Convolutional neural network

Related papers: 20

About

A convolutional neural network (CNN) is a class of deep learning model designed to automatically extract hierarchical spatial features from grid-structured data, most commonly images. Inspired by the organization of the biological visual cortex, CNNs apply learned filters across input data through successive convolutional layers, progressively detecting edges, textures, and complex patterns without requiring hand-crafted feature engineering. In robotics and AI, CNNs serve as a foundational perception tool across a wide range of tasks: object detection and recognition, 6D pose estimation, robotic grasp planning, semantic scene mapping, gesture and action recognition, and end-to-end visuomotor control. They process inputs from cameras, LiDAR, depth sensors, and even electromyography signals, enabling robots to interpret and act upon rich sensory data in real time. CNNs matter because they dramatically outperform traditional computer vision methods in accuracy and generalization, enabling robots to operate reliably in unstructured, real-world environments. Their versatility across 2D images, 3D voxel grids, and temporal sequences makes them indispensable for autonomous driving, manipulation, agricultural robotics, and human-robot interaction—forming the perceptual backbone of modern intelligent systems.

Top Cited Papers

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Q. Al-Dujaili, Ye Duan, Omran Al-Shamma, José Santamaría, Mohammed A. Fadhel, Muthana Al‐Amidie, Laith Farhan

Citations: 7484 • 2021

VoxNet: A 3D Convolutional Neural Network for real-time object recognition

Daniel Maturana, Sebastian Scherer

Citations: 3579 • 2015

SECOND: Sparsely Embedded Convolutional Detection

Yan Yan, Yuxing Mao, Bo Li

Citations: 3212 • 2018

Convolutional networks and applications in vision

Yann LeCun, Koray Kavukcuoglu, Clément Farabet

Citations: 2163 • 2010

PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

Xiang Yu, Tanner Schmidt, Venkatraman Narayanan, Dieter Fox

Citations: 2088 • 2018

Temporal Convolutional Networks for Action Segmentation and Detection

Colin Lea, M. D. Flynn, Renè Vidal, Austin Reiter, Gregory D. Hager

Citations: 2028 • 2017

End-to-end training of deep visuomotor policies

Sergey Levine, Chelsea Finn, Trevor Darrell, Pieter Abbeel

Citations: 1715 • 2016

A State-of-the-Art Survey on Deep Learning Theory and Architectures

Md Zahangir Alom, Tarek M. Taha, Chris Yakopcic, Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin, Mahmudul Hasan, Brian C. Van Essen, Abdul Ahad S. Awwal, Vijayan K. Asari

Citations: 1593 • 2019

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

Saurabh Gupta, Ross Girshick, Pablo Arbeláez, Jitendra Malik

Citations: 1531 • 2014

End-to-End Training of Deep Visuomotor Policies

Sergey Levine, Chelsea Finn, Trevor Darrell, Pieter Abbeel

Citations: 1399 • 2015

Skin-inspired highly stretchable and conformable matrix networks for multifunctional sensing

Qilin Hua, Junlu Sun, Haitao Liu, Rongrong Bao, Ruomeng Yu, Junyi Zhai, Caofeng Pan, Zhong Lin Wang

Citations: 1391 • 2018

Going Deeper with Embedded FPGA Platform for Convolutional Neural Network

Jiantao Qiu, Jie Wang, Song Yao, Kaiyuan Guo, Boxun Li, Erjin Zhou, Jincheng Yu, Tianqi Tang, Ningyi Xu, Sen Song, Yu Wang, Huazhong Yang

Citations: 1260 • 2016

Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics

Jeffrey Mahler, Jacky Liang, Sherdil Niyaz, Michael Laskey, Richard Doan, Xinyu Liu, Juan Pablo Aparicio, Ken Goldberg

Citations: 1162 • 2017

Learning the signatures of the human grasp using a scalable tactile glove

Subramanian Sundaram, Petr Kellnhofer, Yunzhu Li, Jun-Yan Zhu, Antonio Torralba, Wojciech Matusik

Citations: 1118 • 2019

Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours

Lerrel Pinto, Abhinav Gupta

Citations: 1099 • 2016

DeepFruits: A Fruit Detection System Using Deep Neural Networks

Inkyu Sa, Zongyuan Ge, Feras Dayoub, Ben Upcroft, Tristán Pérez, Chris McCool

Citations: 1079 • 2016

Real-time grasp detection using convolutional neural networks

Joseph Redmon, Anelia Angelova

Citations: 912 • 2015

Facial expression recognition with Convolutional Neural Networks: Coping with few data and the training sample order

André T. Lopes, Edilson de Aguiar, Alberto F. De Souza, Thiago Oliveira-Santos

Citations: 798 • 2016

Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks

Henggang Cui, Vladan Radosavljević, Fang‐Chieh Chou, Tsung-Han Lin, Thi Nguyen, Tzu-Kuo Huang, Jeff Schneider, Nemanja Djuric

Citations: 671 • 2019

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

Manfredo Atzori, Matteo Cognolato, Henning Müller

Citations: 662 • 2016