SMErobotics

Integrating Cognitive Aspects into Robot Systems for SMEs

Project Description

The state of the art in production using industrial robots is mainly concentrated on large scale production facilities. Small and medium-sized enterprises (SMEs) are mostly reluctant to consider automation using robots. Unlike large scale industries, SMEs have small slot size and constantly changing product cycles. These facts make the use of typical industrial robot work cells difficult since, they are not easy to program and require skilled technicians for operation. Furthermore, SME shop floors are less structured as compared to their counterparts in large industrial settings, making robot deployment even more challenging.

The goal of the SMErobotics project is to bring industrial robots to SME production lines. For this purpose, the project aims towards developing a robot system which supports intuitive programming and can easily adapt to changing product cycles. Most importantly, this robot system should be able to cooperate with an average skilled human worker. Special attention will be given to the system error recovery by means of assistance from the human worker, robot system or both.

Contributions

From this project, the SMEs will immensely benefit in the form of continuous improvement in throughput,  human working standards and production quality. Moreover, with such a flexible robot system, they could easily adapt to their changing product cycles while still maintaining quality standards, without the need of expert knowledge. This results in reduced installation and operation costs.

During the course of this project, systems in the area of artificial Intelligence will be researched and developed. This will be a contribution to the state of the art in symbiotic interaction and mutual learning.

In the SMErobotics project, fortiss will be responsible to deliver system modules for multi-modal sensor fusion/fission, perception, reasoning and planning. This task will be achieved by using, extending and implementing state of the art tools/techniques of artificial intelligence (reasoning/planning) on standard industrial robots. These modules will be integrated together with modules for process models, task execution under uncertainties, and robot control, which will be developed by our project partners.

Partners

Fraunhofer-Institut für Produktionstechnik und Automatisierung

COMAU Robotics S.p.A.

Deutsches Zentrum für Luft- und Raumfahrt e.V.

Danish Technological Institute

GPS Gesellschaft für Produktionssysteme GmbH

Güdel AG

KUKA Laboratories GmbH

Reis GmbH & Co. KG Maschinenfabrik

Lund University

Funding

This research project receives funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement n° 287787.

PUBLICATIONS

Export list as BibTeX file

  • Alexander Perzylo, Nikhil Somani, Stefan Profanter, Ingmar Kessler, Markus Rickert and Alois Knoll. Intuitive Instruction of Industrial Robots: Semantic Process Descriptions for Small Lot Production. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2293–2300, Daejeon, Republic of Korea, 2016. Details DOI BibTeX
  • Mathias Haage, Stefan Profanter, Ingmar Kessler, Alexander Perzylo, Nikhil Somani, Olof Sörnmo, Martin Karlsson, Sven Gestegård Robertz, Klas Nilsson, Ludovic Resch and Michael Marti. On Cognitive Robot Woodworking in SMErobotics. In Proceedings of the International Symposium on Robotics (ISR), Munich, Germany, 2016. Details BibTeX
  • Markus Rickert and Alexander Perzylo. Industrieroboter für KMU: Flexible und intuitive Prozessbeschreibung. Industrie Management, 32(2):46–49, 2016. Details BibTeX
  • Nikhil Somani, Alexander Perzylo, Caixia Cai, Markus Rickert and Alois Knoll. Object Detection Using Boundary Representations of Primitive Shapes. In Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO), pages 108–113, Zhuhai, China, 2015. Details DOI BibTeX
  • Alina Roitberg, Nikhil Somani, Alexander Perzylo, Markus Rickert and Alois Knoll. Multimodal Human Activity Recognition for Industrial Manufacturing Processes in Robotic Workcells. In Proceedings of the ACM International Conference on Multimodal Interaction (ICMI), pages 259–266, Seattle, WA, USA, 2015. Details DOI BibTeX
  • Alexander Perzylo, Nikhil Somani, Stefan Profanter, Andre Gaschler, Sascha Griffiths, Markus Rickert and Alois Knoll. Ubiquitous Semantics: Representing and Exploiting Knowledge, Geometry, and Language for Cognitive Robot Systems. In Proceedings of the Workshop Towards Intelligent Social Robots - Current Advances in Cognitive Robotics, IEEE/RAS International Conference on Humanoid Robots (HUMANOIDS), Seoul, South Korea, 2015. Details BibTeX
  • Alexander Perzylo, Nikhil Somani, Markus Rickert and Alois Knoll. An Ontology for CAD Data and Geometric Constraints as a Link Between Product Models and Semantic Robot Task Descriptions. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 4197–4203, Hamburg, Germany, 2015. Details DOI BibTeX
  • Stefan Profanter, Alexander Perzylo, Nikhil Somani, Markus Rickert and Alois Knoll. Analysis and Semantic Modeling of Modality Preferences in Industrial Human-Robot Interaction. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1812–1818, Hamburg, Germany, 2015. Details DOI BibTeX
  • Alexander Perzylo, Nikhil Somani, Stefan Profanter, Markus Rickert and Alois Knoll. Multimodal Binding of Parameters for Task-Based Robot Programming Based on Semantic Descriptions of Modalities and Parameter Types. In Proceedings of the Workshop on Multimodal Semantics for Robotic Systems, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, 2015. Details BibTeX
  • Alexander Perzylo, Nikhil Somani, Stefan Profanter, Markus Rickert and Alois Knoll. Toward Efficient Robot Teach-In and Semantic Process Descriptions for Small Lot Sizes. In Proceedings of the Workshop on Combining AI Reasoning and Cognitive Science with Robotics, Robotics: Science and Systems (RSS), Rome, Italy, 2015. Details BibTeX
  • Andre Gaschler, Ingmar Kessler, Ronald P. A. Petrick and Alois Knoll. Extending the Knowledge of Volumes Approach to Robot Task Planning with Efficient Geometric Predicates. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2015. Details DOI BibTeX
  • Alexander Perzylo, Sascha Griffiths, Reinhard Lafrenz and Alois Knoll. Generating Grammars for Natural Language Understanding from Knowledge about Actions and Objects. In Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO), Zhuhai, China, 2015. Details DOI BibTeX
  • Andre Gaschler, Quirin Fischer and Alois Knoll. The Bounding Mesh Algorithm. TUM-I1522, Technische Universität München, Munich, Germany, 2015. Details BibTeX
  • Sören Jentzsch, Andre Gaschler, Oussama Khatib and Alois Knoll. MOPL: A Multi-Modal Path Planner for Generic Manipulation Tasks. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, 2015. Details DOI BibTeX
  • Alina Roitberg, Alexander Perzylo, Nikhil Somani, Manuel Giuliani, Markus Rickert and Alois Knoll. Human Activity Recognition in the Context of Industrial Human-Robot Interaction. In Proceedings of the AsiaPacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pages 1–10, Siem Reap, Cambodia, 2014. Details DOI BibTeX
  • Nikhil Somani, Caixia Cai, Alexander Perzylo, Markus Rickert and Alois Knoll. Object Recognition Using Constraints from Primitive Shape Matching. In Proceedings of the 10th International Symposium on Visual Computing (ISVC'14), pages 783–792, Las Vegas, NV, USA, 2014. Springer. Details DOI BibTeX
  • Andre Gaschler, Maximilian Springer, Markus Rickert and Alois Knoll. Intuitive Robot Tasks with Augmented Reality and Virtual Obstacles. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages 6026–6031, Hong Kong, China, 2014. Details DOI BibTeX
  • Nikhil Somani, Emmanuel Dean-Leon, Caixia Cai and Alois Knoll. Scene Perception and Recognition for Human-Robot Co-Operation. In ICIAP'13 workshop: First International Workshop on Assistive Computer Vision and Robotics (ACVR 2013). The 17th International Conference on Image Analysis and Processing., 2013. Details BibTeX
  • Nikhil Somani, Emmanuel Dean-Leon, Caixia Cai and Alois Knoll. Perception and Reasoning for Scene Understanding in Human-Robot Interaction Scenarios. In CAIP'13 workshop: Recognition and Action for Scene understanding (REACTS 2013). The 15th International Conference of Computer Analysis of Images and Patterns., 2013. Details BibTeX
  • Nikhil Somani, Emmanuel Dean-Leon, Caixia Cai and Alois Knoll. Scene Perception and Recognition in Industrial Environments for Human-Robot Interaction. In 9th International Symposium on Visual Computing (ISVC'13), 2013. Springer. Details BibTeX