In our robotics group, we are deeply engaged in advancing the field of autonomous driving, focusing our research on pivotal areas including vehicle perception and control systems. Our goal is to enhance the way autonomous vehicles understand and interact with their environment, ensuring they can navigate safely and efficiently in complex scenarios. We focus on different deep learning approaches (imitation learning, reinforcement learning) and architectures (modular, end-to-end) to achieve great autonomous behaviours.
As fans and active users of CARLA and AWS DeepRacer, we are continuously exploring their limits and possibilities, integrating them into our research to push the boundaries of what is achievable in autonomous driving technology. Through our efforts, we aim to contribute meaningful advancements to the field, paving the way for safer, more reliable autonomous vehicles.
What we do
Imitation Learning
End-to-end Route Navigation
Obstacle Avoidance
Reinfocement Learning
Speed Adaptation
What we use
CARLA
AWS Deep Racer
JetBOT/JetRACER
Publications
Model Optimization in Deep Learning Based Robot Control for Autonomous Driving
Sergio Paniego, Nikhil Paliwal, and José María Cañas
IEEE Robotics and Automation Letters 2024
RL-Studio: A Tool for Reinforcement Learning Methods in Robotics
Pedro Cabo, Rubén Lucas, Ignacio Arranz, and Sergio Paniego, José M. Cañas
ROBOT2022: Fifth Iberian Robotics Conference 2023
Memory based neural networks for end-to-end autonomous driving
Sergio Paniego, Sakshay Mahna, Utkarsh A. Mishra, and JoseMaria Canas
2022 Arxiv
Open Source Assessment of Deep Learning Visual Object Detection
Sergio Paniego, Vinay Sharma, and José María Cañas
Sensors 2022
Robust Real-Time Traffic Surveillance with Deep Learning
Jessica Fernández, José María Cañas, Vanessa Fernández, and Sergio Paniego
Computational Intelligence and Neuroscience 2021
Projects
GAIA: Gestión integral para la prevención, extinción y reforestación debido a incendios forestales
Proyectos de I+D en líneas estratégicas en colaboración entre organismos de investigación y difusión de conocimientos TRANSMISIONES 2023
01/01/2024-31/12/2026
Thesis
End-to-end vision based Autonomous Driving using Deep Learning
