End-to-end Multi-Instance Robotic Reaching from Monocular Vision
Zheyu Zhuang,Xin Yu,Robert Mahony,Zheyu Zhuang,Xin Yu,Robert Mahony
Multi-instance scenes are especially challenging for end-to-end visuomotor (image-to-control) learning algorithms. "Pipeline" visual servo control algorithms use separate detection, selection and servo stages, allowing algorithms to focus on a single object instance during servo control. End-to-end systems do not have separate detection and selection stages and need to address the visual ambiguiti...
