About

Small, senior, Aarhus

A small, senior studio in Aarhus building perception and control systems for machines that have to read the physical world in real time.

The studio

  • Aarhus Based in
  • 2023 Founded
  • Perception → production Focus

Dōjutsu is a small studio. Everyone here has shipped systems that run on real hardware, and that shapes how we work. We stay deliberately senior and deliberately small, so the people who scope a project are the people who build it.

Half of us come from machine-learning research, half from the factory floor, and most projects stall in the gap between them. A model that scores well on a benchmark is not the same as a system that holds up across a shift, in changing light, on hardware that has to earn its place in a budget. Closing that gap is the work.

We are based in Aarhus and work with manufacturers and robotics teams across the Nordics and Europe. The approach is functionalist by temperament. Measure before you claim, say plainly what you are unsure about, and ship something that keeps running after we leave.

Principles

What we hold to

Measure, then claim

We quantify before we describe. Latency, accuracy, false-reject rates, drift over time. Numbers you can check, taken on your data and your hardware, not a vendor's slide.

Honest about uncertainty

Every perception system has an operating envelope and a failure mode. We tell you where ours sits and where it breaks, so you can plan around the edges instead of discovering them in production.

Built to ship

Research that never leaves a notebook is not finished work. We design for the target hardware from the first week, packaging, telemetry, and regression tests included, so the system survives contact with the real world.

Restraint

The simplest design that meets the spec is the one we keep. We add a sensor, a model, or a dependency only when it earns its cost in reliability or maintenance.

Engagement

From scope to handover

  1. 01

    Scope

    We start with your constraints, on site where it matters, the environment, the optics, the latency budget, and the people who will own the system. We define what good enough means in numbers before any code is written.

  2. 02

    Prototype

    We build the smallest version that can prove or kill the idea, measured against real data from your line. You see results early, and you can stop early if the numbers do not hold.

  3. 03

    Harden

    We move from a working prototype to a system that runs unattended. Edge deployment, observability, defined fallback behaviour, and tests that catch regressions before the fleet does.

  4. 04

    Handover

    We document what we built and why, then hand it to your team with the tooling to maintain it. We stay reachable for the questions that surface after go-live.

Bring us the hard part

Tell us what the machine needs to see.

Share your environment, sensors, and what “good” looks like. We’ll tell you what is buildable, what is not, and where we would start.

[email protected]