design of reconfigurable hardware solutions for object grasping and part feeding, which can be adopted to a variety of manufacturing situations where parts are introduced into the system unordered in bulk. Furthermore, we will focus on the aspect of intuitive robot programming for part feeding and assembly of industrial parts, based on human demonstration. Finally, we will discuss the integration and benchmarking of the mentioned approach carried out on an industrial reconfigurable platform designed to be used in several industrial projects running in the industry 4.0 laboratory at University of Southern Denmark.

Title:
Toward Knowledge-Based Digital Engineering

Abstract:
Classical robot programming for industrial robots requires an explicit specification of individual low-level commands in order to achieve a certain result. In this approach, the robot is not aware of the context and overarching goal, while executing its program. Service robots on the other hand are expected to perform complex tasks based only on a high-level instruction. Typically, these instructions are heavily under-specified and formulate a goal without explaining in detail how it can be achieved.
In order to transfer such goal-oriented task specifications to industrial manufacturing processes, it is necessary to formally model various types of knowledge in a way that enables processing by a technical system. Semantic description languages encode common sense knowledge and domain specific knowledge on products, industrial processes, and robot workcells. Based on the product specification and the derived process requirements in combination with the capabilities of the robot system, a solution can be generated automatically.
In this talk, I will present a knowledge-based approach to robot programming. It enables intuitive instruction of complex robot systems in a short time frame even for non-expert users. As a result, small lot production, common in small and medium-sized enterprises, becomes financially viable. In an extended digital engineering approach, in which all company data including product and production data is semantically annotated and linked, a fully automated generation of robot programs for a large number of product variations becomes feasible.

Title:
Intuitive robot programming from few demonstrations

Abstract:
A wide range of SMEs would benefit from the development of robots that can acquire manipulation skills by interaction with humans. Such interaction requires that the skills learned by the robots can be interpreted by the users. This transparency allows the users to dynamically assess if the taught tasks have been correctly understood, and provide new data in consequence (in the form of demonstrations or corrections).
Such iterative learning challenge requires the development of intuitive interfaces to acquire meaningful demonstrations, the development of movement representations that can exploit the structure and geometry of the acquired data in an efficient way, and the development of adaptive control techniques that can exploit the possible variations and coordinations in movements. The developed models need to serve several purposes (recognition, prediction, generation), and be compatible with different learning strategies (imitation, self-refinement). For the reproduction of skills, these models need to be enriched with force and impedance information to enable human-robot collaboration and to generate safe and natural movements. I will illustrate these challenges with manipulation skill learning examples targeting manufacturing environments.

Title:
Smart hardware and software integration for efficient setup and reconfiguration of robot workcells

Abstract:
We developed a reconfigurable robot workcell aimed at automating low-volume production. The distinguishing feature of our cell is the application of passive, reconfigurable hardware components and module exchange systems, supported by the underlying ROS-based modular control software. The deployment of new applications and workcell reconfiguration is facilitated by intuitive, user-friendly robot programming methods, which are tightly integrated with the provided reconfigurable hardware. The developed system was evealuated by implementing several use cases from different manufacturing industries.

Title:
How the Italian Academy responds to the Industry 4.0 challenge: the National Institute of Robotics and Intelligent Machines (I-RIM), and the Industrial Computer Engineering at the University of Verona.

Abstract:
In Italy, the need to support companies in their renovation process is being met with nation-wide and local initiatives. The national initiatives rely on the newly formed scientific association I-RIM that puts together all the research groups working on robotics and intelligent machines in Italy. The I-RIM association has its first event in Rome on October 18-20, which consisted on round tables on education, technology transfer and project presentations, together with a scientific conference and an exhibition of solutions for advanced manufacturing. At the local level, funded by the Ministry of Education and University, the University of Verona has developed a pilot research line to experiment with the complete software stack powering the Industry 4.0 development, from cloud application to embedded firmware. In this talk I will give a brief summary of the national and the local initiatives, emphasizing their technical aspects and the interest to develop scientific collaborations.