Flexible assembly in space and industry: transfer project strengthens robot autonomy and teamwork with humans
Autonomous mobile robots that work safely and intuitively with humans are not only an important building block of Industry 4.0. In future space missions, they are expected to support infrastructure construction on foreign planets. In the recently completed transfer project TransFIT, the German Research Center for Artificial Intelligence (DFKI), the University of Bremen and Siemens AG developed the robotic skills required for the autonomous and collaborative execution of complex assembly work. The project was funded through the German Aerospace Center (DLR) by the Federal Ministry for Economic Affairs and Climate Action (BMWK).
To protect astronauts from hostile environmental conditions and to enable them to stay on alien celestial bodies for longer periods of time, it is essential to build up infrastructure. Autonomous mobile robots are predestined for this demanding work as they can take on tasks that are potentially dangerous or physically demanding for humans, both on their own and in robotic teams. However, the systems reach their limits where human intellect, dexterity, and creativity are required. At the end of the TransFIT project that launched in July 2017, the cooperation partners Robotics Innovation Center of the DFKI, Robotics Group of the University of Bremen and Siemens AG presented innovative technologies that not only strengthen the autonomous capabilities of the robots through artificial intelligence (AI) methods, but also enable the situationally appropriate and intuitive support by humans. In addition, the partners demonstrated the high transfer potential of the solutions by setting up a flexible assembly cell for industrial production. At the same time, a software framework specifically developed for autonomous production, which plans processes depending on system capabilities, was incorporated into the space scenario.
Prof. Dr. Dr. h.c. Frank Kirchner, head of the DFKI Robotics Innovation Center: „Future space missions will increasingly rely on artificial intelligence methods and the combination of human and robotic capabilities. With the completion of the TransFIT project, which is a significant part of the DFKI Space Roadmap, we have succeeded in laying important foundations for cooperative infrastructure development in space and in demonstrating the transferability of the developed technologies to the industrial context. In perspective, both sectors will benefit immensely from the use of autonomous robots that can work in teams with humans.“
Human-robot collaboration for infrastructure construction in space
During the extraterrestrial construction of stationary camps, shelters or facilities for resource extraction, robots must tackle tasks of varying complexity, which also requires collaboration with astronauts. TransFIT therefore focused on the implementation of a cooperation scenario in which a human and a humanoid robot jointly perform an assembly task. They are supported by another person who can control the robot with an exoskeleton from a greater distance, for example from the station in orbit or from the lander. The cooperation partners interact to varying degrees according to the concept of „sliding autonomy“, from complete autonomy to autonomy with „operator in the loop“ and teleoperation with partially autonomous functions to pure teleoperation. To realize this alternation between autonomous work, cooperation and teleoperation, the project partners developed an easy-to-use control software that allows rapid adaptability of the robot’s behavior on site and during the mission. This ensures that even unforeseen assembly tasks such as unplanned repairs can be carried out flexibly by the robot in cooperation with the astronaut instead of autonomously.
Learning assistant robot for complex assembly work and teleoperation
As a robotic test platform, DFKI researchers built the humanoid RH5 Manus, an assistance robot developed for use in a human environment that features a hybrid serial-parallel design. Due to its innovative adaptive grasping system equipped with tactile sensors, near-field recognition, and a local microcontroller for biologically inspired grasping reflexes, the robot can perform complex grasping movements. It can both grasp and hold components as well as directly cooperate with the astronaut thanks to machine learning methods for environment perception, such as object recognition and grasping pose determination. In addition, RH5 can be remotely controlled with an active exoskeleton developed at the Robotics Innovation Center and optimized for teleoperation. However, the collaboration does not solely aim at the division of tasks but also aims to enable the robot to learn from interaction with humans in order to act more and more autonomously and adapt to changing requirements. For example, in extraterrestrial missions, it must be considered that the system cannot always be repaired or not at all. For example, if the robot’s movement is restricted because one of its joints no longer functions properly, the technologies developed in TransFIT enable it to take this restriction into account and adapt its behavior accordingly.
Improved teamwork thanks to intuitive interaction possibilities
For the most intuitive human-robot collaboration possible, the interaction partners can communicate via speech using predefined commands. In addition, the robot can be controlled by simple gestures, which are recognized with the help of a sensor suit worn by the astronaut. The project partners are also using the human electroencephalogram (EEG) to improve interaction: First, they developed methods to determine the cognitive load of the interacting person from the brain data, which can be used to provide support as needed. Second, in the event of an incorrect action by the robot, a negative feedback signal can be obtained from the EEG, the so-called error potential. This enables the system to continuously improve its behavior and relieves the human, who does not have to consciously give the feedback to the robot.
Transfer of space technologies in the context of Industry 4.0
In addition to implementing the extraterrestrial cooperation scenario, TransFIT aimed to transfer the developed technologies to terrestrial applications, specifically to industrial manufacturing and production. Here, the increasing number of variants of the products to be manufactured and the ever-shorter product life cycles lead to ever smaller batch sizes. A factor, that makes the use of classic automation paradigms almost impossible, even in assembly, which is largely dependent on manual work. Thus, the project partners, under the leadership of Siemens AG, developed a highly flexible and cooperative assembly cell for the production of complex assemblies. The cell, which has two robotic arms, can implement abstract task specifications autonomously and in cooperation with a human worker. For this purpose, object recognition, grasp pose determination and intuitive human-machine interaction technologies were transferred from the space scenario to the industrial context. In addition, a skill-based framework developed specifically for autonomous production enables hierarchical modeling and orchestration of sequences in the manufacturing process based on semantic product descriptions and required system capabilities. This framework has again been successfully transferred to human-robot collaboration in space to assign the actions required for a task to the actors and to plan the sequence of actions.
TransFIT was funded from July 1st, 2017 to December 31st, 2021 via the German Aerospace Center (DLR) by the Federal Ministry for Economic Affairs and Climate Action (BMWK) with around 7.9 million euros.
DFKI Press Contact:
Corporate Communications Bremen
Phone: +49 421 178 45 4180
Dipl.-Inf. Michael Maurus
Project Manager TransFIT
Phone: 0421 178 45 4196
https://robotik.dfki-bremen.de/en/research/projects/transfit/ project website
https://cloud.dfki.de/owncloud/index.php/s/AqGEFwbWX5iyg2M Images are available for download in the DFKI Cloud. You are welcome to use these if you cite the source.