Learning robust, real-time, reactive robotic grasping

By Douglas Morrison, Peter Corke, Jürgen Leitner. Int. J. Robotics Res., 2019

474 citations recorded by the source corpus.

We present a novel approach to perform object-independent grasp synthesis from depth images via deep neural networks. Our generative grasping convolutional neural network (GG-CNN) predicts a pixel-wise grasp quality that can be deployed in closed-loop grasping scenarios. GG-CNN overcomes shortcomings in existing techniques, namely discrete sampling of grasp candidates and long computation times. The network is orders of magnitude smaller than other state-of-the-art approaches while achieving better performance, particularly in clutter. We run a suite of real-world tests, during which we achieve an 84% grasp success rate on a set of previously unseen objects with adversarial geometry and 94% on household items. The lightweight nature enables closed-loop control of up to 50 Hz, with which we observed 88% grasp success on a set of household objects that are moved during the grasp attempt. We further propose a method combining our GG-CNN with a multi-view approach, which improves overall grasp success rate in clutter by 10%. Code is provided at https://github.com/dougsm/ggcnn

Subfields: Biomedical Engineering, Control and Systems Engineering, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/870de810dd0f9763b08e97bccb59e6fea70a8519

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Haoshu Fang
2. Chenxi Wang
3. Shirin Joshi
4. Cewu Lu
5. Ferat Sahin
6. Sulabh Kumra
7. Minghao Gou

In Control and Systems Engineering

1. Shirin Joshi
2. Ferat Sahin
3. Haoshu Fang
4. Chenxi Wang
5. Cewu Lu
6. Sulabh Kumra
7. Minghao Gou

In Human-Computer Interaction

1. Cewu Lu
2. Shirin Joshi
3. Ferat Sahin
4. Haoshu Fang
5. Chenxi Wang
6. Sulabh Kumra
7. Minghao Gou

Citations in the corpus

• Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network (2019, background): “[20] suggests that it reduces existing shortcomings of discrete sampling and computational complexity.”
• AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains (2022, methodology): “For dynamic grasping without prior, existing methods either choose the nearest grasp pose in the next image as the same grasp target [25] or generate possible future candidates and evaluate their grasp quality [38].”