Next Article in Journal
Microwave Staring Correlated Imaging Based on Time-Division Observation and Digital Waveform Synthesis
Previous Article in Journal
Objective Image Quality Measures for Disparity Maps Evaluation
Previous Article in Special Issue
Prediction of Critical Flashover Voltage of High Voltage Insulators Leveraging Bootstrap Neural Network
Open AccessArticle

Artificial Neural Network Controller for a Modular Robot Using a Software Defined Radio Communication System

1
Telecommunications Engineering Department, Universidad Distrital Francisco José de Caldas, Bogotá 11021-110231588, Colombia
2
Control and Automation Engineering Department, Universidad Distrital Francisco José de Caldas, Bogotá 11021-110231588, Colombia
3
Electrical Engineering Department, Universidad Distrital Francisco José de Caldas, Bogotá 11021-110231588, Colombia
*
Author to whom correspondence should be addressed.
Electronics 2020, 9(10), 1626; https://doi.org/10.3390/electronics9101626
Received: 11 July 2020 / Revised: 7 August 2020 / Accepted: 12 August 2020 / Published: 2 October 2020
(This article belongs to the Special Issue Theory and Applications of Fuzzy Systems and Neural Networks)
Modular robots are flexible structures that offer versatility and configuration options for carrying out different types of movements; however, disconnection problems between the modules can lead to the loss of information, and, therefore, the proposed displacement objectives are not met. This work proposes the control of a chain-type modular robot using an artificial neural network (ANN) that enables the robot to go through different environments. The main contribution of this research is that it uses a software defined radio (SDR) system, where the Wi-Fi channel with the best signal-to-noise Ratio (SNR) is selected to send the information regarding the simulated movement parameters and obtained by the controller to the modular robot. This allows for faster communication with fewer errors. In case of a disconnection, these parameters are stored in the simulator, so they can be sent again, which increases the tolerance to communication failures. Additionally, the robot sends information about the average angular velocity, which is stored in the cloud. The errors in the ANN controller results, in terms of the traveled distance and time estimated by the simulator, are less than 6% of the real robot values. View Full-Text
Keywords: artificial neural network (ANN); modular robot; software defined radio (SDR); signal-to-noise ratio (SNR) artificial neural network (ANN); modular robot; software defined radio (SDR); signal-to-noise ratio (SNR)
Show Figures

Figure 1

MDPI and ACS Style

Pedraza, L.F.; Hernández, H.A.; Hernández, C.A. Artificial Neural Network Controller for a Modular Robot Using a Software Defined Radio Communication System. Electronics 2020, 9, 1626. https://doi.org/10.3390/electronics9101626

AMA Style

Pedraza LF, Hernández HA, Hernández CA. Artificial Neural Network Controller for a Modular Robot Using a Software Defined Radio Communication System. Electronics. 2020; 9(10):1626. https://doi.org/10.3390/electronics9101626

Chicago/Turabian Style

Pedraza, Luis F.; Hernández, Henry A.; Hernández, Cesar A. 2020. "Artificial Neural Network Controller for a Modular Robot Using a Software Defined Radio Communication System" Electronics 9, no. 10: 1626. https://doi.org/10.3390/electronics9101626

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop