# Using Synthetic Data and Deep Networks to Recognize Primitive Shapes for Object Grasping

arXiv: https://arxiv.org/abs/1909.08508 · HTML: https://mlsanity.com/paper/1909.08508/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [ShapeGrasp: Zero-Shot Task-Oriented Grasping with Large Language Models through Geometric Decomposition](https://mlsanity.com/paper/2403.18062/) (2024)
- [GKNet: grasp keypoint network for grasp candidates detection](https://mlsanity.com/paper/2106.08497/) (2021)
- [Grasp Pre-shape Selection by Synthetic Training: Eye-in-hand Shared Control on the Hannes Prosthesis](https://mlsanity.com/paper/2203.09812/) (2022)
- [AGILE: Approach-based Grasp Inference Learned from Element Decomposition](https://mlsanity.com/paper/2402.01303/) (2024)
- [Classification of Seeds using Domain Randomization on Self-Supervised Learning Frameworks](https://mlsanity.com/paper/2103.15578/) (2021)

## Abstract (arXiv)

A segmentation-based architecture is proposed to decompose objects into multiple primitive shapes from monocular depth input for robotic manipulation. The backbone deep network is trained on synthetic data with 6 classes of primitive shapes generated by a simulation engine. Each primitive shape is designed with parametrized grasp families, permitting the pipeline to identify multiple grasp candidates per shape primitive region. The grasps are priority ordered via proposed ranking algorithm, with the first feasible one chosen for execution. On task-free grasping of individual objects, the method achieves a 94% success rate. On task-oriented grasping, it achieves a 76% success rate. Overall, the method supports the hypothesis that shape primitives can support task-free and task-relevant grasp prediction.