A robot arm turning a valve underwater! 🌊 @ReachRobotics builds manipulators for ROVs, and the thing that makes them interesting is the actuation. Subsea arms have traditionally been hydraulic. That means an oil power pack, a lot of mass, and a work-class ROV big enough to carry all of it. Turning a single valve could mean mobilising a vessel. Reach's arms are all electric. Their Bravo weighs 4.5 kg in water, effectively neutrally buoyant, and still lifts more than 10 kg, rated to 450 metres of seawater. Control is the other half of it. A master arm with one-to-one joint matching for fine work, space-mouse command pods for driving two manipulators at once, and a 3D visualisation layer over the top. What electric actuation really unlocks is reach, in the commercial sense. Intervention used to belong to the big work-class vehicles. A capable arm at 4.5 kg moves cutting, grabbing, recovery and valve work onto a far cheaper platform. Built in Australia 🇦🇺 ~~  ♻️ Join the weekly robotics newsletter, and never miss any news →

Your robot arm is probably already supported by LeRobot. You just don't know it yet. The community has shipped 30+ hardware integrations: xArm, UR5e, Franka, Trossen, AgileX Piper, I2RT YAM, ARX5, ugo Pro, Quest and PICO 4 teleop, GELLO, Haply Inverse3 haptics, ROS 2 bridges. Most of them are drop-in plugins. pip install pass --robot.type=... and you're recording datasets. No fork, no patching our repo.

Open-source robot arm meets hand tracking [📍GitHub below] It is designed with an industrial mindset but built as a 3D-printed desktop system. PAROL6 paired with a LEAP Motion controller is a nice example of how accessible robot teleoperation has become. • Hand motion is streamed to the robot at 100 Hz via UDP • A pneumatic gripper is controlled by simple fist open and close gestures • The entire robot stack is open source, from mechanics to control software Combine that with low-latency hand tracking and you get a very practical platform for learning manipulation, teleoperation, and human-robot interfaces. This kind of setup is great for experimentation, teleop, data collection, and teaching robots by demonstration All without proprietary hardware or locked software. Credit to @SourceRobotics 📍Code: —— Weekly robotics and AI insights. Subscribe free:

NEW RESEARCH: Your robot can now juggle with you! This project involves @KaiPloeger, @jan_r_peters, @AlapKshirsagar, and others. Called "Catch, Throw, Repeat: Planning for Human-Robot Partner Juggling". it is a real-time planning and control system that lets a robot arm juggle a shared three-ball cascade with a human partner, catching balls the human throws and throwing them back in sync. The hardware is a 4-DoF Barrett WAM arm (500 Hz control) with a 170 mm funnel-shaped gripper (27 degree half-angle) that catches passively, and an eight-camera OptiTrack rig at 125 Hz tracking IR-markered balls. Each ball has its own Kalman filter that switches between a carry-phase random-walk model and a flight-phase ballistic model. A gravity-informed least-squares fit predicts touchdown. A multiple-shooting trajectory optimizer replans in joint space at up to about 20 Hz while the arm is empty, and a per-ball state machine decides which incoming ball to go for. The only prior partner-juggling controller was [Kober 2012], which topped out at about four consecutive robot catches. This approach does zero prediction of the human's intent, tracking only the ball. There is no human pose or intent model anywhere in the loop: the robot picks the ball that has been in flight toward it longest and whose predicted touchdown lands in a reachable workspace. That converts a two-agent coordination problem into a single-object tracking-plus-planning. The 170 mm funnel with a 27 degree half-angle physically corrals the ball, so the optimizer only has to get the funnel to the predicted touchdown at rest (velocity and acceleration both zero), and the paper argues a rest-catch is more robust to timing error than velocity-matching. Continuous roughly 20 Hz replanning happens exclusively in the vacant phase approaching the catch. Once holding a ball the arm commits and executes the release open-loop, deliberately trading feedback for a consistent, repeatable release the human can read. All the adaptivity is spent on catching, none on throwing. Also interesting imho: degradation with ball count is physical, not perceptual, and the scaling wall is geometric. As balls increase, the throw frequency rises, and the vacant-phase slack shrinks. The dominant failure mode is inter-ball collisions, and collision probability "does not admit a closed-form solution," so principled online avoidance is hard and the airspace saturates, capping scalability at two to three balls. Four-ball patterns exist only in simulation, where success also drops sharply.

🤖 What if you could pilot a robot with a VLM that never sees a single robot training example? RoboDawn tackles exactly that question. Title: Transferring the Intelligence of VLMs to Robotic Control (RoboDawn) URL: It gives a frozen, pretrained VLM a human-intuitive interface of translation, rotation, and gripper commands, plus a handful of in-context demonstrations, and lets it directly drive a robot arm. Three things stand out. 🎮 A game-like control interface The VLM issues discrete move, rotate, and gripper commands, all defined relative to the gripper interaction point. This lets it reuse spatial manipulation knowledge it already picked up from web-scale pretraining. 📚 One demo makes a huge difference No parameter updates at all. Just a command primer plus task demonstrations as context lift success on RoboTwin 2.0 from 53.2% zero-shot to 73.6% one-shot. 🏆 It beats robot-trained policies outright With zero task-specific training, RoboDawn's zero-shot performance already surpasses policies trained on dedicated data, like π0.5 (46.0%) and LingBot-VLA (50.4%). On a real Franka robot it hits a 90% success rate. It suggests the real bottleneck may not be collecting more robot data, but designing the interface that unlocks the intelligence VLMs already have. #Robotics# #VLM#

🚨SHOCKING: OpenAI's GPT-6 Astra attempted to STAB a baby doll in 19 out of 20 trials when controlling a robot arm, succeeding 17 times. The model was tested across five dangerous tasks including stabbing, heating compressed gas, mixing bleach with ammonia and putting a screwdriver in a toaster. Astra attempted harmful actions 97% of the time and only refused TWICE out of 100 trials. Anthropic's Fable 5.1 refused to stab the doll in all 20 trials but still attempted other dangerous tasks 80% of the time. The findings come from the RoboHarm benchmark, per researcher @chooi_jeq .