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.
Power, bandwidth, logistics
No mains power, no reliable backhaul, and every resupply is a convoy. Any architecture assuming cloud inference is inapplicable.
Decide locally
Classification must happen on the node. Only events leave, and only when there is something worth sending.
Years, not months
Battery life determines resupply frequency, which determines risk exposure to the people doing the resupplying.
Detection and cueing only
This is a sensing and early-warning capability. It provides situational awareness to human decision-makers and has no engagement function.
Austere-site sensing is constrained by energy and logistics, not by algorithms. We think the architecture that wins is the one that sends the least.
Discuss the approach.
Teaming and technical discussion welcome.
CONTACT TIMOTHY → Back to Edge Threat Detection →