Neurocognitive Shared Visuomotor Network for End-to-end Learning of Object Identification, Localization and Grasping on a Humanoid

2019 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), pages 19--24, doi: 10.1109/DEVLRN.2019.8850679 - Aug 2019
Associated documents :  
We present a unified visuomotor neural architecture for the robotic task of identifying, localizing, and grasping a goal object in a cluttered scene. The RetinaNet-based neural architecture enables end-to-end training of visuomotor abilities in a biological-inspired developmental approach. We demonstrate a successful development and evaluation of the method on a humanoid robot platform. The proposed architecture outperforms previous work on single object grasping as well as a modular architecture for object picking. An analysis of grasp errors suggests similarities to infant grasp learning: While the end-to-end architecture successfully learns grasp configurations, sometimes object confusions occur: when multiple objects are presented, salient objects are picked instead of the intended object.

 

@InProceedings{KEHAW19, 
 	 author =  {Kerzel, Matthias and Eppe, Manfred and Heinrich, Stefan and Abawi, Fares and Wermter, Stefan},  
 	 title = {Neurocognitive Shared Visuomotor Network for End-to-end Learning of Object Identification, Localization and Grasping on a Humanoid}, 
 	 booktitle = {2019 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {19--24},
 	 year = {2019},
 	 month = {Aug},
 	 publisher = {IEEE},
 	 doi = {10.1109/DEVLRN.2019.8850679}, 
 }