Novel Interaction Strategies for Learning from Teleoperation

27 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

ROBOTURK: A Crowdsourcing Platform for Robotic Skill Learning through Imitation (2018, background): “…supervision can be provided through contemporary game interfaces such as a keyboard and mouse [26, 27], a video game controller [28], a 3D-mouse [29, 30], special purpose master-slave interfaces[31, 32], or through free-space positioning interfaces such as virtual reality (VR) [33, 34, 35].”
Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations (2016, methodology): “ expressiveness can change relative performance of RC and HC. LfD Interfaces: Standard techniques for providing demonstrations to a robot are teleoperation, kinesthetic and waypoint speciﬁcation [2], [3], [4]. Kinesthetic teaching is deﬁned as moving the robot body via a human exerting force on the ”
Using dVRK teleoperation to facilitate deep learning of automation tasks for an industrial robot (2017, background): “Due to the high cost and complexity of early systems, recent research in LfD has considered low-DOF input devices such as the Phantom Omni [11] and the Xbox controller [7], which can limit the ability of the operator to simultaneously control multiple degrees of freedom at once [1], and devices…”