Picture for Peter I. Corke

Peter I. Corke

Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination

Add code
May 15, 2017
Fangyi Zhang, Jürgen Leitner, Michael Milford, Peter I. Corke
Figure 1 for Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination
Figure 2 for Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination
Figure 3 for Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination
Figure 4 for Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination

This paper introduces an end-to-end fine-tuning method to improve hand-eye coordination in modular deep visuo-motor policies (modular networks) where each module is trained independently. Benefiting from weighted losses, the fine-tuning method significantly improves the performance of the policies for a robotic planar reaching task.

* 2 pages, to appear in the Deep Learning for Robotic Vision (DLRV) Workshop in CVPR 2017 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon