Mobile Robot Navigation Using an Object Recognition Software with RGBD Images and the YOLO Algorithm

被引:47
作者
Dos Reis, Douglas Henke [1 ]
Welfer, Daniel [2 ]
De Souza Leite Cuadros, Marco Antonio [3 ]
Tello Gamarra, Daniel Fernando [1 ]
机构
[1] Fed Univ Santa Maria Santa Maria UFSM, Control & Automat Engn Course, Santa Maria, RS, Brazil
[2] Univ Fed Santa Maria, Santa Maria UFSM, Dept Appl Comp, Santa Maria, RS, Brazil
[3] IFES, Profess Master Program Control & Automat Engn, Vitoria, ES, Brazil
关键词
731.5; Robotics; -; 921; Mathematics;
D O I
10.1080/08839514.2019.1684778
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This work presents a vision system based on the YOLO algorithm to identify static objects that could be obstacles in the path of a mobile robot. In order to identify the objects and its distances, a Microsoft Kinect sensor was used. In addition, a Nvidia Jetson TX2 GPU was used to increase the image processing algorithm performance. Our experimental results indicate that the YOLO network has detected all the predefined obstacles for which it has been trained with good reliability and the calculus of the distance using the depth information returned by the Microsoft Kinect camera had an error below of 3,64%.
引用
收藏
页码:1290 / 1305
页数:16
相关论文
共 24 条
[1]  
BERSAN D, 2018, 2018 BRAZ S ROB 2018
[2]  
BEZERRA CG, 2004, THESIS
[3]   A Study on Measures to Improve Physical Health of College Students in China under the Guidance in "Healthy China" Strategy [J].
Chen, Li ;
Zhou, Wei ;
Pu, Tingyan ;
Zhao, Ziling .
2018 5TH INTERNATIONAL CONFERENCE ON TEACHING AND COMPUTATIONAL SCIENCE (ICTCS 2018), 2018, :27-32
[4]  
CUADROS MAS, 2014, AS PAC COMP SCI APPL
[5]  
*EQ DAT SCI AC, DEEP LEARN BOOK
[6]  
FADLI H, 2017, INT C ADV MECH INT M
[7]   Control of a nonholonomic mobile robot using neural networks [J].
Fierro, R ;
Lewis, FL .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (04) :589-600
[8]  
GAMARRA DFT, 2005, P IEEE INT C ROB AUT
[9]  
GU S, 2018, C ADV INT MECH AIM A
[10]  
GUO Y, 2016, NEUROCOMPUTING RECEN