Dr. José Martinez-Carranza
Biography
Dr. Martinez-Carranza is a Full-Time Titular Researcher A (Associate Professor) in the Computer Science Department at the Instituto Nacional de Astrofísica, Óptica y Eletrónica (INAOE); and Honorary Senior Research Fellow at the University of Bristol in the UK. In 2012, he received his PhD from the University of Bristol, where he also worked as Postdoctoral Researcher (2012-2014). He received the highly prestigious Newton Advanced Fellowship (2015-2018), granted by the Royal Society in the UK, which funded his research on autonomous drones in GPS denied environments. He also leads a Mexican team that has achieved outstanding performance in International Drone Competitions: 1st Place in the IEEE IROS 2017 Autonomous Drone Racing competition; 2nd Place in the International Micro Air Vehicle competition (IMAV) 2016; best flight performance award in the IMAV 2019; and 3rd Place in the Tier 1 of the Game of Drones competition of NeurIPS 2019, organised by Microsoft and Stanford University. His team is the first Mexican team to win an International Autonomous Drone Competition.
Website: https://ccc.inaoep.mx/~carranza/
Twitter: @josemtzcarranza
Email: carranza [at] inaoep.mx
Intelligent drones that can see, hear and touch
In this talk, I will present some of the most relevant work that my group has developed related to “Intelligent drones”. This work has been strongly motivated by the classical problem in robotics, where a robotic system has to navigate autonomously in an unknown environment. For drones, this translates into the problem of autonomous flight in GPSdenied scenarios. The latter demands an alternative localisation mechanism in indoor or outdoor environments with the GPS signal prone to fail, to be blocked or compromised, such as in warehouses, urban canyons or the woods. Another motivation has been a series of competitions that have emerged in the last years, seeking to push the development of drones. Competitions such as the IEEE IROS Autonomous Drone Racing has posed the challenge of developing an autonomous drone capable of beating a human in a drone race. By addressing these challenges, we have come up with solutions to enable drones to take decisions autonomously. For that, we have explored different paradigms based on robotics, computer vision and machine learning. The latter has allowed us to develop drones that can navigate autonomously using a single camera to build a 3D map for localisation, to detect nearby drones by their sound, or even capable of touching a vertical surface without human intervention, among other examples that will be discussed during the presentation.