Embedded Files
Please reload this website if you don't find any videos in this page.
RaccoonBot:
An Autonomous Wire-Traversing Solar-Tracking Robot for Persistent Environmental Monitoring
RaccoonBot:
An Autonomous Wire-Traversing Solar-Tracking Robot for Persistent Environmental Monitoring
Robotics · Mechatronics · Embedded Systems · Power Electronics · IoT · AI/ML · Energy Autonomy
RaccoonBot during a validation test at UCI.
RaccoonBot is an autonomous, bio-inspired robotic platform I developed for persistent environmental monitoring. Designed to traverse suspended wires while tracking the sun for energy harvesting, it integrates robotics, embedded systems, power electronics, environmental sensing, IoT connectivity, and AI/ML-based energy management into a field-ready system that was deployed at the Crystal Cove State Park in Newport Beach, California, USA, for nearly a year from 2025 to 2026.
I led its development from concept and system architecture through prototyping, integration, validation, and deployment. During its field operation, RaccoonBot collected and remotely transmitted environmental data while serving as a real-world testbed for persistent robotic autonomy.
Stage 1 – Robotic Platform Development
Stage 1 – Robotic Platform Development
The robotic platform combines a wire-traversing locomotion system, self-locking worm-gear drive, environmental sensing, embedded control, and solar-energy harvesting. Its active solar-tracking system maximizes available charging power, while the self-locking drivetrain allows the robot to remain stationary without consuming energy for position holding.
I developed and integrated the platform's mechanical, electrical, embedded, and power systems, taking the robot through iterative prototyping, laboratory testing, manufacturing, field validation, and final deployment.
RaccoonBot and the UCI Robot Ecology Lab were featured by the Los Angeles Times in April 2025 for their nature-inspired approach to robotics and environmental applications:
The development from the robotic platform led to the following publications:
IEEE ICRA 2025 – RaccoonBot: An Autonomous Wire-Traversing Solar-Tracking Robot for Persistent Environmental Monitoring.
IEEE Access Journal Paper – V-model Based Mechatronic and Power Electronics Integration for an Efficient Solar-Powered Wire-Traversing Robot.
IEEE Conference Paper – Noise Mitigation in Power Sensing under EMI via RMS-Based Numerical Filtering for Embedded Systems in Mechatronic Devices.
Graphical abstract from RaccoonBot's ICRA 2025 paper (click to access the paper).
RaccoonBot's video for ICRA 2025.
RaccoonBot featured in the Los Angeles Times' Daily Plot (click to access the article).
Stage 2 – Edge-to-Cloud IoT Architecture
Stage 2 – Edge-to-Cloud IoT Architecture
Deploying RaccoonBot for persistent environmental monitoring introduced a new challenge: the data collected in the field needed to be reliably transmitted, stored, and accessed remotely, while the robot's essential sensing and autonomous functions remained independent of continuous internet connectivity.
To solve this, I designed and led the development of an edge-to-cloud IoT architecture that distributes functionality across the robot, a local gateway, and the cloud. Environmental measurements are processed onboard and transmitted over LoRa to a nearby Raspberry Pi gateway, which connects the remote robotic platform to the internet and forwards the data to Firebase Firestore for cloud storage and remote visualization.
The resulting architecture extended RaccoonBot from an autonomous field robot into a persistent remote environmental monitoring system, connecting physical sensing in the field with remotely accessible data while preserving autonomous operation at the edge.
This development led to the following publication:
IEEE Internet of Things Journal (IoT-J) — Enabling Remote Persistent Environmental Monitoring with Robotic Platforms using an Edge-to-Cloud IoT Architecture.
RaccoonBot's deployment site at the Crystal Cove State Park in Newport Beach, California, USA.
RaccoonBot's deployment day with members of the Robot Ecology Lab at the Crystal Cove State Park.
RaccoonBot's remote environmental monitoring Edge-to-Cloud IoT architecture.
Stage 3 – Bio-Inspired Torpor and Learning-Based Energy Autonomy
Stage 3 – Bio-Inspired Torpor and Learning-Based Energy Autonomy
Long-term field deployment exposed one of the fundamental challenges of persistent robotics: RaccoonBot needed to remain operational despite changing weather and periods of limited solar energy. Rather than simply increasing battery capacity, we looked back to the animal that inspired the robot itself. Raccoons can reduce their activity and energy expenditure during harsh environmental conditions, inspiring a robotic torpor behavior that prioritizes energy conservation when conditions become unfavorable.
I initially implemented this behavior through a rule-based torpor controller, allowing RaccoonBot to transition between active and low-power states based on its energy conditions. Experience from extended field operation revealed the limitations of fixed rules under variable weather, motivating me to develop a learning-based controller using an artificial neural network (ANN) for more adaptive energy management.
The learning-based controller was validated over months of real-world operation, demonstrating improved energy management compared with the original rule-based strategy. RaccoonBot was able to maintain healthier energy levels, recover from periods of reduced solar availability and energy perturbations, and better sustain operation under challenging weather conditions. By combining a survival strategy inspired by nature with learning from its own field experience, RaccoonBot could adapt its behavior to available energy—turning bio-inspired torpor into a practical strategy for greater autonomy and endurance.
The development and field validation of this bio-inspired energy-management strategy led to the following publication:
IEEE Transactions on Field Robotics (T-FR) (Under first Review) – Learning-Based Energy-Aware Torpor Control for Persistent Solar-Powered Robots.
Main actors in the bio-inspired learning-based torpor framework for RaccoonBot's energy-aware autonomy.
With Kate Wheeler (President and CEO of Crystal Cove Conservancy) and Dr. Magnus Egerstedt during RaccoonBot's final retrieval from Crystal Conve State Park.
Autonomous Drone:
A Custom-Built UAV for GPS-Guided Flight and Navigation with ArduPilot
Autonomous Drone:
A Custom-Built UAV for GPS-Guided Flight and Navigation with ArduPilot
Robotics · Autonomous Systems · UAVs · Autonomous Navigation · Flight Control · Embedded Systems · Sensor Integration
Driven by my interest in autonomous systems and my passion for hands-on engineering, I took Dr. Peter Burke's Autonomous Drones course at UCI as an opportunity to explore a new robotics domain beyond my research work.
I built a fully autonomous UAV from the ground up, with the goal of developing an aerial platform capable of executing a complete GPS-guided mission without manual flight control. Starting from individual components, I assembled the mechanical platform, soldered and integrated the electronics and power system, and incorporated the onboard flight controller, IMU, GPS, ESCs, telemetry radios, and failsafe systems.
Bringing the aircraft from a collection of integrated subsystems to reliable autonomous flight required extensive calibration, debugging, control tuning, and iterative flight testing. I configured the ArduPilot firmware, calibrated the onboard sensors, and tuned the PID control loops, progressively validating the aircraft from initial flight tests to stable controlled flight and, ultimately, autonomous operation. The completed UAV successfully executed a fully autonomous GPS-guided mission, including takeoff, waypoint navigation, and landing, demonstrating the successful integration of its mechanical, electrical, sensing, control, and embedded systems.
Field testing with Dr. Peter Burke, a UAV Guinness World Record holder, at UCI.
Final autonomous mission of the UAV I built, performing takeoff, waypoint navigation, and landing.
The autonomous UAV I built during field testing at UCI.
Jean Luc:
Animatronic Robot Redesign for Theatrical Performance
Jean Luc:
Animatronic Robot Redesign for Theatrical Performance
I led and mentored a team of engineering students in the full redesign of Jean Luc, an animatronic robot featured in the Winter Lights show at the Discovery Cube in Orange County. This revamp modernized the robot’s mechanical design, electronics, and embedded systems to support live, repeatable performances.
Key contributions included:
Redesigning the robot’s mechanical architecture for expressive, reliable movement.
Developing a custom PCB with integrated power electronics.
Programming embedded software to synchronize with audio-visual cues.
Creating a human-machine interface (HMI) to enhance real-time actor control.
This project led to the following publication:
IEEE Conference Paper (Best Paper Award 🏆) – Jean Luc: An Animatronic Robot for Challenge-Based Learning and STEAM Outreach.
This project highlights my ability to translate artistic vision into functional robotic systems and to lead multidisciplinary efforts from concept to live deployment.
Integrated MPPT and DC-DC Converter Design: Metaheuristic Optimization from Theory to Application
Integrated MPPT and DC-DC Converter Design: Metaheuristic Optimization from Theory to Application
This project showcases the integration of all my major contributions as a Ph.D. student at Tecnológico de Monterrey—ranging from the development of an enhanced Maximum Power Point Tracking (MPPT) algorithm based on metaheuristic optimization, to the creation of a novel design methodology for DC-DC converters.
I introduced the first simulated version of the improved MPPT algorithm using the Earthquake Optimization Algorithm (EA) in a peer-reviewed journal article, demonstrating the algorithm’s potential for a range of power electronics applications. Building on this, I contributed a book chapter proposing a reinitialization technique for MPPTs based on a perceptron artificial neural network (ANN), enabling greater robustness in metaheuristic-based tracking algorithms. Finally, I consolidated these efforts in a comprehensive peer-reviewed journal publication, which experimentally validated both the enhanced MPPT algorithm and the optimally designed DC-DC converter that served as its hardware testbed.
You can find bellow these publications:
Journal Paper – Improved MPPT Algorithm for Photovoltaic Systems Based on the Earthquake Optimization Algorithm.
Book Chapter – Solar Irradiation Changes Detection for Photovoltaic Systems Through ANN Trained with a Metaheuristic Algorithm.
Journal Paper – Experimental Validation of an Enhanced MPPT Algorithm and an Optimal DC–DC Converter Design Powered by Metaheuristic Optimization for PV Systems.
This project reflects my ability to integrate advanced optimization techniques with practical power electronics and real-time embedded systems. It also validates my hands-on expertise in designing, fabricating, and testing custom PCBs for functional, field-deployable energy systems—demonstrating a complete pipeline from theoretical modeling to physical implementation.
Self-balancing robot:
PSO-Optimized Control on a Custom Robotic System
Self-balancing robot:
PSO-Optimized Control on a Custom Robotic System
During my Ph.D. at Tecnológico de Monterrey, I developed a self-balancing robot with custom mechanical design, motor drivers, and a PID controller optimized using the Particle Swarm Optimization (PSO) algorithm, all running on an NXP FRDM-K64F embedded platform. I presented this work at the joint ICMEAE-2020 and ICCRE-2020 IEEE conferences in Osaka, Japan, where it received the Best Presentation Award.
The project resulted in the following publication:
IEEE Conference Paper – Self-Balancing Robot Control Optimization Using PSO.
This project deepened my expertise in control systems, mechatronic integration, and embedded optimization techniques.
Furuta pendulum system:
Adaptive Control and Mechatronic Integration
Furuta pendulum system:
Adaptive Control and Mechatronic Integration
During my Ph.D. at Tecnologico de Monterrey, I developed a Furuta Pendulum system with custom mechanical design, power electronics, and an embedded MRAC-PID controller running on an NXP FRDM-K64F board. This mechatronic system stabilized a nonlinear plant in real time and integrated adaptive control techniques with hardware implementation.
I presented this work at the joint ICMEAE-2019 and ICCRE-2019 IEEE conferences in Nanjing, China, where it received the Best Presentation Award. An extended version was later published in a peer-reviewed journal, highlighting an ANN-based MRAC-PID strategy.
The project resulted in the following publications:
IEEE Conference Paper – Design, Implementation and Nonlinear Control Analysis of a Furuta Pendulum System.
Extended Journal Paper – ANN Based MRAC-PID Controller Implementation for a Furuta Pendulum System Stabilization (ASTESJ).
This project reflects my strength in integrating control theory with real-time embedded systems—skills I continue to apply in robotics and intelligent mechatronic design.
Earthquake Optimization Algorithm:
Development, Validation, and Real-Time Application
Earthquake Optimization Algorithm:
Development, Validation, and Real-Time Application
As a Ph.D. student at Tecnológico de Monterrey, I developed the Earthquake Optimization Algorithm, a novel metaheuristic designed for applications with broad search spaces, including multi-objective optimization problems. I validated its effectiveness through a case study involving DC motor model identification and PID controller tuning (through MATLAB and Simulink), comparing its performance to analytical methods (AM) for both modeling and control tasks.
The entire system was implemented and tested in real-time using NI FPGA hardware through LabVIEW, demonstrating the algorithm's reliability in embedded applications. I also fully developed the testbed and the electrical circuit design for the motor driver and instrumentation.
This work was first presented at the NanoFim-2018 IEEE conference in Mexico City, Mexico. An extended version was later published in a peer-reviewed journal, showcasing the algorithm’s capability as a training method for Artificial Neural Networks (ANNs), with successful applications in mobile phone usage detection and logic gate emulation.
Here you can find both publications:
IEEE Conference Paper – Electric machines control optimization by a novel geo-inspired earthquake metaheuristic algorithm.
Extended Journal Paper – Mobile Phone Usage Detection by ANN Trained with a Metaheuristic Algorithm.
This project highlights my ability to bridge optimization techniques, control systems, and real-time embedded deployment, strengths I continue to apply across my field-deployable solutions.
Micro-CNC Machine Integration:
Firmware and HMI Development
Micro-CNC Machine Integration:
Firmware and HMI Development
As part of the Bi-National Laboratory on Smart Sustainable Energy Management and Technology Training project, I designed and coded embedded systems for Micro-CNC machines. My responsibilities included system integration, firmware development, and adapting code to translate G-code into precise waypoints to guide the CNC’s motion during the manufacturing process. I enabled real-time operation by linking the human-machine interface (HMI) with actuators, joysticks, and control buttons.
This role not only strengthened my embedded systems expertise, but also validated my ability to develop robust, application-ready solutions for advanced manufacturing systems.
Real-Time Motor Testing Platform:
Power Electronics and Embedded Systems Development
Real-Time Motor Testing Platform:
Power Electronics and Embedded Systems Development
As a Hardware and Software R&D Engineer at RT Venalia, I contributed to the full product development process in a fast-paced startup environment, focusing on embedded systems for high-voltage motor control. I developed and deployed firmware using FreeRTOS on an NXP MK64FN1M0VLL12 microcontroller, to enable reliable real-time operation of human-machine interfaces (HMIs) used for testing and controlling AC, BLDC, and DC motors.
I implemented multiple speed and torque control strategies, instrumented motors with encoders to enable closed-loop feedback, and integrated these systems with automatic testing routines. I also assisted in debugging PCB layouts and collaborated in the design of 6000W (400V-15A) inverters for sustainable energy and industrial applications. Additionally, I developed LabVIEW VIs to validate the reliability of the power inverters under various control schemes, interfacing with a NI FPGAs to simulate different input conditions and ensure consistent performance across multiple control signal sources (cross-platform interfacing).
This experience deepened my expertise in real-time embedded systems and power electronics, validating my ability to develop robust and field-deployable solutions for high-performance, safety-critical environments.
ExoTec project:
Design and Implementation of a Lower-Limb Rehabilitation Exoskeleton
ExoTec project:
Design and Implementation of a Lower-Limb Rehabilitation Exoskeleton
As lead engineer for my final degree project at Tecnológico de Monterrey (B.Sc. in Mechatronics Engineering, Robotics Concentration), I led a team to design and implement a wearable lower-limb rehabilitation exoskeleton. This multidisciplinary project combined mechanical, electrical, and embedded system design to deliver a functional prototype.
I took charge of the mechanical design and supervised CNC machining of custom parts. I developed the complete electronics system, including schematic design, PCB fabrication, and soldering. Together with my team, we integrated electromyographic (EMG) sensors for muscle-driven control and rotary encoders for motor velocity feedback. I personally implemented all embedded control software in C, covering signal processing and motor control on a microcontroller platform.
This project provided invaluable experience in leading a full-cycle mechatronic development effort and strengthened my expertise in robotics and embedded control systems.
Line-following robotic spider:
Embedded Control and Instrumentation for a Quadruped Platform
Line-following robotic spider:
Embedded Control and Instrumentation for a Quadruped Platform
As part of the capstone project for a robotics course within my concentration at Tecnológico de Monterrey, I developed an autonomous four-legged line-following robotic spider. I handled the full embedded systems development, from sensor integration to control logic, and assembled and instrumented the entire platform. The robot was designed to demonstrate walking gait coordination and responsive movement through embedded programming in C.
This hands-on project reinforced my skills in embedded control, mechatronic integration, and quadruped locomotion strategies.
Page updated
Google Sites
Report abuse