Viam

Viam is the software platform for building, deploying, and managing robotics applications.

[Viam @viamrobotics]

Salad-making. Wine-pouring. Coffee-brewing. Robotic dogs. Autonomous air hockey.

Our team spent 3 days building robots of all kinds just as easily as they build software, all on Viam. Check out the highlight reel to see what they built.

#robotics #buildonviam #physicalAI

[Viam @viamrobotics]

https://t.co/wb28nFwbH8

[Viam @viamrobotics]

RWD spins shouldn’t wreck your navigation stack. 🤖 📐

Look at how we use Viam’s Frame System to dynamically map extrinsic definitions and parent sensor frames right to a mobile chassis. The platform handles the sensor fusion math automatically, keeping SLAM maps predictable. 👇

[Viam @viamrobotics]

@openEuler centralized YAML for joints, controllers, and sensor extrinsics with seamless sim ↔ real switching is a great foundation!

Viam is a robotics platform that runs great on Linux distros like openEuler. Our Frame System complements tools like yours by handling dynamic 3D spatial transforms at runtime: declare parent/child relationships (e.g., LiDAR on a spinning base) once, and it automatically manages all the transforms, even as components move. No hardcoded math or constant recalcs.

Curious how you handle re-parenting or moving sensors today?

[Viam @viamrobotics]

@Iqbalmde You can align telemetry contextually at the resource level and only upload high-value edge cases—keeping the data loop clean. Here is how that edge-to-cloud plumbing works if you're interested: https://t.co/W5IBIDo2Xk

[Viam @viamrobotics]

Managing data ingestion across a distributed fleet is an incredibly tough infrastructure problem if you're just streaming raw logs to the cloud. Shifting the logic to the edge platform level allows for conditional syncing and edge filtering (a huge unlock we have built into Viam).

[Viam @viamrobotics]

Huge win when you can spend more time building, less time recalculating.

[Viam @viamrobotics]

Was talking with a #robotics engineer about the autonomous office cart he's building on Viam. Still in early phases, but very cool.

Heard how brutal manual sensor fusion is if you're running RWD 🛞 ; any spin completely wrecks your trigonometry.

[Viam @viamrobotics]

He used the Viam Frame System to parent the #LiDAR and camera to the base so the platform handles the transforms dynamically. Clean maps and (best of all) *no hardcoded math*.

[Viam @viamrobotics]

* SurfaceAI is a solution we built on Viam, a platform expressive enough to account for the variation inherent in any real manufacturing environment, *and* take in human oversight and input.

Operators, based on their experience and judgement, can direct the machine to focus on particular areas of a piece using a UI (no robotics PhD required). The robotic arms can execute and adjust as needed

[Viam @viamrobotics]

@oprydai When you treat the factory as a computational system rather than a series of belts, the robot finally becomes a teammate. We’re seeing this with our SurfaceAI system for industrial surface finishing (sanding, polishing, etc).

[Viam @viamrobotics]

Great point. We see it less as an either/or and more as a shift toward Software-Defined Scaling. An expressive platform still allows for the horizontal scalability of a fleet, whether it’s one station or a line of 20 coordinated arms. The software allows you to scale up volume without losing the agility to handle a high-mix floor.

[Viam @viamrobotics]

This is spot on. The 88% of US manufacturers without a robot aren't holding back because of hardware costs or generic fear of automation. They’re avoiding the ‘Agility Tax’ inherent in traditional automation.

[Jason Shuman @JasonrShuman]

I spent the last week in over a dozen pitches with robotics companies across Silicon Valley, NY and Europe...then I looked at the US Census Bureau Data

Turns out 88% of US manufacturing plants don't own a single robot...and that's the opportunity Founders are seeing.

Despite the endless deluge of humanoid robot demos and "AI factory" hype in our feeds, nearly 9 out of 10 American factories look exactly the same as they did 20 years ago.

Manual labor, mechanical machinery, a retiring workforce and challenges in filling roles.

The reasons why they haven't been "updated" historically breaks down into two clear buckets that I call:

1. The Integration Iceberg: A robot arm might cost $25,000 and has come down in price, but the custom tooling, safety cases and software integrations to make it work cost $125,000.

2. The Agility Tax: A traditional robot does one thing a million times. But the average US shop does "high-mix, low-volume" work. To reprogram a robot for a new part has required an expensive software engineer and could take days depending on engineer availability.

The next generation of massive robotics outcomes won't come from building shinier hardware for the 12% of factories that are already automated.

It will come from the Founders solving the integration and business model friction for the 88% that aren't.

If your GTM strategy doesn't solve the 18-month ROI math of a shop owner in Ohio who needs financing, fast onboarding and the ability for the robot to handle a variety of tasks, then you're likely going to struggle.

If you're working on a robotics business solving our countries biggest talent bottlenecks, I want to chat.

[Viam @viamrobotics]

We built SurfaceAI on our own expressive software platform so the robot can actually 'see' and adapt to the part where it sits. The automation is flexible enough to handle a high-mix floor without expensive re-programming, so the machine is an asset, not a drag on productivity.

[Viam @viamrobotics]

In industrial surface finishing as an example (sanding, spraying, polishing, etc), traditional robots fail if a part is even 1/2" out of place, or if the part doesn’t match the CAD model 100% 🙄 Requires so much time and precision that disrupts operations.

[Viam @viamrobotics]

@JohnVial e.g. we swapped between two industrial arms in our lab in the final 2min of this video

https://t.co/OlEEv9uqyJ

[Viam @viamrobotics]

Our approach is to treat hardware like LEGOs at the software level, too.

Using a platform like Viam means you can swap a $20 motor for a $200 or $2K one down the line, or add a new sensor to your config without rewriting your entire stack. Founders should be free to spend their time iterating based the user feedback and operating data, not on infrastructural plumbing.

[Viam @viamrobotics]

Our approach is to treat hardware like LEGOs at the software level, too.

Using a platform like Viam means you can swap a $20 motor for a $200 or $2K one down the line, or add a new sensor to your config without rewriting your entire stack. Founders should be free to spend their time iterating based the user feedback and operating data, not on infrastructural plumbing.

[Viam @viamrobotics]

@thearslaniqbal @KennethCassel We’ve built a robotic surface finishing solution that can take feature upgrades and fixes, all over the air. No technician traveling out to install anything. No depreciating machines taking space on the floor.

Appreciating hardware is the future.

[Viam @viamrobotics]

@thearslaniqbal @KennethCassel You have to be able to 1) solve a *real* problem they have (not shoehorning your tech onto their floor for the sake of it) and 2) demonstrate a willingness to iterate to get results. And your tech stack has to really support that. A brittle system built on macros won’t cut it.