Safety & observability
ActivePhysical AI Safety Observability
Runtime safety layer on Jetson AGX Thor that measures pipeline performance and model inference, so operators can see when the system is outside safe limits.
Measured results
- Pipeline overhead28.6 frames/sMock model, AGX Thor, 2026-09-09
- Cosmos-Reason2-2Bp50 4.35 s per frameAGX Thor, 2026-09-09
- Detection qualityNot yet measuredNo ground truth yet
- PhysicalCameras and sensors
- Edge computePerception pipeline
- Edge computeInference on AGX Thor
- Edge computeLatency and throughput telemetry
- Edge computeChecks against budgets
- PhysicalOperator review with a RAG assistant
The problem
A robot that works most of the time is not deployable. Operators need to know when perception or inference has degraded before it becomes a physical failure, and they need evidence they can review afterward.
Approach
- Instrument the full perception and inference pipeline on Jetson AGX Thor, not just the model.
- Measure pipeline overhead separately from model cost, using a mock model as a baseline.
- Use retrieval-grounded agents to help an operator interpret what the telemetry shows, with a human making the call.
Where it stands
Pipeline overhead and Cosmos-Reason2-2B inference are measured on Thor. Detection quality is not measured yet because there is no ground truth set.
On 2026-10-29 the rules were written up as a hazard analysis in the vocabulary of SOTIF and ISO 26262: a hazard table, the triggering conditions, and the acceptance criteria any safety-related use would need. It is method and vocabulary only, with no conformance claim, and it restates the boundary: the system observes and alerts, and never stops or commands a robot.