Scoring Graspability based on Grasp Regression for Better Grasp Prediction
This work addresses the challenge of improving grasp prediction accuracy for robots, which is incremental but important for enhancing robotic manipulation in real-world environments.
The paper tackles the problem of robotic grasp prediction by introducing a novel loss function that correlates graspability scoring with grasp regression, improving performance from 82.13% to 85.74% on the Jacquard dataset and achieving a 92.4% success rate on a real robot compared to 88.1% for the baseline.
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.