Collision-Detection for RoboCup@Work-Competitions

The RobotCup@Work league is motivated by industrial scenarios where objects has to be automatically transported between different working positions. During these operations the rules prohibit and penalize collisions of robots with the arena. Human referees distributed around the arena are responsible for identifying occurred collisions and for their annotation. If a robot moves parts of the arena, a collision is obvious. But, a slight contact is hard to recognize, since not all referees do have a permanent line of sight to the robot and distraction, caused by the surrounding, fatigue, or personal perception are human factors that might affect the outcome of a run. A majority vote might smooth the results, but it is an unsatisfactory solution in debatable situations.

[1]  Heinz Wörn,et al.  Development of a flexible tactile sensor system for a humanoid robot , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[2]  Jae-Bok Song,et al.  Collision detection and reaction on 7 DOF service robot arm using residual observer , 2012 .

[3]  Tao Zhang,et al.  Unsupervised learning to detect loops using deep neural networks for visual SLAM system , 2017, Auton. Robots.

[4]  Tim Niemüller,et al.  Knowledge-Based Instrumentation and Control for Competitive Industry-Inspired Robotic Domains , 2016, KI - Künstliche Intelligenz.

[5]  Mehmet Akar,et al.  RoboCup Small-Size League: Past, Present and Future , 2014, RoboCup.

[6]  Manuela M. Veloso,et al.  Event-based automated refereeing for robot soccer , 2017, Auton. Robots.

[7]  Omid Amir Ghiasvand,et al.  Ground-truth localisation system for humanoid soccer robots using RGB-D camera , 2017, Int. J. Comput. Vis. Robotics.

[8]  Luis Sentis,et al.  Full-body collision detection and reaction with omnidirectional mobile platforms: a step towards safe human–robot interaction , 2015, Autonomous Robots.

[9]  Jae-Bok Song,et al.  Collision detection algorithm robust to model uncertainty , 2013 .

[10]  André Dias,et al.  Real-Time Visual Ground-Truth System for Indoor Robotic Applications , 2013, IbPRIA.

[11]  Roger Feltman,et al.  The influence of red on perceptions of relative dominance and threat in a competitive context. , 2011, Journal of sport & exercise psychology.

[12]  Frederik Hegger,et al.  RoboCup@Work: Competing for the Factory of the Future , 2014, RoboCup.