Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Session Chair: Maurizio Valle, University of Genova
Soft robotic structures by smart encapsulation of electronic devices
A. Winkler1, A. Ehrenhofer2, T. Wallmersperger2, M. Gude1, N. Modler1
1Technische Universität Dresden, Institute of Lightweight Engineering and Polymer Technology, Germany; 2Technische Universität Dresden, Institute of Solid Mechanics, Germany
Due to the digitalization and advanced automation of industrial processes, the interaction of robotic systems with humans is a very important issue. Soft robotics are therefore becoming increasingly important, as soft interfaces could prevent dangerous injuries to people. The current paper presents a concept for a soft robotic system that focusses on an organ-like encapsulation in robotic systems and allows the utilization of rigid parts in the context of soft robotics.
The current contribution shows initial investigations about the concept of encapsulated batteries to mimic mitochondria: In biological cells, there are types of organelles that provide the power to the other organs/organelles. In the proposed soft robot, multiple batteries/accumulators are individually encapsulated in poly(N-isopropylacrylamide) (PNiPAAm) hydrogel to perform this task. Due to the thermo-responsivity of the PNiPAAm gel, a swelling or a deswelling of the active encapsulation is obtained by changing the local temperature. In the current work, we apply the Temperature-Expansion-Model to represent this active behavior. Numerical simulations by applying the Finite Element method are performed in order to show the features of the investigated system.
The paper presents investigations for the design and simulation of tailored active material encapsulations that can be intrinsically activated from inside the organism. Thus, a robot is obtained that – due to its softness – can be used in interaction with humans. At the same time, it can react to inner stimuli (global decisions from microcontrollers) or outer stimuli (local influences from the environment) to adapt its properties to occurring challenges.
Near Sensors Computation based on Embedded Machine Learning for Electronic Skin
A. Ibrahim1,2, H. Younes1,2, M. Alameh1, M. Valle1
1University of Genova, Italy; 2Lebanese International University, Lebanon
The electronic skin system is usually made of distributed tactile sensors integrated with an embedded electronic system for tactile data decoding. Meaningful information e.g. texture classification and pattern recognition can be decoded from tactile data by employing machine learning methods. Near sensors computation using embedded machine learning algorithms may enable the electronic skin system to be used in various application domains such as wearable Internet of Things devices, prosthetics, and robotics. However, embedding machine-learning algorithms is constrained by the high computational complexity of Machine Learning methods. This poses relevant challenges on 1) real-time operation and 2) very low (e.g. pJ/op) power/energy consumption due to the limited energy budget available on wearable/portable systems. In this perspective, the paper presents our recent achievements in the implementation of embedded machine learning methods for near sensors tactile data processing. The paper provides an overview about the implementation on dedicated hardware platforms. Finally, efficient techniques for embedded machine learning highlighting the challenges and perspectives are discussed with major emphasis on energy-efficient intelligent electronic skin systems.
Influence of Elastomeric Tensioned Members on the Characteristics of Compliant Tensegrity Structures in Soft Robotic Applications
J. Chavez Vega1,2, P. Schorr1,2, T. Kaufhold1, K. Zimmermann1, L. Zentner1, V. Böhm2
1TU Ilmenau, Germany; 2OTH Regensburg, Germany
The use of mechanically prestressed compliant structures in soft robotics is a recently discussed topic. Tensegrity structures, consisting of a set of rigid disconnected compressed members connected to a continuous net of prestressed elastic tensioned members build one specific class of these structures. Robots based on these structures have manifold shape changing abilities and can adapt their mechanical properties reversibly by changing of their prestress state according to specific tasks. In the paper selected aspects on the potential use of elastomer materials in these structures are discussed with the help of theoretical analysis.
Quality optimization of mechanical joining processes by the use of human-robot collaboration
F. Schmatz1, F. Beuß1, J. Sender1, W. Flügge2
1Fraunhofer Institute for Large Structures in Production Engineering IGP, Albert-Einstein-Str. 30,18059 Rostock, Germany; 2University of Rostock, Faculty of Mechanical Engineering and Marine Technology, Chair of Manufacturing Engineering, Albert-Einstein-Str. 2, 18059 Rostock, Germany
This paper presents a new form of setting process monitoring for mechanical joining implemented into a human-robot collaboration. The used lightweight robot can be manipulated in an intuitive way. We developed an easy to use hand guiding opportunity for cobots from Universal Robots by providing an URCap. This way such a cobot can be manipulated quickly and precisely with ease by any operator new to the system within minutes. It enables an economic use of hand guiding with an additional hand guiding device. With this device the teach pendant is not needed during the regular operations which simplifies the usage of the cobot. The integrated sensors (primarily a force-torque sensor) collect data, which gives information about the setting process. Several errors (e.g. no rivet head support, angle offset, gap between the sheets) were carried out on a test setup while recording the data for evaluation. The resulting force/torque-time graphs give indication of the occurring error. As a result the classified error can be immediately displayed to the operator for recognizing the need for reworking. In combination with an error avoidance algorithm the overall quality of the product can be sustainably improved.
Design of Human Robot Collaboration workstations – Two automotive case studies
D. Andronas, A. Argyrou, K. Fourtakas, P. Paraskevopoulos, S. Makris
Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, Patras 26500, Greece
Human Robot Collaboration assembly cells benefit the capabilities and skills of both industrial robots and humans, although fenceless coexistence leads to issues related to safety and human-system interaction. A series of methods for hybrid workstation design focusing on safe yet efficient Human Robot Collaboration is presented, where various layout configurations are illustrated and evaluated aiming industrial implementation. Two distinct automotive use cases, with different requirements and challenges, are used as reference for highlighting particularities on lightweight and high-payload robots, in addition to small and large size product assemblies.