# Learning suction graspability considering grasp quality and robot reachability for bin-picking

arXiv: https://arxiv.org/abs/2111.02571 · HTML: https://mlsanity.com/paper/2111.02571/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 73 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 29 of 29)

- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [TossingBot: Learning to Throw Arbitrary Objects with Residual Physics](https://mlsanity.com/paper/1903.11239/) (2019)
- [Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning](https://mlsanity.com/paper/1803.09956/) (2018)
- [Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching](https://mlsanity.com/paper/1710.01330/) (2017)
- [ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation](https://mlsanity.com/paper/1910.02550/) (2019)
- [Deep Learning for Detecting Robotic Grasps](https://mlsanity.com/paper/1301.3592/) (2013)
- [Jacquard: A Large Scale Dataset for Robotic Grasp Detection](https://mlsanity.com/paper/1803.11469/) (2018)
- [6-DOF Grasping for Target-driven Object Manipulation in Clutter](https://mlsanity.com/paper/1912.03628/) (2019)
- [Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network](https://mlsanity.com/paper/1909.04810/) (2019)
- [SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python](https://mlsanity.com/paper/1907.10121/) (2019)
- [Robotic Grasp Detection using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1611.08036/) (2016)
- [SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping](https://mlsanity.com/paper/2103.12311/) (2021)
- [ROI-based Robotic Grasp Detection for Object Overlapping Scenes](https://mlsanity.com/paper/1808.10313/) (2018)
- [A Billion Ways to Grasp: An Evaluation of Grasp Sampling Schemes on a Dense, Physics-based Grasp Data Set](https://mlsanity.com/paper/1912.05604/) (2019)
- [Fully Convolutional Grasp Detection Network with Oriented Anchor Box](https://mlsanity.com/paper/1803.02209/) (2018)
- [Dynamic Grasping with Reachability and Motion Awareness](https://mlsanity.com/paper/2103.10562/) (2021)
- [Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter](https://mlsanity.com/paper/1809.08564/) (2018)
- [A New Approach to Time-Optimal Path Parameterization based on Reachability Analysis](https://mlsanity.com/paper/1707.07239/) (2017)
- [Reuleaux: Robot Base Placement by Reachability Analysis](https://mlsanity.com/paper/1710.01328/) (2017)
- [Collision-Aware Target-Driven Object Grasping in Constrained Environments](https://mlsanity.com/paper/2104.00776/) (2021)
- [GKNet: grasp keypoint network for grasp candidates detection](https://mlsanity.com/paper/2106.08497/) (2021)
- [Learning to Generate 6-DoF Grasp Poses with Reachability Awareness](https://mlsanity.com/paper/1910.06404/) (2019)
- [DefGraspSim: Simulation-based grasping of 3D deformable objects](https://mlsanity.com/paper/2107.05778/) (2021)
- [Workspace Aware Online Grasp Planning](https://mlsanity.com/paper/1806.11402/) (2018)
- [Minimal Work: A Grasp Quality Metric for Deformable Hollow Objects](https://mlsanity.com/paper/1909.11226/) (2019)
- [GI-NNet & RGI-NNet: Development of Robotic Grasp Pose Models, Trainable with Large as well as Limited Labelled Training Datasets, under supervised and semi supervised paradigms](https://mlsanity.com/paper/2107.07452/) (2021)
- [Deformation-Aware Data-Driven Grasp Synthesis](https://mlsanity.com/paper/2109.05320/) (2021)

## Built on by (most cited first, 5 of 5)

- [Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmark](https://mlsanity.com/paper/2305.16378/) (2023)
- [Model-free Grasping with Multi-Suction Cup Grippers for Robotic Bin Picking](https://mlsanity.com/paper/2307.16488/) (2023)
- [OptiGrasp: Optimized Grasp Pose Detection Using RGB Images for Warehouse Picking Robots](https://mlsanity.com/paper/2409.19494/) (2024)
- [Diffusion Suction Grasping with Large-Scale Parcel Dataset](https://mlsanity.com/paper/2502.07238/) (2025)
- [Sim-MEES: Modular End-Effector System Grasping Dataset for Mobile Manipulators in Cluttered Environments](https://mlsanity.com/paper/2305.10580/) (2023)

## Abstract (arXiv)

Deep learning has been widely used for inferring robust grasps. Although human-labeled RGB-D datasets were initially used to learn grasp configurations, preparation of this kind of large dataset is expensive. To address this problem, images were generated by a physical simulator, and a physically inspired model (e.g., a contact model between a suction vacuum cup and object) was used as a grasp quality evaluation metric to annotate the synthesized images. However, this kind of contact model is complicated and requires parameter identification by experiments to ensure real world performance. In addition, previous studies have not considered manipulator reachability such as when a grasp configuration with high grasp quality is unable to reach the target due to collisions or the physical limitations of the robot. In this study, we propose an intuitive geometric analytic-based grasp quality evaluation metric. We further incorporate a reachability evaluation metric. We annotate the pixel-wise grasp quality and reachability by the proposed evaluation metric on synthesized images in a simulator to train an auto-encoder--decoder called suction graspability U-Net++ (SG-U-Net++). Experiment results show that our intuitive grasp quality evaluation metric is competitive with a physically-inspired metric. Learning the reachability helps to reduce motion planning computation time by removing obviously unreachable candidates. The system achieves an overall picking speed of 560 PPH (pieces per hour).