Depth-sensor – projector safety model for human-robot collaboration

We propose a depth sensor and projector based safety model for human-robot collaboration in a compact shared workspace. The model consists of three spatial zones, robot zone, danger zone and human zone. The zones are online modelled, updated and monitored using a single depth sensor and user notification and interaction is provided by a projectormirror display. Our model includes methods for detection of safety zone violations (an obstacle enters the danger zone) and prevents the robot to move to “unverified” (changed) workspace regions. Unverified regions are verified by user interaction. In the experimental part, we define an assembly task with the standard Cranfield benchmark parts where our proposed model reduces robot idle time by 43% and achieves 12.4% average reduction in task completion time as compared to a baseline.

[1]  Christoph Walter,et al.  Safeguarding and Supporting Future Human-robot Cooperative Manufacturing Processes by a Projection- and Camera-based Technology , 2017 .

[2]  Marko Pfeifer,et al.  A new strategy for ensuring human safety during various levels of interaction with industrial robots , 2017 .

[3]  Carlos Morato,et al.  Toward Safe Human Robot Collaboration by Using Multiple Kinects Based Real-Time Human Tracking , 2014, J. Comput. Inf. Sci. Eng..

[4]  Christoph Walter,et al.  A projection-based sensor system for safe physical human-robot collaboration , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Luigi Villani,et al.  A Conformable Force/Tactile Skin for Physical Human–Robot Interaction , 2016, IEEE Robotics and Automation Letters.

[6]  Lihui Wang,et al.  Active collision avoidance for human–robot collaboration driven by vision sensors , 2017, Int. J. Comput. Integr. Manuf..

[7]  Alessandro De Luca,et al.  Integrated control for pHRI: Collision avoidance, detection, reaction and collaboration , 2012, 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[8]  Jack Sklansky,et al.  Finding the convex hull of a simple polygon , 1982, Pattern Recognit. Lett..

[9]  Mohamad Bdiwi.  Integrated Sensors System for Human Safety during Cooperating with Industrial Robots for Handing-over and Assembling Tasks , 2014 .

[10]  Joni-Kristian Kämäräinen,et al.  Projector Calibration by "Inverse Camera Calibration" , 2011, SCIA.

[11]  Alessandro De Luca,et al.  Collision detection and reaction: A contribution to safe physical Human-Robot Interaction , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Lihui Wang,et al.  Research Letters Vision-guided active collision avoidance for human-robot collaborations , 2013 .

[13]  Christoph Walter,et al.  Towards safe physical human-robot collaboration: A projection-based safety system , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Matteo Saveriano,et al.  Distance based dynamical system modulation for reactive avoidance of moving obstacles , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Thomas Timm Andersen.  Optimizing the Universal Robots ROS driver. , 2015 .