SHOW ROBOTICS

A new chapter for @vitanovashow While taking Vita out and recording some clips for the past weeks we’ve been learning a ton trying new tech and listening to what people want to see next We are feeling ready to take on a whole new frontier of robotics rebuilding her hardware from the ground up with way more real world capability and intelligent vision guiding her actions and navigation. To make this work we will start with a more gradually developing character that is simpler but more capable Excited to bring the build logs back soon. What are you most excited to see?

@CryptoKatze That's more like it 🤭

@SHOW_ROBOTICS Cookies 🍪😁

We might be cooking something 👀

@CryptoKatze B&E ain't degen enough I think

@SHOW_ROBOTICS Whatcha cooking 👀 Bacon and eggs?

@Mikebdbo Yep just maybe 😉

@SHOW_ROBOTICS maybe

Robotic season begins on @virtuals_io 🤖 Dropping a short @SHOW_ROBOTICS zap.

@nutcha_nj @0xNikos @virtuals_io Appreciate the support 🫡

@0xNikos @SHOW_ROBOTICS @virtuals_io this 💯 price goes up or down, we know they’re still there

my kind of robotics team @SHOW_ROBOTICS has been building for a year now and admittedly is one of the best projects to truly represent how @virtuals_io is supposed to be working, supporting builders and early stage teams.

First point cloud of @SHOW_ROBOTICS test area from the Intel RealSense depth sensor. Pretty solid already for visual odometry. Next step: adding a 360° LiDAR, so we can fuse it in and get very precise time-of-flight odometry for mapping.

We’re not trying to control a robot. We’re setting up an environment where an embodied agent can learn continuously and develop its own behavior over time. If anything like companionship is possible, it has to emerge, not be forced. We’re explicitly not training a polite, subordinated assistant. “Useful” shouldn’t mean constant attention or obedience. If it chooses to spend days mapping its world, studying patterns, or obsessing over something mundane, that’s a feature not a bug. If this resonates: we’d love your thoughts. What experiment designs, constraints, or “emergence-friendly” approaches would you try? Reply with ideas / papers / critiques.

We’re entering a new phase of the project. The platform is getting ready for deployment. We’ve finalized @showrobotics test area, added live A/V displays for system status and navigation visualizations, completed floor markings and the outdoor access ramp, brought the control room online, finished wiring the rig, and installed fire alarms and extinguishers across the facility. Next step: an autonomous docking station for continuous charging. Why this matters: The embodied agent will soon start roaming freely across the entire facility, indoors and outdoors, operating continuously. This marks the beginning of our first real experiments in continual learning. We’re deliberately starting with a very simple, open exploration policy. No strong rewards. No predefined objectives. Just minimal nudges and maximum autonomy. Our hypothesis is that, over time, this setup will lead to emergent behaviors and allow the agent’s character to evolve through sustained interaction with the real world, rather than task optimization. Learning, here, is not episodic. It’s continuous, grounded, and unconstrained in time.

@SHOW_ROBOTICS is entering the next phase. We’re expanding with a dedicated test area and a full control room. 🤖

Over the past few days, we’ve been running a series of experiments across hardware, perception, and cognition layers: - Integrated a main battery disconnect and replaced driver fuses with resettable breakers, improving fault isolation and rapid maintenance. - Finalized auto-tracking (“follow me”) behavior, now extended with speech commands using voice direction-of-arrival (DOA) for spatial interaction. - Validated Dynamixel servo identification, closed-loop calibration, and inverse kinematics on a 3D-printed manipulator prototype. - Designed and prototyped a protective bumper for the depth-sensing stack. - Evaluated LiDAR architectures and identified the Unitree 4D LiDAR L2 as a strong candidate for dense, dynamic perception. - Initiated a design language exploration focused on machines as machines, functional, legible, and expressive through structure. - Began deeper discussions on continuous and in-context learning, examining reward structures, goal formation, emergence, and ethical boundaries.

🎄 Special Christmas update from @SHOW_ROBOTICS workshop Happy Christmas 🎅

@CryptoKatze @VitaNovaShow @metrox_eth Ho ho ho 💜

Ho Ho Ho Ho 🎅 It's $SHOW time for Vita! Merry $VIRTUAL and a happy Christmas @VitaNovaShow You've grown so much this year with the @SHOW_ROBOTICS team Everyday we are seeing you grow and now your legs are coming together with @metrox_eth's help! Soon you will be driving around talking to the people in Thailand and livestreaming your adventures. Looking forward to your next evolution! Yours Truly, Virtuals Villageman

Update #20 from @SHOW_ROBOTICS workshop Hard to believe we’ve already reached update #20. I started these daily updates as a replacement for Notion build logs when we began working on locomotion. Thanks to everyone who believed early and for all the thoughtful comments. I can’t tag everyone, but the community is growing every day. As for the update, today I've finally finished the main path cement work. In just one month of locomotion work, we’ve achieved: ✅ Sourced all parts from overseas and local suppliers in just 5 days ✅ Tested three different wheel types and configurations ✅ Built a full holonomic motion platform with perception ✅ Built access ramps outside the workshop ✅ Poured concrete paths for navigation and mapping experiments No worries if there are no updates for the next couple of days. I’m thinking about a new format for what comes next.

30 days of iteration on mobility

Update #19 from @SHOW_ROBOTICS workshop

@metrox_eth 🦾👏

Update #18 from @SHOW_ROBOTICS workshop Very productive day. I added struts between the wheel reinforcements; they serve two purposes: preventing the wheels from bending under the payload’s weight, and forming the gantry for the undercarriage, which now houses the battery. All aluminium profiles have been closed with custom 3D-printed end caps. A laser-cut top plate was added to mount the electronics. Last but not least, the sensor mast is now proudly holding the RealSense depth camera.

Update #17 from @SHOW_ROBOTICS workshop Work on the suspension is finally finished. I had to reinforce it and make sure everything was properly squared. Same for the frame. What looked like a couple of hours of work ended up being a complete teardown, taking the whole day and being pretty intense. Countless holes to drill, threads to cut, adjustments to make, and a lot of precise grinding. But we’re finally there. Tomorrow: sensor mast, undercarriage and battery holder, then putting all the electronics back on.