Page - 85 - in Proceedings of the OAGM&ARW Joint Workshop - Vision, Automation and Robotics

While it is essential to have a direct link from the safety- oriented sensor fusion to the robot control for adapting speed limitations or triggering an emergency stop, the combined information from the sensors also serves as a valuable input for generating task-level plans for the robot system. We use ROSPlan [2] as our infrastructure for task planning, which allows us to formulate the planning domain in the quasi- standard Planning Domain Definition Language (PDDL) [5]. The planner, given abstract logical models of the system and relevant entities in its surroundings on the one hand and goals to be achieved on the other, would typically generate sequences of actions such as picking up a certain object, placing it ina certain pose into the product that is being built, and fixing it there in a certain manner, using a certain path of motion trajectories from a set of possible ones. There could also be actions representing interaction with humans via user interface components or invoking arbitrary meaningful functionalities of connected devices. The currently obtained safety zone information and other results of sensor fusion can be mapped to logical facts in the planning domain, and they in turn can be used in the conditions of PDDL actions in order to tie their applicability to the current safety situation. Examples for such conditional safety limitations include forbidding certain actions as a whole, forbidding trajectories in which parts of the robot would intrude certain zones or exceed a certain speed limit, forbidding interacting with potentially hazardous objects, or forcing the robot to assume a predefined home pose between any two other poses. The planning system takes care that such restrictions are not only considered when a new plan is generated but also that the current plan’s execution is halted when an assumed precondition, safety-related or other, for a robot action is found to be not actually fulfilled, or when an action’s execution was not successful. Then, starting from the updated current state, a new plan is generated and goes into effect. VI. CONCLUSION In this paper, we have emphasized the importance of a safe perception system in HRI scenarios where both human and robot coexist in a shared environment and collaborate toward their goals. We have taken into account a holistic approach toward safe perception and managed to introduce the requirements for a general architecture that integrates safety in any robotic environment independent of scenario, scale, shape, and the number of robots and humans. This ar- chitecture is modular, reproducible, context aware, intelligent and also has parallel redundancy, heterogeneous sensors, and embedded safety. Furthermore we have presented how our safe perception is set up for a collaboration scenario in our lab to demonstrate the simplicity and reusability of our approach in real-world applications. In this demonstration multiple safety standards have been considered and included in order to have a correct risk analysis and safety-zone calculation. REFERENCES [1] B. Breiling, B. Dieber, and P. Schartner, “Secure communication for the robot operating systems,” inProceedings of the 11thAnnual IEEE International Systems Conference, 2017, to appear. [2] M. Cashmore, M. Fox, D. Long, D. Magazzeni, B. Ridder, A. Carrera, N. Palomeras, N. Hurto´s, and M. Carreras, “Rosplan: Planning in the robot operating system,” in Proceedings of the Twenty-Fifth International Conference on Automated Planning and Scheduling, ICAPS 2015, Jerusalem, Israel, June 7-11, 2015., 2015, pp. 333–341. [Online]. Available: http://www.aaai.org/ocs/index.php/ICAPS/ICAPS15/paper/view/10619 [3] B. Dieber, S. Kacianka, S. Rass, and P. Schartner, “Application-level security for ros-based applications,” in 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct 2016, pp. 4477–4482. [4] M. Faber, J. Bu¨tzler, and C. M. Schlick, “Human- robot cooperation in future production systems: Analysis of requirements for designing an ergonomic work system,” Procedia Manufacturing, vol. 3, pp. 510 – 517, 2015. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S2351978915002164 [5] M. Fox and D. Long, “PDDL2.1: an extension to PDDL for expressing temporal planning domains,” J. Artif. Intell. Res. (JAIR), vol. 20, pp. 61–124, 2003. [Online]. Available: http://dx.doi.org/10.1613/jair.1129 [6] M. Giuliani, C. Lenz, T. Mu¨ller, M. Rickert, and A. Knoll, “Design principles for safety in human-robot interaction,” International Journal of Social Robotics, vol. 2, no. 3, pp. 253–274, 2010. [Online]. Available: http://dx.doi.org/10.1007/s12369-010-0052-0 [7] M. Huber, H. Radrich, C. Wendt, M. Rickert, A. Knoll, T. Brandt, and S. Glasauer, “Evaluation of a novel biologically inspired trajectory generator in human-robot interaction,” in Proceedings of the IEEE International SymposiumonRobot andHuman InteractiveCommuni- cation, Toyama, Japan, 2009, pp. 639–644. [8] ISO, ISO13849-1:2006: Safety ofmachinery – Safety-related parts of control systems – Part 1: General principles for design. Geneva, Switzerland: International Organization for Standardization, Nov. 2006. [9] ISO, ISO 12100:2010: Safety of machinery – General principles for design – Risk assessment and risk reduction. Geneva, Switzerland: International Organization for Standardization, 2010. [10] ISO, ISO 10218-1:2011: Robots and robotic devices - Safety require- ments for industrial robots - Part 1: Robots. Geneva, Switzerland: International Organization for Standardization, July 2011. [11] ISO, ISO 10218-2:2011: Robots and robotic devices - Safety require- ments for industrial robots - Part 2: Robot systems and integration. Geneva, Switzerland: International Organization for Standardization, July 2011. [12] ISO, ISO/TS 15066:2016:Robots and robotic devices –Collaborative robots. Geneva, Switzerland: International Organization for Standard- ization, Feb. 2016. [13] D. Kulic´, “Safety for human-robot interaction,” Ph.D. dissertation, University of British Columbia, 2006. [14] P. A. Lasota, G. F. Rossano, and J. A. Shah, “Toward safe close- proximity human-robot interaction with standard industrial robots.” in CASE. IEEE, 2014, pp. 339–344. [15] J. McClean, C. Stull, C. Farrar, and D. Mascareas, “A preliminary cyber-physical security assessment of the robot operating system (ros),” in Proc. SPIE, vol. 8741, 2013, pp. 874110–874110–8. [Online]. Available: http://dx.doi.org/10.1117/12.2016189 [16] G. Michalos, S. Makris, P. Tsarouchi, T. Guasch, D. Kontovrakis, and G. Chryssolouris, “Design considerations for safe human-robot collaborative workplaces,”Procedia {CIRP}, vol. 37, pp. 248 – 253, 2015. [17] M. Quigley, K. Conley, B. P. Gerkey, J. Faust, T. Foote, J. Leibs, R. Wheeler, and A. Y. Ng, “ROS: an open-source Robot Operating System,” in ICRAWorkshop onOpen Source Software, 2009. [18] P. E. Rybski, P. Anderson-Sprecher, D. Huber, C. Niessl, and R. G. Simmons, “Sensor fusion for human safety in industrial workcells,” in 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2012, Vilamoura, Algarve, Portugal, October 7-12, 2012, 2012, pp. 3612–3619. [Online]. Available: http://dx.doi.org/10.1109/IROS.2012.6386034 [19] B. Schmidt and L. Wang, “Contact-less and programming-less human- robot collaboration,”Procedia {CIRP}, vol. 7, pp. 545 – 550, 2013. [20] M. Vasic and A. Billard, “Safety issues in human-robot interactions.” in ICRA. IEEE, 2013, pp. 197–204. 85