Improved GQ-CNN: Deep Learning Model for Planning Robust Grasps
This work addresses the challenge of robust grasp planning for robots, but it is incremental as it builds upon an existing method with specific accuracy improvements.
The paper tackles the problem of improving grasp success rates for unknown objects in robot grasping by enhancing the Grasp Quality Convolutional Neural Network (GQ-CNN), resulting in increased validation accuracy from 92.2% to 95.8% on image-wise splits and from 85.9% to 88.0% on object-wise splits.
Recent developments in the field of robot grasping have shown great improvements in the grasp success rates when dealing with unknown objects. In this work we improve on one of the most promising approaches, the Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2.0 dataset. We propose a new architecture for the GQ-CNN and describe practical improvements that increase the model validation accuracy from 92.2% to 95.8% and from 85.9% to 88.0% on respectively image-wise and object-wise training and validation splits.