Analysis of human peg-in-hole executions in a robotic embodiment using uncertain grasps

In this paper, we perform a quantitative and qualitative analysis of human peg-in-hole operations in a tele-operating setting with a moderate degree of dexterity. Peg-in-hole operation with different starting configurations are performed with the aim to derive a strategy for performing such actions with a robot. The robot is a 6 DoF robot arm with the dexterous 3 finger SDH-2 gripper. From the extracted data, we can distill important insights about (1) feasible grasps depending on the peg's pose, (2) the object trajectory, (3) the occurrence of a particular force-torque pattern during the monitoring of the action and (4) an appropriate insertion strategy. At the end of the paper, we discuss consequences for using these insights for deriving algorithms for robot execution of peg-in-hole actions with dexterous manipulators.

[1]  Seung-kook Yun,et al.  Compliant manipulation for peg-in-hole: Is passive compliance a key to learn contact motion? , 2008, 2008 IEEE International Conference on Robotics and Automation.

[2]  Alin Albu-Schäffer,et al.  Programming by touch: the different way of human-robot interaction , 2003, IEEE Trans. Ind. Electron..

[3]  W. Marsden I and J , 2012 .

[4]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[5]  J. Wikander,et al.  Control design and stability analysis of a surgical teleoperator , 1999 .

[6]  Rüdiger Dillmann,et al.  Teaching and learning of robot tasks via observation of human performance , 2004, Robotics Auton. Syst..

[7]  Danica Kragic,et al.  Interactive grasp learning based on human demonstration , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[8]  K. Kleinmann,et al.  A modular approach for solving the peg-in-hole problem with a multifingered gripper , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[9]  Richard Alan Peters,et al.  Robonaut task learning through teleoperation , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[10]  Stefan Schaal,et al.  Robot Programming by Demonstration , 2009, Springer Handbook of Robotics.

[11]  Giovanni C. Pettinaro Behaviour-based peg-in-hole , 1999, Robotica.