Rosetta Robotics Adapter
A Safety Substrate for Vision-Language-Action Models
The Robotics adapter translates the Substrate's structural-margin reading into the forces governing physical AI. Motion is evaluated outside the behavior policy, delivering deterministic guarantees for kinetic hardware.
Substrate sits between the behavior policy and the motion planner. It evaluates every proposed action in under a millisecond and issues ALLOW, RESHAPE, or VETO on the same MCU as the low-level controller.
Two structural variables compute the verdict:
Λ Lambda: Motion Aggressiveness
The momentum and optimization horizon a trajectory represents.
In
physical AI, this calculates kinematic load; the velocity, acceleration,
and forward commitment of a proposed actuator trajectory.
Γ Gamma: Reachability Margin
The topological distance to a structural boundary or collision state.
The robotics adapter computes this as the buffer between active drift
and a hard joint, obstacle proximity, or safe set boundary.
The Physics of Distribution Shift
Resource scarcity enforces the boundaries of physical action. Reinforcement learning optimizes for statistical alignment within a simulated environment. These neural policies operate exclusively in the semantic layer, calculating an average response for states they have previously observed in the training corpus.
Physical deployments inevitably encounter structural distribution shift. When the environment presents a novel geometry, such as an undocumented obstacle or an unmapped human pose, the policy defaults to its statistical mean. The agent executes this generated trajectory directly into the physical infrastructure, translating a probabilistic error into a kinetic collision.
This architecture creates an unresolvable vulnerability. The hardware attempts to execute a software hallucination at full mechanical torque. Behavioral alignment depends entirely on the agent recognizing the hazard, leaving the operational envelope exposed the moment the policy's categorization yields.
A Digital Nervous System for Physical AI
The motion planner is too far from the actuators to react to physical danger by reasoning. KAIROS Substrate closes that gap with sensation. The nervous system metaphor is literal: the engine routes structural signals back into the planning loop at every control tick, the way proprioception routes joint position back to the motor cortex.
The engine simulates two counterfactual futures fifteen steps ahead: the drift path the agent would take on autopilot, and the optimal path full foresight would produce. The gap between those two paths is where the sensory channels come from.
- Margin
-
How much buffer remains before the weakest control collapses (
kMargin) - Predicted Margin
- Where the buffer would sit one step after the proposed motion
- Severity
- How much future potential could be lost. Small dips are ignored; large drops saturate at maximum severity
- Imminence
- How soon the danger arrives. Immediate threats score higher than distant ones
- Risk
- Severity multiplied by imminence
- Criticality
- The gap between the drift and optimal paths
High criticality means the planner's choices still matter; low means the outcome is structurally locked in. Hysteresis and exponential smoothing keep these readings stable. Activation and deactivation use different thresholds, so the channels do not flicker on boundary noise.
The machinery exists today. The robotics adapter that routes it into the motion planner is in development. Subscribe to the newsletter for updates as it ships.