YumaniqYumaniq
Yumaniq

Motor Intelligence Infrastructure for Physical AI

We build the execution layer that makes physical AI systems actually work, across changing environments, with safety guarantees, personalized to each user.

Under the hood: state-aware control, objective inference from expert behavior, and hard safety limits, so systems keep working when the body, environment, or dynamics change.

The Problem

Physical AI has a transfer problem

Physical AI can look impressive in a controlled setting, until the dynamics change.

Different bodies. Different environments. Different constraints. Small shifts in dynamics create big failures.

The gap is not more AI. It is the missing execution layer: a system that adapts actions in real time to the dynamics that actually exist, while staying safe and auditable.

The Product

RAST, the execution layer

RAST is a software stack that runs alongside an existing control system. It converts expert demonstrations into a compact intent package, then computes actions continuously from live state while enforcing hard safety limits.

Intent Studio

Offline tooling that infers the motor objective behind expert behavior from demonstrations, and exports a deployable intent package.

RAST Runtime

On-device execution that recomputes actions from live state and intent, staying aligned as operating conditions shift instead of replaying a brittle policy.

Safety Guardian

Deterministic constraint enforcement. Clamps unsafe actions, monitors execution, and produces audit logs for safety-critical use.

Not a policy library. A state aware execution loop with hard constraint projection.

Solutions

One engine. Four ways conditions change.

Health and Rehabilitation

When the body changes after cardiac events, surgery, or neurological injury, rehabilitation means learning to move within new physical constraints. Generic protocols ignore the motor strategy each patient already has. RAST extracts individual movement priorities and guides progression that respects them: objective baselines, dose-aware targets, and safety limits enforced in the loop. The therapist stays in charge. The dosing gets precise.

Driver Safety and ADAS

When the situation changes, a pedestrian steps out, traction breaks, reaction time compresses. Your driving strategy faces conditions it wasn't practiced for. RAST models the motor strategy behind normal driving and infers how each driver balances precision, reaction, and risk. That profile can inform predictive safety systems and personalize ADAS response to how you actually drive, not a population average.

Robotics and Teleoperation

When the physics change, policies trained in one environment fail in another. Different gravity, communication latency, unfamiliar actuators. RAST captures expert motor intent on Earth and re-optimizes for target conditions. No retraining. No million-episode simulation. The operator's strategy transfers; the robot computes locally within explicit safety bounds.

Music and Expression

When the environment changes, from practice room to stage, from studio control to live response, musical performance demands the same intent under different physical and acoustic conditions. RAST captures the motor signature of musical expression: how you shape pitch, dynamics, and rhythm. Not what you played, but how you meant it.

Technology

State-aware control, in the loop

  • State-aware action computation: actions are computed continuously from live state, not selected from a static script.
  • Objective inference from experts: infer what experts optimize for, not only what they did.
  • Minimal-change corrections: adjust only what matters to the task, preserve the rest of the natural strategy.
  • Hard safety limits: bounds enforced in the loop with auditability and predictable behavior.

We do not claim magic. We engineer the bridge from mathematical movement models to deployable systems.

Team

Team

Founding team
Nitsan Sharon
Founder and CEO

I have spent decades building high-reliability systems where correctness and operational reality matter. Today I apply that mindset to Physical AI, turning rigorous movement science into software that can run in the loop, safely and measurably, in the real world.

Tomer Sela
Chief Scientist

I am an MSc in Autonomous System and Robotics from the Technion, focused on Deep RL and Control Theory in Complex environments. I bridge scientific rigor with practical implementation, drawing on R&D experience at Rafael and The Technion advanced robotic lab.

Research collaborations
  • Technion BCI Lab - validation of motor intelligence inference
  • Clinical partner in Israel - first deployment focus in a Cardiac Rehabilitation Center, with outcomes measurement
Contact

Contact

If you are building a system where intent meets dynamics - robotics, rehab, or safety-critical automation - let's talk about deployment paths and pilot design.

info@yumaniq.com