US 11,668,581 B2
Generating positions of map items for placement on a virtual map
Han Liu, Millbrae, CA (US); Yiwei Zhao, Sunnyvale, CA (US); Jingwen Liang, Mountain View, CA (US); Mohsen Sardari, Burlingame, CA (US); Harold Chaput, Castro Valley, CA (US); Navid Aghdaie, San Jose, CA (US); and Kazi Zaman, Foster City, CA (US)
Assigned to ELECTRONIC ARTS INC., Redwood City, CA (US)
Filed by Electronic Arts Inc., Redwood City, CA (US)
Filed on Sep. 2, 2022, as Appl. No. 17/902,290.
Application 17/902,290 is a continuation of application No. 16/886,634, filed on May 28, 2020, granted, now 11,473,927.
Claims priority of provisional application 62/970,631, filed on Feb. 5, 2020.
Prior Publication US 2022/0412765 A1, Dec. 29, 2022
Int. Cl. G01C 21/36 (2006.01); G06N 3/08 (2023.01); G06F 16/29 (2019.01)
CPC G01C 21/3673 (2013.01) [G01C 21/367 (2013.01); G01C 21/3682 (2013.01); G06F 16/29 (2019.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method of training a generator neural network for use in generating positions of map items for placement on a virtual map, the method comprising:
receiving one or more training examples, each training example including: (i) map data, including one or more channels of position information for a region, (ii) a latent vector, and (iii) at least one ground truth placement of map items;
for each training example of the one or more training examples:
generating, with the generator neural network, a generated placement of map items for the training example, including processing the map data and the latent vector of the training example;
determining, with a discriminator neural network, an estimated probability of the generated placement of map items being generated by the generator neural network, including processing: (i) the generated placement of map items (ii) the map data of the training example, and (iii) the latent vector of the training example; and
updating parameters of the generator neural network, including:
determining an adversarial loss using the estimated probability; and
updating the parameters of the generator neural network in dependence on the adversarial loss.