US 12,190,022 B2
Generative design techniques for automobile designs
James Stoddart, Atlanta, GA (US); David Benjamin, Brooklyn, NY (US); Danil Nagy, New York, NY (US); and Damon Lau, New York, NY (US)
Assigned to AUTODESK, INC., San Francisco, CA (US)
Filed by AUTODESK, INC., San Francisco, CA (US)
Filed on Oct. 18, 2022, as Appl. No. 18/047,607.
Application 18/047,607 is a continuation of application No. 16/387,527, filed on Apr. 17, 2019, granted, now 11,475,178.
Claims priority of provisional application 62/668,736, filed on May 8, 2018.
Prior Publication US 2023/0060989 A1, Mar. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 30/15 (2020.01); B62D 65/00 (2006.01); G06F 30/00 (2020.01); G06F 30/13 (2020.01)
CPC G06F 30/15 (2020.01) [B62D 65/00 (2013.01); G06F 30/00 (2020.01); G06F 30/13 (2020.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method for generating automotive designs, the method comprising:
computing a first plurality of metric values based on a first plurality of parameter values for a parameterized automobile model that is associated with at least one previously-generated design;
performing one or more optimization operations on the first plurality of parameter values to generate a second plurality of parameter values;
generating, based on the second plurality of parameter values, a plurality of production designs, wherein at least one design included in the plurality of production designs is more convergent with respect to at least one design goal than the at least one previously-generated design; and
displaying a design space that includes at least one or more of the production designs included in the plurality of production designs.