# Real-Time, Highly Accurate Robotic Grasp Detection using Fully Convolutional Neural Network with Rotation Ensemble Module

## TL;DR

This paper introduces a rotation ensemble module for robotic grasp detection using CNNs, achieving high accuracy and real-time performance, especially for multiple objects and novel items.

## Contribution

The paper presents a novel rotation ensemble module that enhances rotation invariance in grasp detection, outperforming existing methods in accuracy and speed.

## Key findings

- Achieved up to 99.2% accuracy on Cornell dataset
- Real-time grasp detection at 50 fps
- 93.8% success rate in robotic grasping of small objects

## Abstract

Rotation invariance has been an important topic in computer vision tasks. Ideally, robot grasp detection should be rotation-invariant. However, rotation-invariance in robotic grasp detection has been only recently studied by using rotation anchor box that are often time-consuming and unreliable for multiple objects. In this paper, we propose a rotation ensemble module (REM) for robotic grasp detection using convolutions that rotates network weights. Our proposed REM was able to outperform current state-of-the-art methods by achieving up to 99.2% (image-wise), 98.6% (object-wise) accuracies on the Cornell dataset with real-time computation (50 frames per second). Our proposed method was also able to yield reliable grasps for multiple objects and up to 93.8% success rate for the real-time robotic grasping task with a 4-axis robot arm for small novel objects that was significantly higher than the baseline methods by 11-56%.