US 11,052,772 B2
Cooperative distributed control of target systems
Wolf Kohn, Seattle, WA (US); Michael Luis Sandoval, Bellevue, WA (US); Vishnu Vettrivel, Bothell, WA (US); Jonathan Cross, Bellevue, WA (US); Jason Knox, Kenmore, WA (US); David Talby, Mercer Island, WA (US); and Mike Lazarus, San Diego, CA (US)
Assigned to Veritone Alpha, Inc., Costa Mesa, CA (US)
Filed by Veritone Alpha, Inc., Costa Mesa, CA (US)
Filed on Oct. 9, 2018, as Appl. No. 16/155,816.
Application 16/155,816 is a continuation of application No. 14/746,777, filed on Jun. 22, 2015, granted, now 10,133,250.
Claims priority of provisional application 62/015,018, filed on Jun. 20, 2014.
Prior Publication US 2019/0041817 A1, Feb. 7, 2019
This patent is subject to a terminal disclaimer.
Int. Cl. B60L 50/60 (2019.01); G05B 13/04 (2006.01); G06Q 10/06 (2012.01); G06Q 50/06 (2012.01); G05B 17/02 (2006.01); B60W 10/06 (2006.01); B60W 10/08 (2006.01); G05B 19/042 (2006.01); G05B 19/048 (2006.01)
CPC B60L 50/60 (2019.02) [B60W 10/06 (2013.01); B60W 10/08 (2013.01); G05B 13/04 (2013.01); G05B 13/041 (2013.01); G05B 17/02 (2013.01); G05B 19/042 (2013.01); G05B 19/048 (2013.01); G06Q 10/06315 (2013.01); G06Q 50/06 (2013.01); B60W 2510/0666 (2013.01); B60W 2510/086 (2013.01); G05B 2219/2639 (2013.01); Y10S 903/93 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, by one or more computing systems, system information that describes a physical system having a plurality of inter-related elements and having one or more outputs whose values vary based at least in part on values of one or more manipulatable control elements of the plurality, wherein the system information includes multiple rules that have conditions to evaluate and that specify restrictions involving the plurality of elements;
generating, by the one or more computing systems, a Hamiltonian function that expresses a model describing a current state of the physical system, including converting coupled differential equations that are based on the system information and based on sensor information identifying current state information for at least one element of the plurality and based on objective information identifying a goal to be achieved while controlling the physical system;
performing, by the one or more computing systems, a piecewise linear analysis of the coupled differential equations to identify one or more control actions that manipulate values of the one or more manipulatable control elements and that provide a solution for the goal;
initiating performance of the identified one or more control actions in the physical system to control the physical system at a first time, including manipulating values of the one or more manipulatable control elements and causing resulting changes in the values of the one or more outputs; and
updating, by the one or more computing systems, and based at least in part on further sensor information obtained after the first time that identifies further state information for at least one element of the plurality, the Hamiltonian function to represent the further sensor information within the model, for use in further controlling the physical system after the first time.