Juan Escobar-Naranjo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Juan Escobar-Naranjo has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Marcelo Vladimir Garcia
Universidad Técnica de Ambato, UTA
6 shared publications - Ana Pamela Castro-Martin
Facultad de Ingeniería en Sistemas Electrónica e Industrial (FISEI), Universidad Técnica de Ambato (UTA), Campus Huachi Chico, Ambato 180207, Ecuador
4 shared publications - Carlos A. Garcia
Universitat Politecnica de Catalunya
4 shared publications - David-I. Ilvis
Universidad Técnica de Ambato, UTA
3 shared publications - Dalia Alvarez-Montenegro
Universidad Técnica de Ambato, UTA
2 shared publications - Gustavo Caiza
Departamento De Electrónica, Universidad Politécnica Salesiana, UPS, Quito 170146, Ecuador
2 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 158 (1) , 35
An Artificial Intelligence-Based System for Automated Solid Waste Sorting
Inadequate solid waste management necessitates efficient automated sorting solutions. This paper presents an automated waste sorting system integrating artificial intelligence and Internet of Things technologies. Guided by CRISP DM and Modular Design principles, the prototype employs a YOLOv11s model deployed on an NVIDIA Jetson Nano alongside an ESP32 microcontroller to classify plastic bottles, paper, organic waste, and electronic waste. Functional testing across fifty operational trials achieved a 90% overall classification accuracy. The integrated physical system effectively synchronizes computer vision with mechanical actuation, offering a viable technological contribution toward source separation and urban sustainability.
- 2 November 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 158 (1) , 35
Open AccessAn Artificial Intelligence-Based System for Automated Solid Waste Sorting
Inadequate solid waste management necessitates efficient automated sorting solutions. This paper presents an automated waste sorting system integrating artificial intelligence and Internet of Things technologies. Guided by CRISP DM and Modular Design principles, the prototype employs a YOLOv11s model deployed on an NVIDIA Jetson Nano alongside an ESP32 microcontroller to classify plastic bottles, paper, organic waste, and electronic waste. Functional testing across fifty operational trials achieved a 90% overall classification accuracy. The integrated physical system effectively synchronizes computer vision with mechanical actuation, offering a viable technological contribution toward source separation and urban sustainability.
- Open Access
- 7 May 2026
- Published by Frontiers Media SA in Frontiers in Robotics and AI
- Vol. 13, 1825254
A methodological framework and experimental protocol for proactive human–robot collaboration with multimodal intention prediction and adaptive control
Industry 5.0 requires collaborative robots that can anticipate operator needs to improve fluency and safety in assembly. However, many human–robot collaboration (HRC) systems still treat perception, intention inference, and control as separate components. This study presents a theoretical perception–cognition–action framework that explicitly couples multimodal intention prediction with proactive and adaptive control. Multimodal observations such as RGB-D vision, gaze, wrist force/torque, robot joint state, and previous robot action are encoded by a hybrid Convolutional Neural Network (CNN)– Long Short-Term Memory (LSTM)–Transformer to estimate (i) a probability distribution over future human intentions and (ii) a short-horizon motion trajectory, trained with a composite loss that jointly optimizes classification and regression with kinematic coherence. The predicted intention probability is embedded into an augmented Markov Decision Process state, enabling a Soft Actor–Critic agent to learn continuous policies with rewards designed for synergy, efficiency, safety, and fluency. The main contributions of this study are the formal probabilistic linkage from intention prediction to adaptive control, the definition of a multi-output cognitive objective, and the design of an implementation-ready experimental protocol for future empirical validation. Overall, the proposed methodological framework and experimental protocol provide a reproducible basis for future empirical validation of proactive human–robot collaboration in industrial assembly tasks.
- 7 May 2026
- Published by Frontiers Media SA in Frontiers in Robotics and AI
- Vol. 13, 1825254
Open AccessA methodological framework and experimental protocol for proactive human–robot collaboration with multimodal intention prediction and adaptive control
Industry 5.0 requires collaborative robots that can anticipate operator needs to improve fluency and safety in assembly. However, many human–robot collaboration (HRC) systems still treat perception, intention inference, and control as separate components. This study presents a theoretical perception–cognition–action framework that explicitly couples multimodal intention prediction with proactive and adaptive control. Multimodal observations such as RGB-D vision, gaze, wrist force/torque, robot joint state, and previous robot action are encoded by a hybrid Convolutional Neural Network (CNN)– Long Short-Term Memory (LSTM)–Transformer to estimate (i) a probability distribution over future human intentions and (ii) a short-horizon motion trajectory, trained with a composite loss that jointly optimizes classification and regression with kinematic coherence. The predicted intention probability is embedded into an augmented Markov Decision Process state, enabling a Soft Actor–Critic agent to learn continuous policies with rewards designed for synergy, efficiency, safety, and fluency. The main contributions of this study are the formal probabilistic linkage from intention prediction to adaptive control, the definition of a multi-output cognitive objective, and the design of an implementation-ready experimental protocol for future empirical validation. Overall, the proposed methodological framework and experimental protocol provide a reproducible basis for future empirical validation of proactive human–robot collaboration in industrial assembly tasks.
- 8 February 2026
- Published by Springer Nature
- p. 127-144
Detection of Criminal Situations for Surveillance in Commercial Establishments
- 8 February 2026
- Published by Springer Nature
- p. 127-144
Detection of Criminal Situations for Surveillance in Commercial Establishments
- 8 February 2026
- Published by Springer Nature
- p. 101-125
Intelligent System for Gardens with Artificial Vision
- 8 February 2026
- Published by Springer Nature
- p. 101-125
Intelligent System for Gardens with Artificial Vision
- 8 February 2026
- Published by Springer Nature
- p. 453-473
VPD Monitoring with ESP32 and Flask API for Early Detection of Powdery Mildew in Rose Greenhouses
- 8 February 2026
- Published by Springer Nature
- p. 453-473
VPD Monitoring with ESP32 and Flask API for Early Detection of Powdery Mildew in Rose Greenhouses
- 2 January 2026
- Published by Springer Nature
- p. 216-229
Analysis of the Legal Framework for the Cybersecurity Situation in the Ecuadorian Government Sector
- 2 January 2026
- Published by Springer Nature
- p. 216-229
Analysis of the Legal Framework for the Cybersecurity Situation in the Ecuadorian Government Sector
- 2 January 2026
- Published by Springer Nature
- p. 525-542
Integration of Simulation in Strategic Decision-Making in Dairy Industry
- 2 January 2026
- Published by Springer Nature
- p. 525-542
Integration of Simulation in Strategic Decision-Making in Dairy Industry
- Open Access
- 15 November 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 115 (1) , 18
IoT System for Catering Service in Hospitals
In hospitals, IoT has facilitated connectivity between patients and medical services using historical health data. However, its adoption in hospital catering services has been slower. This work describes the implementation of an IoT system with a three-layer architecture: the first layer collects data on patient diets and environmental conditions from the food warehouse, the second layer processes this information, establishing rules and converting raw data into valuable information, and the third layer stores the data in the cloud, presenting it in a web application. A functional system was obtained that meets the needs of catering service personnel and the hospital in which it was implemented.
- 15 November 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 115 (1) , 18
Open AccessIoT System for Catering Service in Hospitals
In hospitals, IoT has facilitated connectivity between patients and medical services using historical health data. However, its adoption in hospital catering services has been slower. This work describes the implementation of an IoT system with a three-layer architecture: the first layer collects data on patient diets and environmental conditions from the food warehouse, the second layer processes this information, establishing rules and converting raw data into valuable information, and the third layer stores the data in the cloud, presenting it in a web application. A functional system was obtained that meets the needs of catering service personnel and the hospital in which it was implemented.
- Open Access
- 30 June 2025
- Published by Centro de Investigación Científica e Innovación Académica Profesional in Tse'de
- Vol. 8 (1)
INTEGRACIÓN DE IIOT Y COMPUTACIÓN EN LA NUBE PARA LA AUTOMATIZACIÓN INDUSTRIAL AVANZADA
En el sector industrial, la eficiencia en la producción es esencial para mantener la competitividad, reducir costos y satisfacer las demandas del mercado. Este estudio presentó un sistema basado en tecnologías del Internet Industrial de las Cosas (IIoT) y Computación en la Nube para el control y monitoreo remoto de un proceso de corte de perfiles de aluminio. La integración de herramientas como Ubidots, NodeRed, Firebase, Telegram y PLC’s permitió optimizar la presión y control en tiempo real del proceso, mejorando la productividad y demostrando la fiabilidad del sistema para la automación de procesos industriales.
- 30 June 2025
- Published by Centro de Investigación Científica e Innovación Académica Profesional in Tse'de
- Vol. 8 (1)
Open AccessINTEGRACIÓN DE IIOT Y COMPUTACIÓN EN LA NUBE PARA LA AUTOMATIZACIÓN INDUSTRIAL AVANZADA
En el sector industrial, la eficiencia en la producción es esencial para mantener la competitividad, reducir costos y satisfacer las demandas del mercado. Este estudio presentó un sistema basado en tecnologías del Internet Industrial de las Cosas (IIoT) y Computación en la Nube para el control y monitoreo remoto de un proceso de corte de perfiles de aluminio. La integración de herramientas como Ubidots, NodeRed, Firebase, Telegram y PLC’s permitió optimizar la presión y control en tiempo real del proceso, mejorando la productividad y demostrando la fiabilidad del sistema para la automación de procesos industriales.
- Open Access
- 16 June 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (12) , 7202
Autonomous Navigation of Robots: Optimization with DQN
In the field of artificial intelligence, control systems for mobile robots have undergone significant advancements, particularly within the realm of autonomous learning. However, previous studies have primarily focused on predefined paths, neglecting real-time obstacle avoidance and trajectory reconfiguration. This research introduces a novel algorithm that integrates reinforcement learning with the Deep Q-Network (DQN) to empower an agent with the ability to execute actions, gather information from a simulated environment in Gazebo, and maximize rewards. Through a series of carefully designed experiments, the algorithm’s parameters were meticulously configured, and its performance was rigorously validated. Unlike conventional navigation systems, our approach embraces the exploration of the environment, facilitating effective trajectory planning based on acquired knowledge. By leveraging randomized training conditions within a simulated environment, the DQN network exhibits superior capabilities in computing complex functions compared to traditional methods. This breakthrough underscores the potential of our algorithm to significantly enhance the autonomous learning capacities of mobile robots.
- 16 June 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (12) , 7202
Open AccessAutonomous Navigation of Robots: Optimization with DQN
In the field of artificial intelligence, control systems for mobile robots have undergone significant advancements, particularly within the realm of autonomous learning. However, previous studies have primarily focused on predefined paths, neglecting real-time obstacle avoidance and trajectory reconfiguration. This research introduces a novel algorithm that integrates reinforcement learning with the Deep Q-Network (DQN) to empower an agent with the ability to execute actions, gather information from a simulated environment in Gazebo, and maximize rewards. Through a series of carefully designed experiments, the algorithm’s parameters were meticulously configured, and its performance was rigorously validated. Unlike conventional navigation systems, our approach embraces the exploration of the environment, facilitating effective trajectory planning based on acquired knowledge. By leveraging randomized training conditions within a simulated environment, the DQN network exhibits superior capabilities in computing complex functions compared to traditional methods. This breakthrough underscores the potential of our algorithm to significantly enhance the autonomous learning capacities of mobile robots.