GAIA: Gestión integral para la prevención, extinción y reforestación debido a incendios forestales
Summary
Wildfires that burn for weeks and affect millions of people represent a challenge we are not prepared for. These fires burn with greater intensity in areas where they have always occurred and also in unexpected places, such as dry peatlands and thawing permafrost. They result from a complex interaction of biological, meteorological, physical, and social factors that influence their likelihood, spread, intensity, duration, and extent, as well as their potential to cause damage to economies, the environment, and society. This project investigates how to manage and reduce the risks associated with wildfires through the most advanced technology.
The main 3 contributions of the RoboticsLab group are:
* LIDAR Signal Densification Algorithms: Research focuses on algorithms and software techniques for densifying the LIDAR sensor signal, commonly used in outdoor robots.
* Outdoor Navigation Algorithms: This involves developing and evaluating point-to-point autonomous navigation algorithms for robots in unstructured environments, such as forests.
* Deep Learning for Object and Surface Detection: Evolution of techniques for detecting objects and surfaces in unstructured environments using Deep Learning and sensors like LIDAR and visual cameras, aimed at autonomous robot navigation.
Videos
LiDAR Segmentation
Image Segmentation
Simulated Environments
Synthetic Driving Capture
Trash Detection
Fusion Segmentation, LiDAR + Vision
Publications
Cross-Dataset Evaluation of Visual Semantic Segmentation Models for Off-Road Autonomous Driving
David Pascual-Hernández, Sergio Paniego, Roberto Calvo-Palomino, Inmaculada Mora-Jiménez, Jose Maria Cañas-Plaza
Expert Systems with Applications, Elsevier, 2026
Deep Learning-Based Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving in Unstructured Environments
Félix Martínez, David Pascual-Hernández, Daniel Borja Fernández, Inmaculada Mora Jiménez, José María Cañas
Proceedings of the XXV International Workshop on Physical Agents (WAF), 2025
Imitation Learning for vision based Autonomous Driving with Ackermann cars
Alejandro Moncalvillo, José María Cañas, Sergio Paniego, Roberto Calvo, Abdulla Al-Kaff
Proceedings of the International Workshop of Physical Agents 2024
Enhancing End-to-End Control in Autonomous Driving through Kinematic-Infused and Visual Memory Imitation Learning
Sergio Paniego, Roberto Calvo-Palomino, José M. Cañas
NeuroComputing, Elsevier, 2024
Autonomous Driving in Traffic with End-to-End Vision-based Deep Learning
Sergio Paniego, Enrique Shinohara, José M. Cañas
NeuroComputing, Elsevier, 2024
Behavior Metrics: An Open-Source Assessment Tool for Autonomous Driving Tasks
Sergio Paniego, Roberto Calvo-Palomino, José M. Cañas
