Deep Correspondence Learning for Effective Robotic Teleoperation using Virtual Reality
2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)(2019)
摘要
By projecting into a 3-D workspace, robotic teleoperation using virtual reality allows for a more intuitive method of control for the operator than using a 2-D view from the robot's visual sensors. This paper investigates a setup that places the teleoperator in a virtual representation of the robot's environment and develops a deep learning based architecture modeling the correspondence between the operator's movements in the virtual space and joint angles for a humanoid robot using data collected from a series of demonstrations. We evaluate the correspondence model's performance in a pick-and - place teleoperation experiment.
更多查看译文
关键词
robotic teleoperation,virtual reality,virtual representation,deep learning based architecture,virtual space,humanoid robot,correspondence model,deep correspondence learning,robot visual sensors,3-D workspace,pick-and-place teleoperation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络