Seite - 31 - in Proceedings of the OAGM&ARW Joint Workshop - Vision, Automation and Robotics

Fig. 6. Scheme of the Quality Inspection Unit Data Readout unit that takes synchronization and calibration information from the control system to generate inspection sensor data aligned in 3D to the specimen to be produced. The main part of the QIU is the Inspection Software that is fed with inspection criteria and quality thresholds and a defect catalog. The software decides upon defects and failures and reports those back to the production process. For fulfilling all these tasks the QIU provides a set of functionalities. First of all, it captures the clamps once clamped, using a dedicated visual 2D/3D sensor. Afterwards, it generates a 3D representation, a so called Digital Terrain Model (DTM), of the specimen surface. This DTM is then be analyzed with respect to segments that significantly exceed the ordinary surface plane of the specimen. Optionally a-priori informa- tion about the position of applied clamps can be used, to minimize the search space. In any case, the segments that indicate defects, are detected in this step. For such segments the responsible MES is beeing notified about the erroneous clamp, its position and optionally the amount and/or type of defect. Fig. 7. Sample Images of not fully applied Clamps. Infigure7asampleofnot fullyappliedclampsasdetected by the QIU is shown. In the color coded image (right) the red segments represent undefined areas, which can be caused by an occlusion from a staple fully applied to generate a small ditch, or from an occlusion caused by a staple not fully applied. Dark blue areas are portions with higher elevation, hence not fully applied staples being detected as production errors . Light green means measured ditches. The measurement direction is from above. VI. CONCLUSIONS This paper contains an outline of the RobWood approach. We have described how we could design components which could be used for the company to program the robot with less effort. This is an important issue for workers without profound programming skills. A first, a series of tests of the particular components of the tool chain took place in a gradual manner at the Holzinnovationszentrum [1]. At the end, an integration test with all the components passed successfully. To sum up, we believe that our approach can be integrated in the production for the wood industry in the next three to five years. REFERENCES [1] Holzinnovationszentrum gmbh. [Online]. Available: http://www.hiz.at [2] Proholz austria. [Online]. Available: http://www.proholz.at [3] T. Dietz, U. Schneider, M. Barho, S. Oberer-Treitz, M. Drust, R. Holl- mann, and M. Haegele, “Programming system for efficient use of industrial robots for deburring in sme environments,” in ROBOTIK 2012; 7th German Conference on Robotics, May 2012, pp. 1–6. [4] M. Fowler, Domain-specific languages. Pearson Education, 2010. [5] A. Goldenberg, B. Benhabib, and R. Fenton, “A complete generalized solution to the inversekinematicsof robots,” IEEEJournalonRobotics and Automation, vol. 1, no. 1, pp. 14–20, 1985. [6] J. O. Huckaby and H. I. Christensen, “A taxonomic framework for task modeling and knowledge transfer in manufacturing robotics,” in Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012. [7] P. Neto, J. N. Pires, and A. P. Moreira, “Cad-based off-line robot programming,” in 2010 IEEE Conference on Robotics, Automation and Mechatronics, June 2010, pp. 516–521. [8] A. Nordmann, N. Hochgeschwender, D. L. Wigand, and S. Wrede, “A survey on domain-specific modeling and languages in robotics,” Journal of Software Engineering in Robotics, vol. 7, no. 1, 2016. [9] Z. Pan, J. Polden, N. Larkin, S. V. Duin, and J. Norrish, “Recent progress on programming methods for industrial robots,” Robotics and Computer-Integrated Manufacturing, vol. 28, no. 2, pp. 87 – 94, 2012. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0736584511001001 [10] R. P. Paul and B. Shimano, “Kinematic control equations for simple manipulators,” in 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes, Jan 1978, pp. 1398–1406. [11] L. Richardson and S. Ruby, RESTful web services. ” O’Reilly Media, Inc.”, 2008. [12] C. Schlegel, T. Hassler, A. Lotz, and A. Steck, “Robotic software systems: From code-driven to model-driven designs,” in 2009 Inter- national Conference on Advanced Robotics, June 2009, pp. 1–8. [13] M. Spangenberg and D. Henrich, “Towards an intuitive interface for instructing robots handling tasks based on verbalized physical effects,” in The 23rd IEEE International Symposium on Robot and Human Interactive Communication, Aug 2014, pp. 79–84. [14] U.Thomas,G.Hirzinger,B.Rumpe,C.Schulze, andA.Wortmann,“A new skill based robot programming language using uml/p statecharts,” in 2013 IEEE International Conference on Robotics and Automation, May 2013, pp. 461–466. [15] H. Zeiner, M. Goller, V. J. Expo´sito Jime´nez, F. Salmhofer, and W. Haas, “Secos: Web of things platform based on a microservices architecture and support of time-awareness,” e & i Elektrotechnik und Informationstechnik, vol. 133, no. 3, pp. 158–162, 2016. [Online]. Available: http://dx.doi.org/10.1007/s00502-016-0404-z 31