Techniques for analyzing vehicle design deviations using deep learning with neural networks
A design application is configured to generate a latent space representation of a fleet of pre-existing vehicles. The design application encodes vehicle designs associated with the fleet of pre-existing vehicles into the latent space representation to generate a first latent space location. The first latent space location represents the characteristic style associated with the fleet of pre-existing vehicles. The design application encodes a sample design provided by a user into the latent space representation to produce a second latent space location. The design application then determines a distance between the first latent space location and the second latent space location. Based on the distance, the design application generates a style metric that indicates the aesthetic similarity between the sample design and the vehicle designs associated with the fleet of pre-existing vehicles. The design application can also generate new vehicle designs based on the latent space representation and the sample design.
1. A computer-implemented method for analyzing vehicle designs, the method comprising:
encoding a first vehicle design into a first location within a latent space representation of vehicle design features;
encoding a second vehicle design into a second location within the latent space representation; and
generating a first metric based on the first location and the second location, wherein the first metric indicates a degree to which the first vehicle design differs from a characteristic style associated with the second vehicle design.
2. The computer-implemented method of claim 1 , further comprising generating a third vehicle design based on the first metric, wherein the third vehicle design includes at least one design feature associated with the characteristic style.
3. The computer-implemented method of claim 2 , wherein generating the third vehicle design comprises:
traversing the latent space from the first location to a third location; and
increasing a dimensionality associated with the third location to a dimensionality that is greater than or equal to a dimensionality associated with the first vehicle design.
4. The computer-implemented method of claim 3 , wherein increasing the dimensionality associated with the third location comprises performing a deconvolution operation on the third location.
5. The computer-implemented method of claim 1 , wherein encoding the first vehicle design comprises decreasing a dimensionality associated with the first vehicle design to a dimensionality that is equal to a dimensionality associated with the latent space.
6. The computer-implemented method of claim 5 , wherein decreasing the dimensionality associated with the first vehicle design comprises performing a convolution operation on the first vehicle design.
7. The computer-implemented method of claim 1 , wherein generating the first metric comprises computing a distance value between the first location and the second location.
8. The computer-implemented method of claim 1 , wherein the first vehicle design comprises a two-dimensional array of pixels.
9. The computer-implemented method of claim 1 , wherein the first vehicle design comprises a set of non-uniform rational B-spline (NURBS) curves.
10. The computer-implemented method of claim 1 , further comprising training an encoder network to encode the first vehicle design based on a comparison between the second vehicle design and a third vehicle design.
11. A non-transitory computer-readable medium storing program instructions that, when executed by a processor, cause the processor to analyze vehicle designs by performing the steps of:
encoding a first vehicle design into a first location within a latent space representation of vehicle design features;
encoding a second vehicle design into a second location within the latent space representation; and
generating a first metric based on the first location and the second location, wherein the first metric indicates a degree to which the first vehicle design differs from a characteristic style associated with the second vehicle design.
12. The non-transitory computer-readable medium of claim 11 , further comprising the step of generating a third vehicle design based on the first metric, wherein the third vehicle design includes at least one design feature associated with the characteristic style.
13. The non-transitory computer-readable medium of claim 12 , wherein the step of generating the third vehicle design comprises:
traversing the latent space from the first location to a third location; and
increasing a dimensionality associated with the third location to a dimensionality that is greater than or equal to a dimensionality associated with the first vehicle design.
14. The non-transitory computer-readable medium of claim 13 , wherein increasing the dimensionality associated with the third location comprises performing a deconvolution operation on the third location.
15. The non-transitory computer-readable medium of claim 11 , wherein the step of encoding the first vehicle design comprises decreasing a dimensionality associated with the first vehicle design to a dimensionality that is equal to a dimensionality associated with the latent space.
16. The non-transitory computer-readable medium of claim 15 , wherein decreasing the dimensionality associated with the first vehicle design comprises performing a convolution operation on the first vehicle design.
17. The non-transitory computer-readable medium of claim 11 , wherein the step of generating the first metric comprises computing a distance value between the first location and the second location.
18. The non-transitory computer-readable medium of claim 11 , further comprising the steps of:
training an encoder network to encode the first vehicle design based on a comparison between the second vehicle design and a third vehicle design; and
training a generator network to generate a third vehicle design based on a comparison between the first vehicle design and the second vehicle design.
19. The non-transitory computer-readable medium of claim 11 , wherein the first vehicle design includes at least one sensor feature associated with an autonomous vehicle.
20. A system, comprising:
a memory that stores a software application; and
a processor that executes the software application to perform the steps of:
encoding a first vehicle design into a first location within a latent space representation of vehicle design features,
encoding a second vehicle design into a second location within the latent space representation, and
generating a first metric based on the first location and the second location, wherein the first metric indicates a degree to which the first vehicle design differs from a characteristic style associated with the second vehicle design.