The eyes of Embodied AI. Spatial AI cameras with onboard VIO/VSLAM, robot navigation & embodied AI data capture. Built for robotics developers.
Wan Chai, HK
Joined December 2025
- Tweets188
- Following25
- Followers418
- Likes32
LooperRobotics retweeted
🔥ROSCon Global 2026 — we made it, did YOU? 👀
Catch @DRoboticsDev at our partners’ booths:
📍 @AgilexRobotics Booth #48
📍 @LooperRobotics Booth SU-3 | Startup Alley
RDK, #ROS 2, #Robotics, #EmbodiedAI...— come talk to us, we're so ready 🤙
#ROSCon2026
LooperRobotics retweeted
We’re thrilled to announce that D-Robotics is a sponsor of ROSCon Global 2026. From ROS 2 applications to intelligent machines in the real world — D-Robotics is bringing RDK to @OpenRoboticsOrg #ROSCon Global 2026!
For us, ROS 2 is not an add-on — it is a core part of the RDK robotics development experience. Across the RDK platform, we support multiple ROS 2 distributions, while TogetheROS.Bot builds on ROS 2 with hardware-accelerated capabilities tailored for robotics.
At ROSCon, we’ll be showing how RDK dev kits + ROS 2 can help developers bring edge AI from the development environment to real robotic systems, with RDK providing the computing foundation to run AI workloads closer to the robot.
Find D-Robotics at our partners' booths ⬇️:
📍 AgileX Robotics Booth #48
📍 LooperRobotics Booth SU-3｜Startup Alley
And you can't miss our Lightning Talk by D-Robotics Engineer Shukun Huang
🎤 AI-Native + ROS: A New Paradigm for Robot Development
Got a ROS 2 project in the works? Bring your ideas, your questions, or even your toughest robotics problem. Come find us, say hi, and let’s build something interesting together.
See you in Toronto! en.d-robotics.cc/blog/d-robo…
LooperRobotics retweeted
The next evolution: VLA+ models
Just yesterday @MSFTResearch released Rho-alpha (ρα) – their first robotics model, built on the Phi family.
While most Vision-Language-Action (VLA) models stop at vision and language, Rho-alpha adds:
▪️ Tactile sensing to feel objects during manipulation
▪️ Online learning that lets it improve from human corrections (via teleoperation, 3D mouse or other tools) in real-time even after deployment.
Both these sides make adaptability central rather than incidental.
Microsoft calls it a VLA+ model, positioning it as an extension beyond what current VLA systems support.
➡️ Today Rho-alpha can control dual-arm robot setups to perform tasks such as:
• Manipulating the BusyBox following natural-language instructions
• Plug insertion
• Toolbox packing and object arrangement with bimanual coordination
But to understand why this "plus" matters, we need to understand what came before.
Here, we'll take you through the entire landscape of VLA models – Gemini Robotics, π0, SmolVLA, Helix, ACoT-VLA and others: turingpost.com/p/vlaplus