←
Zeon Systems51 posts
Zeon Systems avatar

Zeon Systems

@zeonsystems

Accelerating science with AI-powered lab robots.

◷ Joined April 2025▧ 16 Photos and videos
Zeon Systems avatar
Zeon Systems@zeonsystems·Mar 3

AI is writing papers. Scientists are still loading centrifuges. We have built a perception, control, and manipulation stack that lets robots run experiments flexibly in scientific labs. We exist to expand the boundary of what is possible to automate today. Over the next week, we’ll share deeper dives into how our world models, mesh systems, motion planning, and LLM agents come together to make it possible. Centrifuges are everywhere in science - and a nightmare for automation. Here’s a quick preview of our system loading tubes into one.

0:39
Brontë Kolar avatar
⟳ Zeon Systems retweeted
Brontë Kolar@BronteKolar·Jul 31

0 to real experimental data in <24 hours. Not a robot demo. Real scientific results. Hackathon teams did this on the Zeon stack: - designed TEM-1 inhibitor screens with coding agents - previewed them in simulation - ran them on robots and found real hits We had never run these workflows before on our system. This is the whole point - scientists and engineers turning an idea into data in days.

Post attachmentPost attachmentPost attachment
Brontë Kolar avatar
⟳ Zeon Systems retweeted
Brontë Kolar@BronteKolar·Jul 31

I believe the first-ever run of a robotic arm autonomously unsealing a wellplate happened this weekend at our hackathon. The legendary Tacit Teacher team (Erik Brinsmead, Taras Nazarov, Tuan Tran, Sasha Denisin) built this in <24h on the Zeon Systems stack

0:27
Zeon Systems avatar
Zeon Systems@zeonsystems·Jul 26

Day 2 is down to the final sprint ⏳ After a few hours of sleep, teams are pushing their builds across the finish line. Who’s taking the win?

0:31
Zeon Systems avatar
Zeon Systems@zeonsystems·Jul 26

You do not need to be a roboticist to build with robots 🦾 Our hackathon participants are getting hands-on with the Zeon stack, using our software and robots to turn their ideas into scientific workflows. #AIforScience

0:27
Zeon Systems avatar
Zeon Systems@zeonsystems·Jul 25

The AI Science World Model Hackathon is officially underway at Zeon Systems 🤖🧪 Over the next two days, scientists and engineers will team up to build AI systems that can plan experiments, control robots and interact with real lab equipment. Let the building begin. #AIforScience

0:29
Zeon Systems avatar
Zeon Systems@zeonsystems·Apr 1

1/ Write a skill - a reusable robot capability built from low-level primitives that an agent or human can use. Think "pick up an object" or "open a machine" 2/ Compose skills into a workflow. Preview it in simulation before anything touches real hardware. 3/ When it looks right, run it. Our live localization means the workflow works even if objects move - no re-programming if your vortexer shifts position. Engineers/Agents keep full control. Skills, workflows, and world models are all based on Python. Inspect them, modify them, reuse them across experiments. You build a library, not a pile of one-off scripts.

Zeon Systems avatar
Zeon Systems@zeonsystems·Apr 1

Agents can now run real lab workflows. We taught a robot to vortex a rack of tubes in minutes - from natural language. Flexible to write, deterministic to run. build modular skills → compose workflows → simulate → deploy Here's how it works🧵

1:02
Zeon Systems avatar
Zeon Systems@zeonsystems·Mar 17

MOTION PLANNING Because the simulation stays synchronized with reality, robots can safely plan complex motions around real equipment and objects. Dodging shelves, hopping over machines, avoiding each other. Both arms reason about the same live scene and can move simultaneously for higher throughput. This enables coordinated manipulation of lab equipment - opening machines, moving plates, handling tubes, etc.

0:08
Zeon Systems avatar
Zeon Systems@zeonsystems·Mar 17

TRACKING SCIENTIFIC STATE Workflows depend on knowing where samples are and what has happened to them. Tubes, plates, and reagents are persistent entities in the system. When they move between instruments or their contents change, their state updates in the simulated world. This gives the system context on the current state of the lab, allowing workflows to execute reliably. There’s still a long way to go in capturing the full scientific state, but this layer is critical for lab robotics.

0:17
Zeon Systems avatar
Zeon Systems@zeonsystems·Mar 17

TRACKING PHYSICAL STATE Lab machines constantly change geometry: • centrifuge lids open • instrument doors move • trays slide in and out We don't just annotate objects, we model joints, rotors, and doors. Then our parallelized localization algorithms continuously track these moving components in the real world. The simulation always reflects the current configuration of the lab (down to a moving lid) so motion planning stays safe and reliable.

0:09
Zeon Systems avatar
Zeon Systems@zeonsystems·Mar 17

Robots fail in labs for a simple reason: the world keeps changing. Previously we showed how we build world models of scientific labs from scans of the real environment. But a one-time snapshot isn’t enough. In real labs, machines change state (open/closed, loaded/unloaded), tubes and plates move between instruments, and samples transfer between containers. So we maintain a live representation of the lab - continuously updating both the geometry and the scientific state of the system. This lets robots operate reliably even as the lab changes around them. It enables three core capabilities: 1) Tracking physical state – moving machine components (like lids or doors) are continuously localized. 2) Tracking scientific state – tubes, plates, and samples persist as entities whose state updates as the robots run. 3) Motion planning – robots plan safe dual-arm actions directly in the live world model. Check these all out below 🧵

0:05
Zeon Systems avatar
Zeon Systems@zeonsystems·Mar 11

Simulated lab worlds straight from pixels. We scan the lab scene with depth cameras and reconstruct the environment. Each object already has a high-quality mesh in our object library from our mesh scanning system. A localization pipeline places those meshes into a shared coordinate frame, creating a digital version of the lab. This works well for science automation because the environment is constrained: the set of objects is limited, we have accurate models of them, and we don’t need to solve the full open-world perception problem. With this digital lab in place we can: • Drive safe motion planning around real geometry • Track state changes by re-localizing mesh parts (e.g. a lid opening) • Attach objects to the robot when picked so the planner accounts for them and avoids collisions built by @BastotdeHeijden @BlerimAbdullai @TahirMello

0:21
Zeon Systems avatar
Zeon Systems@zeonsystems·Mar 5

You need sub-millimeter precision to automate scientific labs. Calibration is crucial to achieving this. It resolves exactly where cameras and robot arms are with respect to the world and to each other. We have put a lot of work into robust camera and arm calibration so our system understands its environment precisely. Below we show a simple task: inserting a microcentrifuge tube into a tube rack. With proper calibration, inserting into these holes goes from impossible to achievable. - cc @BlerimAbdullai and @BastotdeHeijden for leading this work

0:26