No abstract

Learning new knowledge from single instructions and being able to apply it immediately is highly desirable for artificial agents. We provide the first demonstration of spoken instruction-based one-shot object and action learning in a cognitive robotic architecture and briefly discuss the architectural modifications required to enable such fast learning, demonstrating the new capabilities on a fully autonomous robot.

Controlling remote robots is a difficult task for human computer interface (HCI). Control of remote robots enables accomplishment of tasks without the human controller physically present due to safety concerns or the expert cannot be physically present. This paper presents a method for using an Oculus Rift to improve HCI for telerobotic control. Using the Oculus, an operator could become immersed in the robot’s environment and could more naturally control the desired position of a remotely positioned vision system via head movements. To provide the appropriate visual feedback, a three-axis gimbal was implemented as a test platform. Through software implemented motion tracking, the response of the Oculus was compared to that of a mouse which demonstrates the efficiency of the proposed system over comparable HCI.

No abstract