PORRITTINC
( LAYTON, UT )
POSITION PAPER · NEUROMORPHIC R&D

Edge I&C
at the sensor.

Today intelligence sits in a cabinet and sensors ship raw data to it. We believe the arrangement inverts: the sensor decides, and the cabinet supervises decisions rather than processing samples.

← Back to Edge I&C at the Sensor

POSITION PAPER · TECHNICAL OPINION

This is a technical position paper stating Porritt Inc.'s engineering view. It is not a peer-reviewed publication and does not report experimental results. Where it forecasts capability, it is stating design intent rather than achieved performance.

Position
PREMISE

Bandwidth is the tax

Streaming every tag continuously consumes network, storage, and historian capacity, most of it spent recording that nothing happened.

APPROACH

Decide at the transmitter

When classification costs milliwatts it belongs at the measurement point. The control system receives events with context instead of an undifferentiated sample stream.

CONSEQUENCE

Coverage becomes affordable

At years-on-battery power budgets, instrumentation can be placed where conduit was never going to reach. Coverage becomes an economic decision, not a civil-works project.

HONEST LIMIT

Trust and verification

Distributed decision-making raises a real question: how do you verify a decision made at the edge? We do not consider this solved.

Objectives
mW
Per-node objective
YEARS
Battery objective
EDGE
Decision point
R&D
Not deployed
Open questions

Configuration management across thousands of decision-making endpoints, firmware integrity assurance, and audit of edge decisions are unresolved. In safety-instrumented applications, an edge-resident decision would require a certification pathway that does not yet exist.

Discuss the research.

We welcome technical challenge on these positions. Collaboration enquiries welcome.

CONTACT TIMOTHY → Back to Edge I&C at the Sensor →