Factory of the Future
How to digitalize the robot-aided manufacturing process in Industry 4.0?

Friday, Nov. 8th

Robotics is one of the great technological revolutions of our century, with fundamental implications for a wide range of different industries.

Full-Day Workshop at IROS 2019 in Macau

Friday, Nov. 8th

Industrial mass production is no longer conceivable without robotics and automation. The trend in modern manufacturing is towards individualized products, tailored to the customer, with an exploding variety of variants and much shorter product life-cycles. This, in order to satisfy the market demand of a flexible and customizable industrial production. In this context, the classic way of conceiving industrial automation, which is mainly focused on purely automated or manual forms of production, is clearly reaching its limits.

Nowadays, robots and autonomous systems, partly in direct human-robot cooperation, are moving into the production of smaller batch sizes and can thus create a decisive competitive advantage in all industries. This flexibilisation also includes opportunities to optimize energy and material flows for resource-efficient production.

In our view, a modern manufactory or Factory of the Future needs a broad range of digital production technologies, robot systems, and applications for flexible and networked manufacturing processes effectively integrated in different production scenarios. One focus is on the realization of robust robot-supported manufacturing processes using digitization approaches and industry 4.0. This will make factory applications in particular more efficient, more cost-effective, safer, and more resource-conserving. More in details, a competitive Factory of the Future has to pursue the following objectives:

… of new digital production chains from the digital model to the automatically assembled product. In doing so, resource and energy consumption as well as costs are reduced despite flexibilisation and human personnel are relieved. In this context, digital mapping, the so-called “Digital Twin”, can be used during the entire production cycle of a component, e.g. for preliminary design, design support, virtual commissioning, or optimization of production processes and plants.

… of versatile digital production concepts through mobile robotic systems and networked, intelligent production and assembly robots. For assembly, inspection, maintenance and disposal of products and large structures, the use of mobile manipulators and large robot arms in big production lines seems a promising solution until the “futuristic” use of humanoid robots will become a concrete option.

… collaboration between humans and robots as well as between humans and machines in general in the cognitive production plant of the future. Robotic systems and industry 4.0 concepts have a proven broad impact on general industrial robotics. Lightweight robots are currently undergoing a fundamental change towards human-robot cooperation and sensitive manipulation in automotive manufacturing, production in SMEs, and in surgery. In addition to fully automated solutions, modern manufacturies increasingly relying on advanced assistance systems to support people in order to be able to act highly flexibly and efficiently.

… with high quality standards through efficient material flow, advanced assembly capabilities, and self-reconfigurable machineries and workcells.

The objectives of the Factory of the Future are ambitious and therefore challenging to pursue. The enormous technical challenges need the bundling and closely interlinking of expertise in different fields related to robotics and autonomous systems, like robotic assistance, perception, sensor technology, control, and AI. Only with the joint effort of such expertise, holistic answers to the questions of production and assistance of the future will be possible. This workshop aims at presenting and discussing current research results in the broad field of robot-aided manufacturing, directing the way towards novel innovations and open issues. Some of the questions we will try to answer are:

  • Which level of integration digital solutions have in current in industrial scenarios?
  • Which is the role of intuitive robot programming and human-robot collaboration in flexible manufacturing?
  • Which is the role of mobile and dexterous manipulation in smart factories?
  • Are reconfigurable workcells ready to use in mass production?

In one sentence, our workshop will discuss what has been done and what we need to do to realize the Factory of the Future.


Intuitive robot programming
Reconfigurable workcells
Interfaces for intuitive human-robot collaboration
Learning for flexible manufacturing
Navigation and mobile manipulation in industry
Digital twins and augmented reality
Sensors and actuators for adavanced autonomous assembly

We welcome researchers in the field to submit papers to be presented as posters. Submitted manuscripts should be between 2 and 4 pages, formatted according to IROS standards using the Paper Template downloadable on the IEEE IROS 2019 website (two-column format). Submission of videos accompanying the papers is always encouraged.

Video submissions are also welcomed.

For video submissions, we require a video no longer than 3 minutes formatted according to IROS standards and an extended abstract (1 to 2 pages using IROS 2019 Paper Template) describing the results in the video. Authors of accepted papers will present their work during the poster sessions.


Please submit your contributions via e-mail to Matteo Saveriano and Roman Weitschat before September 15. Papers and videos will be selected based on their originality, relevance to the workshop topics, contributions, technical clarity, and presentation. Accepted papers and videos require that at least one of the authors register to the workshop. Accepted papers and videos will not appear in the conference proceedings.

Important dates
  • Submission deadline for papers and videos: 15 September, 2019
  • Notification of acceptance: 01 October, 2019

Program & Schedule


09:00 Opening Organizers
09:10 Alin Albu-Schäffer DLR and TUM confirmed
09:50 George G.Q. Huang The University of Hong Kong confirmed
10:30 Poster session and coffee break
11:00 Aljaz Kramberger University of Southern Denmark confirmed
11:40 Francesco Ferro PAL Robotics confirmed
12:20 Aleš Ude Jožef Stefan Institute confirmed
13:00 Lunch break
14:00 Sylvain Calinon IDIAP confirmed
14:40 Paolo Fiorini University of Verona confirmed
15:20 Poster session and coffee break
16:00 Markus Rickert FORTISS confirmed
16:40 Manolo Garabini Universitiy of Pisa confirmed
17:20 End



Alin Albu-Schäffer
German Aerospace Center (DLR) and Technical University of Munich, Germany

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

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.

George G.Q. Huang
The University of Hong Kong, China
Aljaz Kramberger
University of Southern Denmark, Denmark

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

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.

Francesco Ferro
PAL Robotics
Markus Rickert
FORTISS, Germany

Toward Knowledge-Based Digital Engineering

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.

Sylvain Calinon
Idiap Research Institute and EPFL, Switzerland

Intuitive robot programming from few demonstrations

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.

Aleš Ude
Jožef Stefan Institute, Slovenia

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

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.

Paolo Fiorini
University of Verona

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.

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.

Manolo Garabini
University of Pisa
matteo 1-36
Matteo Saveriano, Ph.D.
Post-Doctoral Researcher / Contact Person

Universität Innsbruck
Innrain 52, 6020 Innsbruck, Austria

Roman Weitschat, Ph.D.
Post-Doctoral Researcher

Institute of Robotics and Mechatronics
German Aerospace Center (DLR)
Münchener Straße 20, 82234, Weßling, Germany