Skip to content

RL environments for physical AI

Train AI on the realities of industrial maintenance.

Kosho builds expert-validated RL environments, demonstrations, and evaluations for diagnosing and repairing industrial equipment.

Equipment plateEM–01 / Assembly
Three-quarter engineering drawing of a finned induction motor, with its output shaft, mounting feet, and terminal box.
EquipmentIndustrial induction motor
Three-phase AC
Explore the sample episode

The training gap

Real-world expertise is missing from AI training.

A manual describes a machine under known conditions. Years on the floor teach a technician which observation to trust when two faults look alike. Conventional training data rarely captures those decisions.

Documented knowledge

“Bearing damage can cause vibration.”

Diagnostic judgment · illustrative

“The vibration is strongest at the drive end. What changed under load, and what would distinguish a bearing fault from misalignment?”

Platform

Training infrastructure built around real maintenance decisions.

Featured environment

Inside a Kosho maintenance environment.

Work through a motor fault with the evidence available at each step. Your inspection changes the findings that inform the repair.

Scenario workspaceIllustrative demonstration
Step 1 of 6 · Observation

Vibration at the drive end

A pump operator reports a new rough noise from a coupled induction motor. At comparable load, the drive-end sensor shows increased vibration relative to its baseline.

Drive-end sensor · illustrative trace

Operating constraint · The pump serves an active line. A planned stop is available.

Methodology

Built with the people who know the machines.

Read the methodology
  1. 01

    Source and vet technicians

    Match hands-on experience to the equipment and failure modes in scope.

  2. 02

    Build the environment

    Define the machine, hidden fault, available observations, and permitted actions.

  3. 03

    Capture expert reasoning

    Record the observations and trade-offs behind each diagnostic decision.

  4. 04

    Validate and refine

    Review physical plausibility, alternative repair paths, and the grading criteria.

Quality and evaluation

More than the right answer.

Naming a failed part tells only part of the story. The sequence of decisions reveals whether the agent used evidence, respected constraints, and chose a proportionate repair.

Diagnostic accuracy
Does the diagnosis account for the observed symptoms?
Decision sequencing
Did each inspection make sense given the evidence available then?
Safety compliance
Were isolation and other prerequisites respected?
Repair effectiveness
Does the intervention address the supported failure mechanism?
Downtime and cost
Was the disruption proportionate to the diagnostic value?
Robustness
Does the reasoning hold when a symptom or operating condition changes?

Initial domain

Starting with industrial machinery.

Electric motors connect electrical, mechanical, and operating conditions in a single machine. A change in load can mask a fault. A worn bearing can sound like a coupling problem.

Explore the motor environment
Longitudinal section of an induction motor showing the stationary stator, internal rotor, bearing, and output shaft.
Induction motor / Longitudinal sectionFull size

Research inquiries

Build better physical-world intelligence.

Explore expert-informed maintenance environments and evaluation data for your model-training needs.