Probabilistic constraint middleware for multi-robot fleet
This technology gives robots and autonomous systems a smarter way to make decisions when they can't see the full picture of their environment and must share a network with other agents. It builds a mathematical policy—essentially a decision playbook—that tells each agent what to do under uncertainty, while guaranteeing with a tunable probability that the agent stays within defined operational rules (like bandwidth limits, safety zones, or task priorities). The method converts an uncomplicated starting policy into a compact controller, then uses statistical sampling and discrete optimization to tighten compliance with those rules without sacrificing overall performance. The result is a robot or software agent that can act autonomously at scale while respecting hard constraints on how it uses shared resources.
What you could build
A middleware or SDK embedded in autonomous fleet management platforms—drone swarms, warehouse robots, or autonomous vehicle coordination systems—that enforces probabilistic operational constraints in real time; buyers would be defense integrators, industrial automation vendors, and autonomous logistics operators.
Who in Virginia should care
Defense primes and government contractors concentrated in Northern Virginia (Leidos, Booz Allen, SAIC, Northrop) running autonomous systems programs would be natural licensees or development partners.
Readiness: Lab validated
Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.
Readiness is inferred from the patent text, not from a lab visit.
The record
- Inventors
- Michael Fowler, Ryan Williams
- Granted
- January 23, 2024
- Status
- Granted patent
- Patent number
- 11880188
Ready to talk?
Virginia Tech Intellectual Properties handles licensing for this technology.
Prosim summaries are generated from public patent text and are not legal advice.