Alfredo Delgado-Spíndola

Alfredo Delgado-Spíndola

Auto-generated profile, based on publicly available information

Alfredo Delgado-Spíndola

Tecnologico de Monterrey, School of Engineering and Sciences, Torren, Mexico

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2021 in Mechatronics
Verified
Journal Article
Closed access
ADAlfredo Delgado-Spíndola
Alfredo Delgado-Spíndola
RCRicardo Campa
Ricardo Campa
EBEusebio Bugarin
Eusebio Bugarin
AMAngel Israel Soto Marrufo
Angel Israel Soto Marrufo

15 May 2026 in IEEE Access
Verified
Journal Article
Open access
JMJorge Montoya-Cháirez
Jorge Montoya-Cháirez
ADAlfredo Delgado-Spíndola
Alfredo Delgado-Spíndola
IGIsaac Gandarilla
Isaac Gandarilla
VSVictor Santibanez
Victor Santibanez
EBEusebio Bugarin
Eusebio Bugarin
Javier Moreno-ValenzuelaJavier Moreno-Valenzuela
Javier Moreno-Valenzuela
In this work, a robust adaptive neural network controller is proposed for tracking control of the displacement and orientation, while keeping the pendulum in the upright position, of a two-wheeled inverted pendulum system. The proposed approach is designed to be compatible with commercial robotic platforms, which typically employ velocity control signals rather than torque or voltage inputs and provide limited access to inner control layers. Accordingly, the proposed control architecture consists of an inaccessible embedded velocity-control loop, which operates as a black-box subsystem, and an outer adaptive controller that generates the reference velocity commands for the embedded system. To this end, an adaptive neural network controller is designed to achieve the control objectives using acceleration signals, which are subsequently integrated before being applied to the system.Finally, in addition to the stability proof, the effectiveness of the proposed controller is validated through real-time experiments on the RAB-ITLAG-2 platform and compared with a model based, proportional derivative and neuro-fuzzy controllers. The numerical results, including the root mean square, standard deviation, and peak values of the tracking errors, demonstrate the superior performance of the proposed method in the presence of model uncertainties and external disturbances.