Deploy the Safety Core
Once AI Perception is up and running, events are being generated from the input camera streams. The Safety Core converts those events into actionable signals: it judges whether the perception inputs can be trusted, fuses the events that describe the same situation, and turns the result into control actions for field devices.
This page introduces the Safety Core components. The steps to deploy them are in the Deployment Guide.
Components
Safety AI Monitor
The Safety AI Monitor (SAIM) continuously assesses the health of the camera sensor inputs feeding NVIDIA Halos Outside-In Safety Blueprint (HOISA).
It independently observes the same RTSP streams consumed by the AI Perception pipeline and scores every decoded frame against a per-sensor baseline of frame-quality metrics learned during an initial calibration phase.
When a stream degrades — for example, due to out-of-distribution frames, camera blockage or fogging, RTSP transport loss, or stream corruption — SAIM publishes a SENSOR_INVALID trust report to the Safety Event Integrator; when the stream recovers, it publishes a matching SENSOR_VALID report.
This lets fusion and downstream decisions factor sensor integrity into the safety response, rather than relying on perception output from a sensor that can no longer be trusted.
Refer to the Integration Guide and Safety AI Monitor (SAIM) for more details.
Perception Monitor
The Perception Monitor (PCM) assesses whether the AI perception pipeline itself can be trusted, complementing SAIM’s per-sensor view.
It combines container health with data validation of the perception output and publishes an AI_PIPELINE_VALID or AI_PIPELINE_INVALID verdict to the Safety Event Integrator.
The verdict is pipeline-wide: while it is invalid, every Safety Decision Maker holds its safe state.
Refer to the Integration Guide and Perception Monitor (PCM) for more details.
Safety Event Integrator
The Safety Event Integrator (SEI) receives the safety events that the MDX client derives from the AI Perception messages on Kafka. It groups and correlates alerts that represent the same underlying situation, whether they come from redundant detection pipelines or from multiple camera views of the same area. After validating and fusing these inputs into a single high-confidence safety event, Safety Event Integrator forwards the consolidated event to the Safety Decision Maker for action.
Refer to the Integration Guide and Safety Event Integrator (SEI) for more details.
Safety Decision Maker
The Safety Decision Maker (SDM) consumes validated safety events from the SEI and converts them into concrete control actions for field devices and applications. It applies use-case–specific logic to decide when to slow down or stop a vehicle or inhibit or enable a safety function. The blueprint provides reference SDMs for the forklift safety function and for Proximity Monitoring, which you are expected to extend or adapt to match your target equipment, safety policies, and integration requirements. When an SDM detects a fault it latches a safe state, and an operator must release it; see Release a latched safe state.
Refer to the Integration Guide and Safety Decision Maker (SDM) for more details.
Deploy
- Quick Deployment runs the forklift safety function on the VSS Warehouse 2D demo dataset. Complete Prerequisites first.
- Custom Deployment covers your own cameras, Proximity Monitoring, two decision makers and the decision maker on the Functional Safety Island.
- Applications describes what each reference application protects and what it sends.
To write or adapt a decision maker, see Writing a decision maker.
Next steps
- Agentic Deployment — the same bring-up as a single Docker Compose
service under the
baseprofile, rendering decisions as the VSThalo_safetyoverlay, run either by a coding agent or by hand. - Deployment Guide — prerequisites, deployment, configuration and troubleshooting for running the Safety Core.