Scoring Graspability based on Grasp Regression for Better Grasp Prediction

Amaury Depierre (1, 2) , Emmanuel Dellandréa (1) , Liming Chen (1)

1 imagine - Extraction de Caractéristiques et Identification
2 Siléane [Saint-Etienne]

Grasping objects is one of the most important abilities that a robot needs to master in order to interact with its environment. Current state-of-the-art methods rely on deep neural networks trained to jointly predict a graspability score together with a regression of an offset with respect to grasp reference parameters. However, these two predictions are performed independently, which can lead to a decrease in the actual graspability score when applying the predicted offset. Therefore, in this paper, we extend a state-of-the-art neural network with a scorer that evaluates the graspability of a given position, and introduce a novel loss function which correlates regression of grasp parameters with graspability score. We show that this novel architecture improves performance from 82.13% for a state-of-the-art grasp detection network to 85.74% on Jacquard dataset. When the learned model is transferred onto a real robot, the proposed method correlating graspability and grasp regression achieves a 92.4% rate compared to 88.1% for the baseline trained without the correlation.

Domaines: Intelligence artificielle [cs.AI]; Robotique [cs.RO]

Amaury Depierre, Emmanuel Dellandréa, Liming Chen. Scoring Graspability based on Grasp Regression for Better Grasp Prediction. IEEE International Conference on Robotics and Automation (ICRA), May 2021, Xi'an (China), China. ⟨10.1109/ICRA48506.2021.9561198⟩. ⟨hal-02456956v3⟩