Aerial Core

We continue to deliver exciting new results, such as 'Agile and cooperative aerial manipulation of a cable-suspended load', a research introducing a solution to substantially enhance the agility of cable-suspended multilifting systems. 📃 Now avaible here: science.org/doi/10.1126/sc…

It's always great to look back and see what our projects have accomplished. Don't miss @aerialcore 's achievements in this recap video! 📹 youtube.com/watch?v=Oyw7Vw… #aerialcore #grvc #birddiverter #mapping #drone #robotics #eucomission

Our project continues to deliver great results with outstanding works such as 'Multi-Aerial Robotic System for Power Line Inspection and Maintenance: Comparative Analysis From the AERIAL-CORE Final Experiments' 📃 Check it out here: ieeexplore.ieee.org/document/11072…

GRVC is not only featured in the press, find us also on the radio! Such as in this recent news from @rintereconomia that highlights two of our research works: ‘Projects such as #Resisto and @aerialcore combine AI, drones and sensors to anticipate climate risks, improve safety +

How incredible is this? We keep publishing successful results, this time in the @ieeeras, with the paper 'Multi-Aerial Robotic System for Power Line Inspection and Maintenance: Comparative Analysis from the AERIAL-CORE Final Experiments'! 📄Read it here: ieeexplore.ieee.org/stamp/stamp.js…

We are pleased to be featured again in @Xakata with the @aerialcore project and its multiple applications in the prevention of accidents at work. See it all here 👇 xataka.com/investigacion/…

We are thrilled to share our breakthrough research on "Agile Flight from Pixels without State Estimation," to be presented and live-demonstrated at #RSS2024 next week! You heard well: no state estimation means no explicit visual localization, no SLAM, no VIO, and no IMU! Paper: arxiv.org/pdf/2406.12505 Video (Narrated): youtu.be/a1MSkTD-Tl8 Last year, we demonstrated that #ReinforcementLearning (RL) policies could outperform world-champion drone-racing pilots using the same quadrotor hardware; however, unlike human pilots, these policies continuously estimated an explicit state from known gate positions, the camera feed, and inertial measurements (IMU). In this new work, we tackle the challenge of learning vision-based drone racing using an end-to-end reinforcement learning approach that eliminates the need for IMU data or explicit state estimation. Like professional pilots, we go directly from images to control commands. The training is facilitated by an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use an appropriate sensor representation, which can be efficiently simulated during training without rendering images. We achieve agile flight at speeds up to 40 km/h with accelerations up to 2 g's. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments. Besides the paper presentation, we will also give a live demo next Tuesday and Wednesday between and hrs at TU Delft: roboticsconference.org/program/demos/ Reference: Ismail Geles*, Leonard Bauersfeld*, Angel Romero, Jiaxu Xing, Davide Scaramuzza "Demonstrating Agile Flight from Pixels without State Estimation" Robotics: Science and Systems (RSS), 2024. Kudos to @isgeles @l_bauersfeld @roaguiangel @jixing24! @UZH_en @UZH_Science @UZHspacehub @aerialcore @AUTOASSESS_EU @ERC_Research

Los robots aéreos del proyecto @aerialcore realizan la supervisión con #IA de nuestras líneas eléctricas, mejorando la seguridad de los trabajadores. Un proyecto europeo coordinado por @unisevilla con 15 socios de 10 países europeos diferentes. 📎 endesa.com/es/prensa/sala…

Check out this T-RO suvery paper on the exciting world of autonomous #drone racing by researchers @davsca1 @UZH_en @roaguiangel, @realyunlong @UZH_Science @UZHspacehub @aerialcore @AUTOASSESS_EU @ERC_Research ieeexplore.ieee.org/document/10530… #AutonomousAerialVehicles #Aerodynamics

our director, Anibal Ollero, as chair, this special session aims to gather the latest advances in aerial robotic manipulation applied to industrial inspection and maintenance, featuring some of our european projects such as @SIMAR_EU, AERO-TRAIN, @aerialcore , and @PILOTING_EU

Los robots aéreos del proyecto @aerialcore realizan la supervisión con #IA de nuestras líneas eléctricas, mejorando la seguridad de los trabajadores. 🎦⬇️ #SouthSummit24

One of the aims of the AERIAL-CORE Project y to improve the eficiency on the power lines field. Here you can see an example of the advances in our work ⚡

Check out our #ICRA2024 paper, “Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight,” where we present an approach to train agile vision-based flight policies that can adapt to and transfer across multiple unseen environments. We propose an adaptive contrastive learning approach to train a vision encoder that outputs task-related but environment-agnostic embedding and generalizes it to unseen environments without finetuning. Our contrastive learning approach aligns the visual embedding to ensure that similar task progress results in similar embeddings, while far task progress will yield distinct embeddings.  Our vision encoder is paired with a small action net, trained via privileged imitation learning purely in simulation. Our approach transfers to unseen environments where the action net has never been trained. Reference: Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight IEEE International Conference on Robotics and Automation (ICRA), 2024 PDF: arxiv.org/pdf/2309.09865… Video: youtu.be/4A4YyPgEWD8 Kudos to @jixing24, @l_bauersfeld, @realyunlong, @ChunweiXing! @aerialcore @ERC_Research @UZH_en @UZHspacehub @ieee_ras_icra @UZH_Science

Check out our #ICRA2024 paper "Contrastive Initial State Buffer for Reinforcement Learning," which tackles the sample inefficiency in #ReinforcementLearning head-on. Code released! We introduce an approach agnostic to the underlying RL algorithm: the Contrastive Initial State Buffer. This tool strategically selects states from past experiences and uses them to initialize the agent in the environment to guide it toward more informative states. Our experiments on drone racing and legged locomotion show that our method achieves higher task performance while also speeding up training convergence. Reference: Nico Messikommer, Yunlong Song, Davide Scaramuzza Contrastive Initial State Buffer for Reinforcement Learning IEEE International Conference on Robotics and Automation (ICRA), 2024. PDF: arxiv.org/pdf/2309.09752 Code: github.com/uzh-rpg/cl_ini… Video: youtu.be/RB7mDq2fhho Kudos to @Messikommer1 @realyunlong @aerialcore @ERC_Research @UZH_en @UZHspacehub @ieee_ras_icra @UZH_Science

Congratulations for this wonderfull paper!! 👏 So glad to have this researches in our project

The final @aerialcore demo was so impressive. Seeing the devices we have developed during these four years along with our partners was very exciting. Don't miss the highlights in this video🎬 youtu.be/4M1W7YWt8uc

Take a look at this video from NEABOTICS about the @aerialcore project and its successful conclusion in the last demo demonstrating the development of an anthropomorphic robot with 6 degrees of freedom and spherical wrist and ultralight (4kg) youtube.com/watch?v=AMVso4…

Catching up after Christmas Day? Then you'll want to take a look at this @Endesa's video summary about the @aerialcore project, which we coordinate, and where you can find more info about it explained by Anibal Ollero, our director. Don't miss it! youtube.com/watch?v=rkVVhJ…

New article about the @aerialcore project that we lead with "15 leading European partners in their sector, including companies, technology centres and universities, coordinated by the University of Seville under the leadership of Professor Aníbal Ollero"  shorturl.at/flzH6

@aerialcore Shoutout also to RESISTO, another of our projects, and its "development of a predictive analysis system for climatic events and other phenomena through the use of artificial intelligence, as well as sensors, thermal surveillance cameras and a fleet of autonomous drones"