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.

In the Deep Learning for Robotic Vision (DLRV) Workshop at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).