Vehicle diagnostic platform using augmented reality for damage assessment

1 . A computing platform comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

receive a plurality of schematics corresponding to a plurality of visible sections of a vehicle; identify one or more schematics of the plurality of schematics corresponding to one or more visible sections of the plurality of visible sections of the vehicle;

generate, based on a graphical overlay of one or more images that depict the one or more visible sections of the vehicle and using the one or more schematics, x-ray image information corresponding to the identified vehicle; and

communicate, to a user device, one or more instructions that cause the user device to display one or more modified versions of the one or more images that are modified based on the x-ray image information, and an x-ray vehicle interface, wherein the x-ray vehicle interface depicts a graphic representation of a subsurface portion of the vehicle having one or more components that are not visible in the one or more images of the vehicle.

2 . The computing platform of claim 1 , wherein identifying the vehicle comprises:

comparing image data of the one or more images of the vehicle to a machine learning dataset that includes additional image data for a plurality of additional images of a plurality of vehicles;

identifying, based on the comparison, a match between the image data and a subset of the additional image data;

accessing vehicle identification information corresponding to the subset of the additional image data, wherein the vehicle identification information comprises one or more of: a vehicle make, a vehicle model, a vehicle year, or a vehicle condition; and

identifying, using the vehicle identification information, an identity of the vehicle.

3 . The computing platform of claim 1 , wherein identifying the one or more schematics corresponding to the identified vehicle comprises:

accessing a stored dataset of correlations between vehicle identification information and schematics; and

identifying, using the vehicle identification information, the one or more schematics corresponding to the identified vehicle, wherein each of the one or more schematics is associated with a portion of the identified vehicle.

4 . The computing platform of claim 1 , wherein generating the x-ray image information further comprises generating information that may be used to generate the graphical overlay on the one or more images, wherein the graphical overlay comprises one of the one or more schematics overlaid on a portion of the identified vehicle to which the one of the one or more schematics corresponds.

5 . The computing platform of claim 2 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

determine, using one or more image recognition and machine learning algorithms, damage to the identified vehicle, wherein determining the damage to the identified vehicle comprises:

comparing the image data of the one or more images of the identified vehicle to the subset of the additional image data;

identifying, based on the comparison, a match between the image data and a second subset of the additional image data;

accessing damage information corresponding to the second subset of the additional image data, wherein the damage information includes details corresponding to damage of vehicles corresponding to the second subset of the additional image data; and

identifying, using the damage information, the damage to the identified vehicle, wherein identifying the damage to the identified vehicle includes at least identifying a location of the damage to the identified vehicle.

6 . The computing platform of claim 5 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

identify, using the one or more schematics and the location of the damage to the identified vehicle, one or more vehicle components that are within a predetermined distance of the identified damage; and

compute, for each of the one or more vehicle components that are within the predetermined distance of the identified damage and using one or more additional machine learning algorithms, a likelihood of replacement score.

7 . The computing platform of claim 6 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

generate, based on the likelihood of replacement scores for each of the one or more vehicle components, replacement part information;

generate one or more commands directing the user device to display a highlighted x-ray interface; and

send, to the user device, the one or more commands directing the user device to display the highlighted x-ray interface, wherein sending the one or more commands directing the user device to display the highlighted x-ray interface causes the user device to:

generate, using the replacement part information, a highlight overlay for the x-ray vehicle interface that emphasizes, using a particular color, the one or more vehicle components that are within the predetermined distance of the identified damage; and

display, along with the x-ray vehicle interface, the highlight overlay.

8 . The computing platform of claim 6 , wherein computing the likelihood of replacement score comprises:

accessing a stored database that includes correlations between the second subset of the additional image data and, for each vehicle corresponding to the second subset of the additional image data, an indication of vehicle components that were replaced in repairing the corresponding vehicle;

computing, using the indications of vehicle components that were replaced in repairing the corresponding vehicles and for each of the one or more vehicle components that are within the predetermined distance of the identified damage, a likelihood of replacement score for each vehicle component identified in the stored database; and

comparing the likelihood of replacement score for each vehicle component identified in the stored database to a predetermined replacement threshold.

9 . The computing platform of claim 8 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

in response to determining that the likelihood of replacement score for a first vehicle component of the one or more vehicle components that are within the predetermined distance of the identified damage exceeds the predetermined replacement threshold, generate one or more commands directing a third party vendor system to provide a replacement for the first vehicle component; and

send, to the third party vendor system, the one or more commands directing the third party vendor system to provide the replacement for the first vehicle component, wherein sending the one or more commands directing the third party vendor system to provide the replacement for the first vehicle component causes the third party vendor system to cause shipment of the replacement for the first vehicle component to an organization corresponding to the user device.

10 . The computing platform of claim 9 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

in response to determining that the likelihood of replacement score for a second vehicle component of the one or more vehicle components that are within the predetermined distance of the identified damage does not exceed the predetermined replacement threshold, send one or more commands, to a mobile device, directing the mobile device to display a prompt for client authorization;

receive a message, from the mobile device, providing authorization to order a replacement for the second vehicle component; and

send, to the third party vendor system, one or more commands directing the third party vendor system to provide the replacement for the second vehicle component, wherein sending the one or more commands directing the third party vendor system to provide the replacement for the second vehicle component causes the third party vendor system to cause shipment of the replacement for the second vehicle component to the organization corresponding to the user device.

11 . The computing platform of claim 8 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

access the stored database, wherein the stored database further includes correlations between the second subset of the additional image data and repair costs for each vehicle corresponding to the second subset of the additional image data;

compute, by averaging the repair costs for each vehicle corresponding to the second subset of the additional image data, a predicted repair cost for the identified vehicle; and

compare the predicted repair cost to a predetermined repair cost threshold.

12 . The computing platform of claim 11 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

in response to determining that the predicted repair cost does not exceed the predetermined repair cost threshold, cause dispatch of a tow vehicle to a location of the identified vehicle, wherein the tow vehicle is dispatched to the location of the identified vehicle without further authorization provided from a mobile device.

13 . The computing platform of claim 12 , wherein causing dispatch of the tow vehicle comprises:

generating one or more commands directing an autonomous vehicle control system corresponding to the tow vehicle to cause the tow vehicle to drive in an autonomous manner to the location of the identified vehicle; and

sending, to the autonomous vehicle control system, the one or more commands directing the autonomous vehicle control system corresponding to the tow vehicle to cause the tow vehicle to drive in an autonomous manner to the location of the identified vehicle, wherein sending the one or more commands directing the autonomous vehicle control system corresponding to the tow vehicle to cause the tow vehicle to drive in an autonomous manner to the location of the identified vehicle causes the tow vehicle to drive in an autonomous manner to the location of the identified vehicle.

14 . The computing platform of claim 11 , wherein the memory stores additional computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:

in response to determining that the predicted repair cost exceeds the predetermined repair cost threshold, send one or more commands, to a mobile device, directing the mobile device to display a prompt for client authorization;

receive a message, from the mobile device, providing authorization to initiate repair of the identified vehicle; and

cause dispatch of a tow vehicle to a location of the identified vehicle.

15 . A method comprising:

at a computing platform comprising at least one processor, a communication interface, and memory:

receiving a plurality of schematics corresponding to a plurality of visible sections of a vehicle; identifying one or more schematics of the plurality of schematics corresponding to one or more visible sections of the plurality of visible sections of the vehicle;

generating, based on a graphical overlay of the one or more images that depict the one or more visible sections of the vehicle and using the one or more schematics, x-ray image information corresponding to the identified vehicle, wherein the x-ray image information depicts a subsurface portion of the identified vehicle not visible in the one or more images of the vehicle; and

communicating, to user device, one or more instructions that cause the user device to display one or more modified versions of the one or more images that are modified based on the x-ray image information corresponding to the identified vehicle, and one or more commands directing the user device to display an x-ray image and an x-ray vehicle interface, wherein the x-ray vehicle interface depicts a graphic representation of a subsurface portion of the vehicle having one or more components that are not visible in the one or more images of the vehicle.

16 . The method of claim 15 , wherein identifying the vehicle comprises:

comparing image data of the one or more images of the vehicle to a machine learning dataset that includes additional image data for a plurality of additional images of a plurality of vehicles;

identifying, based on the comparison, a match between the image data and a subset of the additional image data;

accessing vehicle identification information corresponding to the subset of the additional image data, wherein the vehicle identification information comprises one or more of: a vehicle make, a vehicle model, a vehicle year, or a vehicle condition; and

identifying, using the vehicle identification information, an identity of the vehicle.

17 . The method of claim 16 , wherein identifying the one or more schematics corresponding to the identified vehicle comprises:

accessing a stored dataset of correlations between vehicle identification information and schematics; and

identifying, using the vehicle identification information, the one or more schematics corresponding to the identified vehicle, wherein each of the one or more schematics is associated with a portion of the identified vehicle.

18 . The method of claim 17 , further comprising:

determining, one or more image recognition and machine learning algorithms, damage to the identified vehicle, wherein determining the damage to the identified vehicle comprises:

comparing the image data of the one or more images of the identified vehicle to the subset of the additional image data;

identifying, based on the comparison, a match between the image data and a second subset of the additional image data;

accessing damage information corresponding to the second subset of the additional image data, wherein the damage information includes details corresponding to damage of vehicles corresponding to the second subset of the additional image data; and

identifying, using the damage information, damage to the identified vehicle, the damage to the identified vehicle, wherein identifying the damage to the identified vehicle includes at least identifying a location of the damage to the identified vehicle.

19 . The method of claim 18 , further comprising:

identifying, using the one or more schematics and the location of the damage to the identified vehicle, one or more vehicle components that are within a predetermined distance of the identified damage; and

computing, for each of the one or more vehicle components that are within the predetermined distance of the identified damage and using one or more additional machine learning algorithms, a likelihood of replacement score.

20 . One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, a communication interface, and memory, cause the computing platform to:

receive a plurality of schematics corresponding to a plurality of visible sections of a vehicle; identify one or more schematics of the plurality of schematics corresponding to one or more visible sections of the plurality of visible sections of the vehicle;

generate, based on a graphical overlay of one or more images that depict the one or more visible sections of the vehicle and using the one or more schematics, x-ray image information corresponding to the identified vehicle; and

communicate, to a user device, one or more instructions that cause the user device to display one or more modified versions of the one or more images that are modified based on the x-ray image information, and an x-ray vehicle interface, wherein the x-ray vehicle interface depicts a graphic representation of a subsurface portion of the vehicle having one or more components that are not visible in the one or more images of the vehicle.