US 12,130,152 B2
System for offsite navigation
Soumya Gupta, Menlo Park, CA (US); John Z. Pang, Menlo Park, CA (US); Andrey Konchenko, Menlo Park, CA (US); Erik Burton, Menlo Park, CA (US); Mugdha Bhusari, Menlo Park, CA (US); Jose R. Celaya Galvan, Menlo Park, CA (US); Ivan Joel Alaniz, McAllen, TX (US); and Crispin Chatar, Sugar Land, TX (US)
Assigned to Schlumberger Technology Corporation, Sugar Land, TX (US)
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
Filed on Nov. 24, 2021, as Appl. No. 17/535,236.
Application 17/535,236 is a continuation in part of application No. 16/878,524, filed on May 19, 2020, granted, now 11,598,639.
Claims priority of provisional application 62/850,482, filed on May 20, 2019.
Prior Publication US 2022/0157167 A1, May 19, 2022
Int. Cl. G01C 21/36 (2006.01); G01C 21/00 (2006.01); G01C 21/32 (2006.01); G01C 21/34 (2006.01)
CPC G01C 21/3697 (2013.01) [G01C 21/32 (2013.01); G01C 21/3407 (2013.01); G01C 21/3446 (2013.01); G01C 21/3852 (2020.08)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
generating, by a navigation service, a route for navigating from a route origin to a route destination using a private roads repository;
identifying a ghost origin and a ghost destination of a ghost road along the route, wherein the ghost road is a proxy road for one or more base roads in a base roads repository and the ghost origin and the ghost destination each correspond to a location where a private road intersects a base road;
sending, using an application programming interface of a base roads engine, a first request for a route from the ghost origin to the ghost destination;
receiving, from the base roads engine in response to the first request, a replacement section from the ghost origin to the ghost destination;
replacing, in the route from the route origin to the route destination, the ghost road with the replacement section to create an updated route comprising a plurality of segments, wherein the replacement section is obtained from the base roads repository via the application programming interface;
generating, using distances and travel times returned by the application programming interface, an estimated travel time from the route origin to the route destination over the plurality of segments of the updated route;
transforming a plurality of metadata describing a vehicle type of a vehicle using the updated route into a vector data structure, wherein the vehicle type identifies a physical size of the vehicle;
predicting, by an unsupervised clustering machine learning model taking as input the vector data structure, a probability of delay for the vehicle type;
estimating a predicted delay from the probability of delay for the vehicle type; and
presenting, on a display, the predicted delay together with the estimated travel time.