US 11,960,926 B2
Automated plan synthesis and action dispatch
Swarup Kumar Mohalik, Bangalore Karnataka (IN); Senthamiz Selvi Arumugam, Solna (SE); and Chakri Padala, Bangalore (IN)
Assigned to Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Appl. No. 17/272,465
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
PCT Filed Sep. 13, 2018, PCT No. PCT/IN2018/050593
§ 371(c)(1), (2) Date Mar. 1, 2021,
PCT Pub. No. WO2020/053871, PCT Pub. Date Mar. 19, 2020.
Prior Publication US 2021/0318906 A1, Oct. 14, 2021
Int. Cl. G06F 9/48 (2006.01); G06F 9/50 (2006.01); G06N 20/00 (2019.01)
CPC G06F 9/4881 (2013.01) [G06F 9/505 (2013.01); G06F 9/5083 (2013.01); G06N 20/00 (2019.01)] 24 Claims
OG exemplary drawing
 
1. A method of controlling when artificial intelligence planning synthesizes a plan to accomplish a task in a system that is an internet-of-things (IoT) system or a cyber-physical system, the method comprising:
determining a quiescent phase during which values of at least some predicates describing a state of the system will remain stable; and
controlling artificial intelligence planning to synthesize the plan during at least some of the quiescent phase;
wherein said controlling comprises controlling the artificial intelligence planning to synthesize the plan as a set of basic or atomic actions to be executed by devices or resources in the system for accomplishing the task, wherein each basic or atomic action is defined by a pair of predicates which capture the state of the system before and after the basic or atomic action is executed, wherein the predicate which captures the state of the system before the basic or atomic action is executed is a precondition predicate and the predicate which captures the state of the system after the basic or atomic action is executed is an effect predicate; and
wherein the quiescent phase is a phase during which values of the precondition predicates in the plan will remain stable.