US 11,941,327 B2
Customizable reinforcement learning of column placement in structural design
Yi Wang, Richmond, CA (US); and Mehdi Nourbakhsh, Richmond, CA (US)
Assigned to AUTODESK, INC., San Francisco, CA (US)
Filed by AUTODESK, INC., San Francisco, CA (US)
Filed on Oct. 15, 2020, as Appl. No. 17/071,992.
Claims priority of provisional application 63/078,047, filed on Sep. 14, 2020.
Prior Publication US 2022/0083703 A1, Mar. 17, 2022
Int. Cl. G06F 30/13 (2020.01); G06F 30/27 (2020.01); G06N 20/00 (2019.01)
CPC G06F 30/13 (2020.01) [G06F 30/27 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
applying one or more placement rules to a floorplan of a building to generate a set of candidate column locations in the floorplan;
selecting, via a first reinforcement learning (RL) agent that comprises a first machine learning model executed by a processor, one or more column locations from the set of candidate column locations based on a structural stability of the one or more column locations; and
outputting the floorplan that includes the one or more column locations as a structural design for the building.