Ramon Roche 🚀

And remember kids, loyalty and respect can't be bought.

We are exploring potential partnerships on bringing Skynode N and MAVLink-M support into air defense turrets / RWS for air defense. Are you interested in partnering with us bringing standards to defense? Send me an email to alliance [at] auterion / com diu.mil/work-with-us/s…

Nine Dronecode members on the floor at #XPO2026 in Detroit this week, plus our Board Chair @drlorenzmeier on the keynote stage Wed May 13 with DIU + Altana. Booth map, sessions, and the full rundown 👇 dronecode.org/dronecode-memb…

The MAVLink-M workgroup kickoff in Washington DC was a major success. Special thanks to @drlorenzmeier and the @auterion team for sponsoring the event and making it happen. Thanks also to everyone who made the trip out, and to our wonderful board directors. @mrpollo

@Dronecode’s Ramon Roche in Washington DC presenting open standards. We are bringing industry and end users together to create interoperability!

Great session with @soren_ma and Ramon Roche from @Dronecode discussion open payload and software standards.

@drlorenzmeier 👀

Stay tuned for a big announcement on MAVLink Military tomorrow!

🚁 Dronecode is forming a working group to steward MAVLink-M, with early collaboration from @auterion, @neros_tech, and @modal_ai. Kicking off May 7 in DC at Auterion Forge. See you there. dronecode.org/mavlink-m-work…

🎉The #ROS 2 Lyrical Luth beta just dropped! We've released the Lyrical illustration and our Lyrical swag store! Support the project and pick up a shirt! All proceeds go to support the non-profit Open Source Robotics Foundation and help pay for our build farm.

Lots of fun! Thanks for being an awesome host Alex!

Looking for a solution for GPS-denied UAV navigation? Mohamed Abdelkader, a professor at @PSU_RUH, just released a paper, source code, and a Docker container, complete with @GazeboSim and @PX4Autopilot integration, on the topic of terrain based navigation. ⬇️⬇️

Ubuntu 26.04 LTS, codenamed #ResoluteRaccoon, is now available to download. 🦝 Resolute Raccoon builds on the resilience-focused improvements introduced in interim releases, with TPM-backed full-disk encryption, improved support for application permission prompting, Livepatch updates for Arm-based servers, and Rust-based utilities for enhanced memory safety. This release also brings native support for industry-leading AI/ML toolkits like NVIDIA CUDA and AMD ROCm, making Ubuntu 26.04 LTS the ideal platform for AI development and production workloads. Install now: ubuntu.com/download/deskt… Learn more about the release: canonical.com/blog/canonical…

@alexklimaj @PX4Autopilot @NXP Can’t wait!

Prototypes of the ARKV6X-RT have arrived and are booting! Running @PX4Autopilot on the @NXP IMXRT1176.

The PX4 Dev Summit track at Open Source Summit NA is LIVE 🚀 2.5 days of talks + workshops from the teams building open source aerial robotics. 📍 Minneapolis, May 18-20 🎟️ More Info: osselcna2026.sched.com/type/PX4+Dev+S… #OSSummit #PX4DevSummit

Jasmeet will be joining us next Wednesday for our monthly @GazeboSim community meeting! If you would like to join us visit: luma.com/basc3xon

We need our open source community to help test the our next #ROS release, Lyrical Luth. 📅Join us for our annual Test and Tutorial Party on April 30th. 🫶Come meet our core team, test the next ROS release, support free and open source software, and earn free ROS swag! ⬇️⬇️⬇️

We are excited to share our #ICRA2026 paper "Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight"! Paper: rpg.ifi.uzh.ch/docs/ICRA26_Ro… Video: youtu.be/nctQ2rxZnIc Can we use Model-Based #ReinforcementLearning (MBRL) to fly a drone from pixels to commands? In this work, we train quadrotor navigation policies from scratch using #WorldModels, mapping raw onboard camera pixels directly to control commands, much like a human pilot! While model-free methods like PPO are sample-inefficient and struggle in this setting, we leverage #MBRL to train visuomotor policies capable of agile flight through a racetrack using only raw pixel observations, no explicit state estimation needed. A key finding: because our policies are trained end-to-end directly from pixels, we no longer need the perception-aware reward term used in previous methods. Instead, this behavior emerges naturally! The policies learn to guide the camera toward feature-rich areas of the observation space on their own. Kudos to @roaguiangel @ashwinshx @isgeles @EliJalbout Reference: "Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight" Angel Romero*, Ashwin Shenai*, Ismail Geles, Elie Aljalbout, Davide Scaramuzza IEEE International Conference on Robotics and Automation (ICRA), Vienna, 2026. @ERC_Research @AUTOASSESS_EU @uzh_ifi @UZH_en @UZH_Science @Prophesee_ai @SynSenseNeuro @UZHspacehub @swissrobotics @nccrrobotics

The best place to learn about drone autonomy in North America

Love to see the community contributing to Foxglove! Zalán Demeter built an extension that brings aircraft-style controls to Foxglove. If you are reviewing flight logs, check it out! To install it, go to Settings->Extensions, then find "Flight Indicators" and install it. Safe flying! #autonomy #RViz #robotics #ROS2 #PX4

Today in Weekly Robotics: 🤖 Drones in GPS-denied environments, 🤖 spline-based trajectory planning, 🤖 a fault-tolerant flight computer for Artemis II, 🤖 a new sensor-fusion library for ROS, and more! weeklyrobotics.com/weekly-robotic… #robotics