# AGILE: Approach-based Grasp Inference Learned from Element Decomposition

arXiv: https://arxiv.org/abs/2402.01303 · HTML: https://mlsanity.com/paper/2402.01303/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Deep Learning for Detecting Robotic Grasps](https://mlsanity.com/paper/1301.3592/) (2013)
- [Real-Time Grasp Detection Using Convolutional Neural Networks](https://mlsanity.com/paper/1412.3128/) (2014)
- [Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image](https://mlsanity.com/paper/2004.01176/) (2020)
- [Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network](https://mlsanity.com/paper/1909.04810/) (2019)
- [End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB](https://mlsanity.com/paper/2107.05287/) (2021)
- [Physical Primitive Decomposition](https://mlsanity.com/paper/1809.05070/) (2018)
- [A Single Multi-Task Deep Neural Network with Post-Processing for Object Detection with Reasoning and Robotic Grasp Detection](https://mlsanity.com/paper/1909.07050/) (2019)
- [Exploiting Kinematic Redundancy for Robotic Grasping of Multiple Objects](https://mlsanity.com/paper/2303.01868/) (2023)
- [Using Synthetic Data and Deep Networks to Recognize Primitive Shapes for Object Grasping](https://mlsanity.com/paper/1909.08508/) (2019)
- [Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering](https://mlsanity.com/paper/2306.07392/) (2023)
- [Hybrid Robotic Grasping with a Soft Multimodal Gripper and a Deep Multistage Learning Scheme](https://mlsanity.com/paper/2202.12796/) (2022)
- [MetaGraspNet_v0: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis](https://mlsanity.com/paper/2112.14663/) (2021)
- [U-Net-based Models for Skin Lesion Segmentation: More Attention and Augmentation](https://mlsanity.com/paper/2210.16399/) (2022)

## Built on by (most cited first, 2 of 2)

- [Scene Understanding in Pick-and-Place Tasks: Analyzing Transformations Between Initial and Final Scenes](https://mlsanity.com/paper/2409.17720/) (2024)
- [AI-Driven Relocation Tracking in Dynamic Kitchen Environments](https://mlsanity.com/paper/2503.01547/) (2025)

## Abstract (arXiv)

Humans, this species expert in grasp detection, can grasp objects by taking into account hand-object positioning information. This work proposes a method to enable a robot manipulator to learn the same, grasping objects in the most optimal way according to how the gripper has approached the object. Built on deep learning, the proposed method consists of two main stages. In order to generalize the network on unseen objects, the proposed Approach-based Grasping Inference involves an element decomposition stage to split an object into its main parts, each with one or more annotated grasps for a particular approach of the gripper. Subsequently, a grasp detection network utilizes the decomposed elements by Mask R-CNN and the information on the approach of the gripper in order to detect the element the gripper has approached and the most optimal grasp. In order to train the networks, the study introduces a robotic grasping dataset collected in the Coppeliasim simulation environment. The dataset involves 10 different objects with annotated element decomposition masks and grasp rectangles. The proposed method acquires a 90% grasp success rate on seen objects and 78% on unseen objects in the Coppeliasim simulation environment. Lastly, simulation-to-reality domain adaptation is performed by applying transformations on the training set collected in simulation and augmenting the dataset, which results in a 70% physical grasp success performance using a Delta parallel robot and a 2 -fingered gripper.