USPTO Awards Vehicle Dispatching Patent to Autonomous Solutions, Inc.

The US Patent & Trademark Office recently awarded ASI with Patent No. US 8,626,565 B2 titled "Vehicle Dispatching Method and System."

Petersboro, UT January 31, 2014


The US Patent & Trademark Office (USPTO) awarded Autonomous Solutions, Inc. (ASI) with a patent entitled "Vehicle Dispatching Method and System." The patent (No. US 8,626,565 B2) deals with optimizing how vehicles are routed in situations where there are multiple origins, destinations, and routes available.

"Most dispatching algorithms are based on linear programming," explained Tom Petroff who leads ASI's Perception Team, a group of researchers responsible for much of ASI's research and development efforts across several industries. "The dispatching is done up front, and it often doesn't handle changes in conditions very well, such as a vehicle going out of service or bad weather." The new dispatching system combines linear programming with reinforcement learning, a methodology that calculates outcomes to optimize a cost function-either minimizing or maximizing. "The algorithm leads to more efficient routes and better cost savings for dispatching scenarios."

While the algorithm is useful for autonomous vehicles, Petroff reminds that this technology is useful for a number of industries. "In the dispatch application the whole idea is to minimize the cost to perform an application or to maximize the amount of haulage or number of trips that can be done in a given time. These benefits extend beyond autonomous vehicles to dispatching situations of all types: transportation, fleets (airplanes, taxis, etc.), mining, farming, or whatever industry it may be."

The Vehicle Dispatching Method and System patent is the fifteenth patent awarded to ASI by the USPTO.

Featured Product

Boston Dynamics Webinar - Why Humanoids Are the Future of Manufacturing

Boston Dynamics Webinar - Why Humanoids Are the Future of Manufacturing

Join us November 18th for this Webinar as we reflect on what we've learned by observing factory floors, and why we've grown convinced that chasing generalization in manipulation—both in hardware and behavior—isn't just interesting, but necessary. We'll discuss AI research threads we're exploring at Boston Dynamics to push this mission forward, and highlight opportunities our field should collectively invest more in to turn the humanoid vision, and the reinvention of manufacturing, into a practical, economically viable product.