Browsing by Autor "Marcelo Saavedra Alcoba"

Now showing 1 - 7 of 7

A Computer Vision-Based Autonomous System for Ripe Strawberry Detection and Navigation
(2025) M. Barba; Marcelo Saavedra Alcoba; Edgar Eduardo Salazar Florez
This work presents an autonomous robotic system designed for ripe strawberry detection and navigation in agricultural environments using cost-efficient hardware and optimized algorithms. The system integrates a Jetson Nano for real-time image processing, employing LAB color space transformation, morphological filtering, and a lightweight MobileNet SSD model trained on the StrawDI dataset to classify strawberries by ripeness. Autonomous navigation is achieved via a Pixhawk flight controller that tracks GPS waypoints and adjusts trajectories dynamically using ultrasonic sensors for obstacle detection. Field experiments in a controlled strawberry field setup demonstrated robust performance: the vision system achieved 86.21% precision and 89.29% recall. Navigation tests showed 95% accuracy in following a 5-meter path, with successful obstacle avoidance. The results validate the feasibility of deploying low-cost, energy-efficient embedded systems for agricultural automation, addressing scalability challenges in resource-limited settings.
Análisis de Comportamientos de Vehículos de Braitenberg para la búsqueda robótica usando El Robot LEGO EV3
(2016) Marcelo Saavedra Alcoba; Mariela Gutierrez Callejas; Luigi Enríquez Paz
En el presente articulo se realiza el estudio del funcionamiento de dos disenos del conjunto de vehiculos propuestos por Valentino Braitenberg en 1984, mediante la plataforma robotica LEGO EV3. Los vehiculos es- tudiados son el comportamiento explorador y el temeroso, cada uno con caracteristicas y configuraciones diferentes pero con un objetivo comun, lograr evitar los obstaculos que se les presentan mientras se explora todo el ambiente. Para completar este proceso se puso una meta, es decir cuando el robot detecte una marca de un color la exploracion finaliza. Se analiza el tiempo total por cada exploracion realizada, esto con el fin de determinar cual de las configuraciones es el mas optimo al momento de buscar un objeto en un ambiente determinado.
Cohesion-Based Flocking Formation Using Potential Linked Nodes Model for Multi-Robot Agricultural Swarms
(Multidisciplinary Digital Publishing Institute, 2026) Kevin Marlon Soza-Mamani; Marcelo Saavedra Alcoba; Felipe Jesus Torres; Alvaro Javier Prado-Romo
Accurately modeling and representing the collective dynamics of large-scale robotic systems remains one of the fundamental challenges in swarm robotics. Within the context of agricultural robotics, swarm-based coordination schemes enable scalable and adaptive control of multi-robot teams performing tasks such as crop monitoring and autonomous field maintenance. This paper introduces a cohesive Potential Linked Nodes (PLNs) framework, an adjustable formation structure that employs Artificial Potential Fields (APFs), and virtual node–link interactions to regulate swarm cohesion and coordinated motion (CM). The proposed model governs swarm formation, modulates structural integrity, and enhances responsiveness to external perturbations. The PLN framework facilitates swarm stability, maintaining high cohesion and adaptability while the system’s tunable parameters enable online adjustment of inter-agent coupling strength and formation rigidity. Comprehensive simulation experiments were conducted to assess the performance of the model under multiple swarm conditions, including static aggregation and dynamic flocking behavior using differential-drive mobile robots. Additional tests within a simulated cropping environment were performed to evaluate the framework’s stability and cohesiveness under agricultural constraints. Swarm cohesion and formation stability were quantitatively analyzed using density-based and inter-robot distance metrics. The experimental results demonstrate that the PLN model effectively maintains formation integrity and cohesive stability throughout all scenarios.
Enhanced 3D Mapping for Mobile Robots: Post-Processing of Dense Stereo-VISLAM PointClouds
(2025) Brayan Gerson Duran Toconas; Marcelo Saavedra Alcoba
3D mapping is crucial for mobile robotics and autonomous navigation. While 3D LiDAR systems provide high accuracy, their cost restricts deployment on budget-constrained platforms. This work proposes a low-cost VISLAM approach using stereo vision for point cloud generation and enhances map quality through post-processing. We emphasize the collection of a dedicated 3D dataset specifically designed for benchmarking and evaluating different filtering techniques. Spectral analysis and Shannon entropy are used to detect structural patterns, reduce noise, with step-by-step visualization. The method is ROS 2-compatible and suited for resource-constrained environments, enabling accurate 3D perception from visual data alone.
Low-Computational-Load Real-time Path Planning and Trajectory Control based on Artificial Potential Fields
(2023) Kevin Marlon Soza Mamani; Marcelo Saavedra Alcoba
The presented project shows the theoretical development, design and subsequent implementation of a low-computational-load path planning system and the corresponding movement control for differential type robots. The model contemplates the use of Artificial Potential Fields for both aspects, control and planning. The theoretical development is based on the combination of the Local Minimum Method with a kinematic motion control model. The model simulations are performed in a Python programming environment (for the generation of the optimal path based on image processing) and in Matlab (for initial trajectory tracking simulation). The subsequent implementation is carried out by means of the GLADIUS ME32A robot in a controlled environment. Likewise, the system is powered by peripheral artificial vision and Wi-Fi communication.
Nonlinear System Identification for Temperature in a Biodiesel Reactor: A Simulation Case Study
(2025) Marcelo Saavedra Alcoba; Edgar Salazar Florez; Daniela Pérez Suárez; Jonathan Villanueva Tavira; Efredy Delgado-Aguilera
Postprocessing Optimization of RRT* Using Machine Learning and Information Theory for Robotic Navigation
(2025) Marcelo Saavedra Alcoba; Edgar Salazar Florez; Brayan G. Duran Toconas; Kevin Marlon Soza Mamani
This work presents an alternative post-processing approach for optimizing mobile robot trajectories by combining vector quantization techniques with information theory. We developed an algorithm based on Vector Quantization (VQ) and Kullback-Leibler Divergence (VQKL) that maintains the original RRT*'s obstacle avoidance capabilities. When comparing VQKL and VQ with the Ramer-Douglas-Peucker (RDP) algorithm, our methods demonstrate significant superiority: VQ achieves a 13% reduction in path length (versus RDP's 10%) while VQKL achieves 14%, along with an 83% (VQ) and 84% (VQKL) reduction in node count compared to the original RRT* output. These results are obtained through an adaptive optimization process that iteratively adjusts centroids using a progressive annealing scheme. To ensure trajectory feasibility, we implemented a validation system that verifies both geometric deviation from the original path and collision-free operation with obstacles. Extensive simulations across 20 different environments with 100 trials each confirm that our method generates significantly shorter, more efficient, and safer trajectories, establishing a viable alternative for robotic path optimization.