# Improving Data Efficiency of Self-supervised Learning for Robotic Grasping

arXiv: https://arxiv.org/abs/1903.00228 · HTML: https://mlsanity.com/paper/1903.00228/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

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

- [RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking](https://mlsanity.com/paper/2309.01918/) (2023)
- [Semantically Controllable Augmentations for Generalizable Robot Learning](https://mlsanity.com/paper/2409.00951/) (2024)
- [Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones](https://mlsanity.com/paper/2311.15033/) (2023)
- [Transferring Experience from Simulation to the Real World for Precise Pick-And-Place Tasks in Highly Cluttered Scenes](https://mlsanity.com/paper/2101.04781/) (2021)
- [Visionary: Vision architecture discovery for robot learning](https://mlsanity.com/paper/2103.14633/) (2021)
- [Good Grasps Only: A data engine for self-supervised fine-tuning of pose estimation using grasp poses for verification](https://mlsanity.com/paper/2409.11512/) (2024)

## Abstract (arXiv)

Given the task of learning robotic grasping solely based on a depth camera input and gripper force feedback, we derive a learning algorithm from an applied point of view to significantly reduce the amount of required training data. Major improvements in time and data efficiency are achieved by: Firstly, we exploit the geometric consistency between the undistorted depth images and the task space. Using a relative small, fully-convolutional neural network, we predict grasp and gripper parameters with great advantages in training as well as inference performance. Secondly, motivated by the small random grasp success rate of around 3%, the grasp space was explored in a systematic manner. The final system was learned with 23000 grasp attempts in around 60h, improving current solutions by an order of magnitude. For typical bin picking scenarios, we measured a grasp success rate of 96.6%. Further experiments showed that the system is able to generalize and transfer knowledge to novel objects and environments.