Daniel Colín García
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Daniel Colín García has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Javier Izquierdo-Reyes
School of Engineering and Sciences, Tecnologico de Monterrey, Mexico city 14380, Mexico
2 shared publications - Rogelio Bustamante-Bello
School of Engineering and Sciences, Tecnologico de Monterrey, Mexico city 14380, Mexico
2 shared publications - Hugo Gustavo Gonzalez-Hernandez
Tecnológico de Monterrey
1 shared publication Isaac López Villegas
School of Engineering and Sciences, Tecnologico de Monterrey, Mexico City Campus, Mexico City, Mexico
1 shared publication- Isaac López-Villegas
School of Engineering and Sciences, Tecnologico de Monterrey, Mexico city 14380, Mexico
1 shared publication - Kevin Javier Medina-Gómez
School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey 64849, Mexico
1 shared publication
Latest Publications
- Open Access
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 69591-69611
Evaluation of Graph- and Sampling-Based Path Planners for Multi-Agent Deployment in Known Urban Environments
Unmanned aerial vehicles (UAVs) have become key tools in emergency missions in urban environments, due to their rapid deployment and ability to operate in hazardous conditions. Path planning is crucial in these disasters, as it determines the safety and efficiency of the mission. This study compares graph-based algorithms, such as A-Star (A) and D-Star Lite (D Lite), as well as sampling-based methods, including Probabilistic Roadmaps (PRM), Rapidly-exploring Random Tree Star (RRT), and Batch Informed Trees (BIT), along with spline-based post-processing applied to the trajectories produced by the sampling-based planners. To evaluate the performance of path planning algorithms, a framework developed in Python generates known three-dimensional urban environments with static obstacles. The benchmark considered 50 scenes, each with 15 obstacles, 5 UAVs, and 5 seed trials, resulting in 10,000 runs across eight different planners. This study used a strict success criterion and analyzed planning time metrics, path length, minimum safety margin, and geometric smoothness. D* Lite achieved the highest success rate (98.8%) and the highest obstacle clearance, but at the cost of longer planning times. RRT* and RRT* with splines were the fastest methods (median ≈ 4.9 ms), although with lower success rates. In contrast, BIT* and BIT* with splines offered the best value, second only to D* Lite, combining high success rates with shorter paths, better path quality, and moderate computational demand. The benchmark provides a quantitative basis for planner selection in non-cooperative multi-agent deployment scenarios, without accounting for flight dynamics, sensor uncertainty, or dynamic obstacles.
- 27 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 69591-69611
Open AccessEvaluation of Graph- and Sampling-Based Path Planners for Multi-Agent Deployment in Known Urban Environments
Unmanned aerial vehicles (UAVs) have become key tools in emergency missions in urban environments, due to their rapid deployment and ability to operate in hazardous conditions. Path planning is crucial in these disasters, as it determines the safety and efficiency of the mission. This study compares graph-based algorithms, such as A-Star (A) and D-Star Lite (D Lite), as well as sampling-based methods, including Probabilistic Roadmaps (PRM), Rapidly-exploring Random Tree Star (RRT), and Batch Informed Trees (BIT), along with spline-based post-processing applied to the trajectories produced by the sampling-based planners. To evaluate the performance of path planning algorithms, a framework developed in Python generates known three-dimensional urban environments with static obstacles. The benchmark considered 50 scenes, each with 15 obstacles, 5 UAVs, and 5 seed trials, resulting in 10,000 runs across eight different planners. This study used a strict success criterion and analyzed planning time metrics, path length, minimum safety margin, and geometric smoothness. D* Lite achieved the highest success rate (98.8%) and the highest obstacle clearance, but at the cost of longer planning times. RRT* and RRT* with splines were the fastest methods (median ≈ 4.9 ms), although with lower success rates. In contrast, BIT* and BIT* with splines offered the best value, second only to D* Lite, combining high success rates with shorter paths, better path quality, and moderate computational demand. The benchmark provides a quantitative basis for planner selection in non-cooperative multi-agent deployment scenarios, without accounting for flight dynamics, sensor uncertainty, or dynamic obstacles.
- Open Access
A Transformer-Based Self-Organizing UAV Swarm for Assisting an Emergency Communications System
Natural disasters often compromise telecommunications infrastructure, leading to unstable services or complete communication blackouts that hinder rescue operations and exacerbate victims’ distress. Rapidly deployable alternatives are, therefore, critical to sustaining reliable connectivity in affected regions. This work proposes a self-organizing multi-Unmanned Aerial Vehicle (UAV) swarm network capable of providing stand-alone and temporary coverage to both victims and emergency personnel in areas with compromised infrastructure through access points installed onboard UAVs. To address the challenges of partial observability in decentralized coordination, we introduce the Soft Transformer Recurrent Graph Network (STRGN), a novel encoder–decoder architecture inspired by the transformer model and extending the Soft Deep Recurrent Graph Network (SDRGN). By leveraging multi-head and cross-attention mechanisms, the STRGN captures higher-order spatiotemporal relationships, enabling UAVs to integrate information about neighbor proximity and ground user density when selecting actions. This facilitates adaptive positioning strategies that enhance coverage, fairness, and connectivity under dynamic conditions. Simulation results show that transformer-based approaches, including STRGN, the Soft Transformer Graph Network, and the Transformer Graph Network, consistently outperform SDRGN, and the Soft Deep Graph Network, and Deep Graph Network baselines by approximately across core metrics, while also demonstrating improved scalability across diverse terrains and swarm sizes. These findings highlight STRGN’s potential as a resilient framework for UAV-assisted communications in disaster response.Open AccessA Transformer-Based Self-Organizing UAV Swarm for Assisting an Emergency Communications System
Natural disasters often compromise telecommunications infrastructure, leading to unstable services or complete communication blackouts that hinder rescue operations and exacerbate victims’ distress. Rapidly deployable alternatives are, therefore, critical to sustaining reliable connectivity in affected regions. This work proposes a self-organizing multi-Unmanned Aerial Vehicle (UAV) swarm network capable of providing stand-alone and temporary coverage to both victims and emergency personnel in areas with compromised infrastructure through access points installed onboard UAVs. To address the challenges of partial observability in decentralized coordination, we introduce the Soft Transformer Recurrent Graph Network (STRGN), a novel encoder–decoder architecture inspired by the transformer model and extending the Soft Deep Recurrent Graph Network (SDRGN). By leveraging multi-head and cross-attention mechanisms, the STRGN captures higher-order spatiotemporal relationships, enabling UAVs to integrate information about neighbor proximity and ground user density when selecting actions. This facilitates adaptive positioning strategies that enhance coverage, fairness, and connectivity under dynamic conditions. Simulation results show that transformer-based approaches, including STRGN, the Soft Transformer Graph Network, and the Transformer Graph Network, consistently outperform SDRGN, and the Soft Deep Graph Network, and Deep Graph Network baselines by approximately across core metrics, while also demonstrating improved scalability across diverse terrains and swarm sizes. These findings highlight STRGN’s potential as a resilient framework for UAV-assisted communications in disaster response.