System and method for cleaning process of target surface

Abstract

The present disclosure provides a system and method for a cleaning process of a target surface. A method includes receiving a set of data associated with a surface condition of a vehicle; determining, by an artificial intelligence system, a degree of instance of one or more defects on a surface of the vehicle; and updating a path followed by one or more robots based on the determination of the degree of the instance of the one or more defects. The determination of the extent of the instance of the one or more defects causes the one or more robots to initiate a remedial action towards a target portion of the surface of the vehicle to address the instance of the one or more defects.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to systems and methods for a paint application process experienced by vehicles during manufacturing production. More specifically, the present disclosure relates to controlling operation of a cleaning method associated with a paint application process. BACKGROUND

[0002] The statements in this section merely provide background information related to the present disclosure and can not constitute prior art.

[0003] As a vehicle travels through a typical automotive finishing facility, the surface of the vehicle can be prepared for painting at a first work station and then travel to other work stations. As the vehicle travels through each of the other work stations, the vehicle can be exposed to build-up on the surface of the vehicle even though there is typically a periodic cleaning of the work stations between work stations.

[0004] The present disclosure addresses these and other issues related to systems and methods for a paint application process. SUMMARY

[0005] This section provides a general summary of the present disclosure and is not a comprehensive disclosure of its full scope or all of its features.

[0006] The present disclosure provides a method comprising: receiving, from a first inspection station, a first set of data associated with a surface condition of a vehicle; determining, by an artificial intelligence system, a degree of a first instance of one or more defects on a surface of the vehicle based on the first set of data; and updating a path followed by one or more robots based on the determination of the degree of the first instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate a remedial action to the surface of the vehicle to address the first instance of the one or more defects; wherein the first set of data comprises a quantity of defects associated with the first instance of the one or more defects, a size of each defect of the first instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof; the method further comprising: predicting, by the artificial intelligence system, a quantity of debris that will result from the remedial action; wherein the update to the path followed by the one or more robots is further based on the predicted quantity of debris; the method further comprising: receiving, from a second inspection station, a second set of data associated with the surface condition of the vehicle; determining, by the artificial intelligence system, a degree of a second instance of one or more defects on the surface of the vehicle based on the second set of data and the predicted quantity of debris that will result from the remedial action; and updating the path followed by the one or more robots based on the determination of the degree of the second instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate the remedial action to at least one of the target portion of the surface of the vehicle or another target portion to address the second instance of the one or more defects; wherein the second set of data comprises a quantity of defects associated with the second instance of the one or more defects, a size of each defect of the second instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof; and wherein the remedial action comprises a sanding process, a polishing process, or a combination thereof, and wherein the first instance and the second instance of the one or more defects comprise a portion of the surface of the vehicle that includes an excess amount of dust, an excess amount of dirt, an excess amount of debris, or a combination thereof.

[0007] The present disclosure provides a system comprising: an infrastructure system configured to: receive, from a first inspection workstation, a first set of data associated with a surface condition of a vehicle; determine, by an artificial intelligence system, a degree of a first instance of one or more defects on a surface of the vehicle based on the first set of data; update a path followed by one or more robots based on the determination of the degree of the first instance of the one or more defects; the first inspection workstation configured to: identify the first set of data; send the first set of data to the infrastructure system; and the one or more robots configured to: initiate a remedial action to address the first instance of the one or more defects to a target portion of the surface of the vehicle based on the update to the path, wherein the first set of data comprises a quantity of defects associated with the first instance of the one or more defects, a size of each defect of the first instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof; wherein the infrastructure system is further configured to: predict, by the artificial intelligence system, a quantity of debris that will result from the remedial action; wherein the update to the path followed by the one or more robots is further based on the predicted quantity of debris; wherein the infrastructure system is further configured to: receive, from a second inspection workstation, a second set of data associated with the surface condition of the vehicle; determine, by the artificial intelligence system, a degree of a second instance of one or more defects on the surface of the vehicle based on the second set of data and the predicted quantity of debris that will result from the remedial action; and update the path followed by the one or more robots based on the determination of the degree of the second instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate the remedial action to address the second instance of the one or more defects to at least one of the target portion or another target portion of the surface of the vehicle; wherein the second set of data comprises a quantity of defects associated with the second instance of the one or more defects, a size of each defect of the second instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof; and wherein the remedial action comprises a sanding process, a polishing process, or a combination thereof, and wherein the first instance and the second instance of the one or more defects comprise a portion of the surface of the vehicle that includes an excess of dust, an excess of dirt, an excess of debris, or a combination thereof.

[0008] The present disclosure provides one or more non-transitory computer-readable media storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to: receive, from a first inspection station, a first set of data associated with a surface condition of a vehicle; determine, by an artificial intelligence system, a degree of a first instance of one or more defects on a surface of the vehicle based on the first set of data; and update a path followed by one or more robots based on the determination of the degree of the first instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate a remedial action to the target portion of the surface of the vehicle to address the first instance of the one or more defects; wherein the first set of data includes an amount of defects associated with the first instance of the one or more defects, a size of each defect of the first instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof; wherein the at least one processor is further caused to: predict, by the artificial intelligence system, an amount of debris that will result from the remedial action, wherein the update to the path followed by the one or more robots is further based on the predicted amount of debris; wherein the at least one processor is further caused to: receive, from a second inspection station, a second set of data associated with the surface condition of the vehicle; determine, by the artificial intelligence system, a degree of a second instance of one or more defects on the surface of the vehicle based on the second set of data and the predicted amount of debris that will result from the remedial action; and update the path followed by the one or more robots based on the determination of the degree of the second instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate the remedial action to at least one of the target portion or another target portion of the surface of the vehicle to address the second instance of the one or more defects; wherein the second set of data includes an amount of defects associated with the second instance of the one or more defects, a size of each defect of the second instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof; and wherein the remedial action includes a sanding process, a polishing process, or a combination thereof, and wherein the first instance and the second instance of the one or more defects include a portion of the surface of the vehicle that includes an excess amount of dust, an excess amount of dirt, an excess amount of debris, or a combination thereof.

[0009] Further areas of applicability will become apparent from the description provided herein. It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order that the disclosure can be well understood, various forms thereof will now be described by way of example with reference to the drawings in which:

[0011] Figure 1 depicts an overall process flow of an example method according to various embodiments;

[0012] Figure 2 depicts an overall system associated with a workstation according to various embodiments;

[0013] Figure 3 shows a defect detected by a defect detection system according to various embodiments;

[0014] Figure 4 is a flowchart showing an example method for a paint application process according to various embodiments; and

[0015] Figure 5 is a flowchart showing another example method for a paint application process according to various embodiments.

[0016] The drawings described herein are for purposes of illustration only and are not intended to limit the scope of the present disclosure in any way. DETAILED DESCRIPTION

[0017] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate like or corresponding parts and features.

[0018] The present disclosure provides a means for reducing buildup on a surface of a vehicle as the vehicle progresses through a manufacturing process. For example, because a typical paint application process allows for buildup to compound on a surface of a vehicle during a manufacturing process, defects can arise downstream of the manufacturing process. By implementing one or more of the means disclosed in the present disclosure, an instant source of feedback associated with a location of buildup on a surface of a vehicle is provided. As an example, the instant source of feedback identifies where a predicted buildup is located on a surface of a vehicle. In both cases where a buildup location is specifically indicated and / or when a predicted buildup location, an indication of an area on a surface of a vehicle that can require additional cleaning is identified.

[0019] Additionally, based on the determination of indications of areas on the vehicle's surface that may require additional cleaning, one or more corrective actions that were not initially part of the predefined paint application process can be taken. Furthermore, the determination of indications of areas on the vehicle's surface that may require additional cleaning provides an increased number of data points associated with the measurement and inspection of the vehicle. Furthermore, based on the determination of indications of areas on the vehicle's surface that may require additional cleaning, a higher percentage of accumulations that may further cause defects in the predefined paint application process are removed. In various examples, this determination allows for an optimized paint application process, as described in greater detail herein.

[0020] Figure 1 Shown with the vehicle (e.g., Figure 2 2 (a vehicle 202 shown in FIG) as part of an overall manufacturing process. However, it should be understood that the exemplary path 100 associated with the paint application process need not be part of the overall manufacturing process, but can be an isolated process and / or part of any other type of overall process. The exemplary path 100 is typically composed of one or more workstations. For example, the exemplary path 100 may include a pre-treatment electrophoretic coating workstation 102, an electrophoretic coating oven workstation 104, a plurality of inspection workstations 106a-106c, a pair of defect sanding / repair workstations 108a, 108b, a pair of robotic dust removal (tack-off) workstations 110a, 110b, a primer spraying workstation 112, a primer oven workstation 114, an enamel spraying workstation 116, an enamel oven workstation 118, and a defect wet sanding / polishing workstation 120. However, fewer or additional workstations of the same or different types are contemplated.

[0021] refer to Figure 2 , shows an example workstation 200 in one or more workstations (e.g., a pre-treatment electrophoretic coating workstation 102, an electrophoretic coating oven workstation 104, a plurality of inspection workstations 106a-106c, a pair of defect sanding / repair workstations 108a, 108b, a pair of robotic dust removal workstations 110a, 110b, a primer spraying workstation 112, a primer oven workstation 114, an enamel spraying workstation 116, and / or a defect wet sanding / polishing workstation 118). For example, Figure 2 A vehicle 202 is shown traveling through the exemplary workstation 200. The exemplary workstation 200 generally includes at least one sensor infrastructure 204 connected to at least a central edge server 206. For example, the central edge server is connected to the at least one sensor infrastructure 204 wirelessly, by wire, or a combination thereof.

[0022] The central edge server 206 is configured to track the progress of the vehicle 202 through the paint application process with sensor data received from the at least one sensor infrastructure 204. The at least one sensor infrastructure 204 includes a set of infrastructure sensors 208, such as, for example, two-dimensional (2D) cameras, three-dimensional (3D) cameras, infrared sensors, radar scanners, laser scanners, light detection and ranging (lidar) sensors, ultrasonic sensors, and the like. The set of infrastructure sensors 208 monitor the progress of the vehicle 202 through the paint application process and / or monitor the buildup on the surface of the vehicle 202. However, it should be understood that other characteristics and / or operations associated with the vehicle 202 can also be monitored.

[0023] Additionally, the central edge server 206 is configured to optimize the paint application process with an artificial intelligence system 210 included within the central edge server 206. For example, in instances in which the artificial intelligence system 210 determines that there is an excessive level of buildup (e.g., debris) on the surface of the vehicle 202 and / or predicts that there can be a subsequent excessive level of buildup, the artificial intelligence system 210 can adjust the predefined robotic cleaning path of one or more robots (not shown) to provide additional cleaning to the identified area on the surface of the vehicle 202. For example, the highlighted area (e.g., the plurality of defects 300 shown in Figure 3 The artificial intelligence system 210 can adjust the predefined robotic cleaning path of one or more robots to provide additional cleaning to the highlighted area on the surface of the vehicle 202 based at least on the sensor data. As another example, the artificial intelligence system 210 can adjust the predefined robotic cleaning path of one or more robots to provide additional cleaning to the highlighted area on the surface of the vehicle 202 by causing the central edge server 206 to transmit one or more instructions and / or one or more signals to the one or more robots. As an additional example, the artificial intelligence system 210 can be internal to the central edge server 206 (e.g., as shown in Figure 2 ) or external with respect to the central edge server 206 (e.g., within an infrastructure system (not shown) that the central edge server 206 can be configured to communicate with).

[0024] Referring back to Figure 1At the pre-treatment electrocoating station 102, the vehicle 202 can enter the paint application process by first cleaning the surface of the vehicle 202 and applying a phosphate to prepare the surface of the vehicle 202 for electrocoating. It should be understood that the pre-treatment electrocoating station 102 can clean the surface of the vehicle 202 any number of times. For example, the central edge server 206 can cause the pre-treatment electrocoating station 102 to clean the surface of the vehicle 202 based on sensor data received from the at least one sensor infrastructure 204 associated with the pre-treatment electrocoating station 102. As another example, the sensor data received from the at least one sensor infrastructure 204 associated with the pre-treatment electrocoating station 102 is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring progress of the vehicle 202 through the pre-treatment electrocoating station 102.

[0025] It should also be understood that the pre-treatment electrocoating station 102 can apply any material to prepare the surface of the vehicle 202 for electrocoating. Once the surface of the vehicle 202 is cleaned and the phosphate is applied, one or more coatings are applied to the pre-treated surface of the vehicle 202 in an electrocoat bath (e.g., an electrocoating process). For example, the electrocoat bath can include a majority percentage of deionized water (e.g., 80-90%) and a minimum percentage of paint solids (e.g., 10-20%). It should be understood that the electrocoat bath can include different percentages of deionized water and paint solids. It should also be understood that the electrocoat bath can include any material mixed with any type of water. A post-rinse process can occur after the electrocoat bath to remove any excess paint residue, thereby maintaining paint uniformity on the surface of the vehicle 202.

[0026] The vehicle 202 can then proceed to the electrocoat bake oven station 104. The electrocoat bake oven station 104 is a station configured to cure a film of paint applied to the surface of the vehicle 202 by baking the surface of the vehicle 202. For example, the bake time can be any duration (e.g., 20 minutes). As another example, the bake process can occur at any temperature (e.g., 375 degrees Fahrenheit). As an additional example, the central edge server 206 can cause the electrocoat bake oven station 104 to change the temperature and / or bake time of the bake process based on sensor data received from the at least one sensor infrastructure 204 associated with the electrocoat bake oven station 104. As another example, the sensor data received from the at least one sensor infrastructure 204 associated with the electrocoat bake oven station 104 is based on one or more images acquired by the set of infrastructure sensors 208 associated with monitoring the progress of the vehicle 202 through the electrocoat bake oven station 104.

[0027] The vehicle 202 can further proceed to a first inspection station 106a of the plurality of inspection stations 106a-c. The first inspection station 106a of the plurality of inspection stations 106a-c is configured to perform an inspection of the surface of the vehicle 202. Additionally, the inspection includes a set of one or more images acquired by the set of infrastructure sensors 208. Moreover, the central edge server 206 is configured to generate one or more records associated with a number, size, and / or location of any defects (e.g., one or more defects 300) on the surface of the vehicle. For example, the defects can be an over accumulation of material on the surface of the vehicle 202, an actual defect associated with the surface of the vehicle 202, or a combination thereof, among other defects. As an example, the central edge server 206 is further configured to generate one or more records associated with a number, size, and / or location of any defects on the surface of the vehicle 202 based at least on sensor data associated with the one or more images acquired by the set of infrastructure sensors 208.

[0028] For example, the one or more images acquired by the set of infrastructure sensors 208 can generate a heat map 302, as shown in Figure 3 The heat map highlights a plurality of defects 300. As another example, the heat map 302 can show a number of defects (e.g., “8 hot spots”) and can indicate a degree of each of the one or more defects 300 by changing an intensity, opacity, and / or radius of the displayed one or more defects 300. For example, the heat map 302 can be further configured to rank each of the one or more defects 300 by a degree of the defect or by any other metric.

[0029] Referring back to Figure 2The artificial intelligence system 210 is configured to determine a degree of the defect on the surface of the vehicle 202. For example, the artificial intelligence system 210 is configured to determine the degree of the defect on the surface of the vehicle 202 based on a level of repair that can be required to resolve the defect. As another example, the artificial intelligence system 210 is configured to determine the degree of the defect on the surface of the vehicle 202 based on one or more of the records and / or the sensor data. It should be appreciated that the artificial intelligence system 210 is configured to determine the degree of the defect on the surface of the vehicle 202 based on one or more of the records, the sensor data, or a combination thereof.

[0030] The artificial intelligence system 210 is further configured to predict any subsequent buildup that can accumulate on the surface of the vehicle 202. For example, the artificial intelligence system 210 is configured to predict any subsequent buildup that can accumulate or form on the surface of the vehicle 202 based on one or more historical entries stored in the database 212 of the central edge server 206. As another example, the historical entries are based on a previous determination made by the artificial intelligence system 210 regarding the degree of the defect on the surface of the vehicle 202, previous records, previous sensor data entries, or a combination thereof.

[0031] The central edge server 206 adjusts one or more predefined robotic cleaning paths of the one or more robots to provide additional cleaning to the highlighted area on the surface of the vehicle 202. For example, the central edge server 206 adjusts one or more predefined robotic cleaning paths of the one or more robots based on the artificial intelligence system 210 determining that there is an excessive level of buildup on the surface of the vehicle 202. As yet another example, the central edge server 206 adjusts one or more predefined robotic cleaning paths of the one or more robots based on the artificial intelligence system 210 predicting that there can be a subsequent excessive level of buildup on the surface of the vehicle 202. As an additional example, the one or more predefined robotic cleaning paths of the one or more robots are associated with at least the first robotic dusting station 110a of the pair of robotic workstations 110a, 110b.

[0032] The vehicle 202 then proceeds to the first defect sanding / repair workstation 108a of the pair of defect sanding / repair workstations 108a, 108b. The first defect sanding / repair workstation 108a is a workstation configured to address any defects detected on the surface of the vehicle 202. For example, in the event that one or more defects are detected on the surface of the vehicle 202, the surface of the vehicle 202 may be sanded (e.g., dry sanded) so that the one or more defects can be repaired. As an example, the central edge server 206 may cause the first defect sanding / repair workstation 108a to apply various pressures and / or various speeds of a sander to the surface of the vehicle 202 based on sensor data received from at least one sensor infrastructure 204 associated with the first defect sanding / repair workstation 108a. As another example, the sensor data received from the at least one sensor infrastructure 204 associated with the first defect sanding / repair workstation 108a is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring the progress of the vehicle 202 through the first defect sanding / repair workstation 108a.

[0033] The vehicle 202 further advances to the first robotic dusting station 110a of the pair of robotic dusting stations 110a, 110b. The first robotic dusting station 110a is configured to enable one or more robots to clean any excess debris or accumulation from the surfaces of the vehicle 202. For example, the one or more robots may be sword-brush cleaners. However, it should be understood that any other type of cleaning machine may be used to clean the surfaces of the vehicle 202.

[0034] The one or more robots associated with the first robotic dust removal workstation 110a are configured to operate based on a predefined robotic cleaning path. For example, before the paint application process begins, the one or more robots are programmed to generally clean (e.g., clean the surface of the vehicle 202 without regard to specific defects) the entire surface of the vehicle 202 at the beginning of the exemplary path 100. However, it should be understood that the one or more robots can be programmed to clean the surface of the vehicle 202 in any manner, such as, but not limited to, a targeted device for cleaning the surface of the vehicle 202, repetitive cleaning of certain areas of the surface of the vehicle 202, or a slower and / or faster method of cleaning the surface of the vehicle 202.

[0035] The one or more robots associated with the first robot dusting station 110a are also configured to operate based on any adjustments to the predefined robot cleaning path in response to the artificial intelligence system 210 determining that an excessive level of buildup is present on the surface of the vehicle 202. The one or more robots associated with the first robot dusting station 110a are also configured to operate based on any adjustments to the predefined robot cleaning path in response to the artificial intelligence system 210 predicting that a subsequent excessive level of buildup is likely to be present on the surface of the vehicle 202.

[0036] The vehicle 202 then proceeds to a primer spray station 112. The primer spray station 112 is a station configured to apply primer on the surface of the vehicle 202. For example, the primer can be applied by a sprayer to evenly apply across the entire surface of the vehicle 202. The central edge server 206 can cause the primer spray station 112 to apply one or more layers of primer to the surface of the vehicle 202 based on sensor data received from at least one sensor infrastructure 204 associated with the primer spray station 112. As another example, the sensor data received from at least one sensor infrastructure 204 associated with the primer spray station 112 is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring the progress of the vehicle 202 through the primer spray station 112.

[0037] The vehicle 202 then proceeds to a primer oven station 114. The primer oven station 114 is a station configured to cure the primer applied to the surface of the vehicle 202 by baking the surface of the vehicle 202. For example, the baking time can be any duration. As another example, the baking process can occur at any temperature. As an additional example, the central edge server 206 can cause the primer oven station 114 to change the temperature and / or baking time of the baking process based on sensor data received from at least one sensor infrastructure 204 associated with the primer oven station 114. As another example, the sensor data received from at least one sensor infrastructure 204 associated with the primer oven station 114 is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring the progress of the vehicle 202 through the primer oven station 114.

[0038] The vehicle 202 further advances to a second inspection station 106b of the plurality of inspection stations 106a-c. Similar to the first inspection station 106a, the second inspection station 106b of the plurality of inspection stations 106a-c is configured to perform another inspection of the surface of the vehicle 202. The artificial intelligence system 210 is configured to determine a degree of any new defects on the surface of the vehicle 202 (e.g., additional defects and / or any unresolved defects that have arisen since the vehicle 202 advanced through the first robotic dusting station 110a). For example, the artificial intelligence system 210 is configured to determine the degree of the new defects on the surface of the vehicle 202 based on a level of repair that can be needed to resolve the new defects. As another example, the artificial intelligence system 210 is configured to determine the degree of the new defects on the surface of the vehicle 202 based on one or more records and / or sensor data. It should be appreciated that the artificial intelligence system 210 is configured to determine the degree of the new defects on the surface of the vehicle 202 based on one or more records, sensor data, the degree of the new defects on the surface of the vehicle 202, or a combination thereof.

[0039] The artificial intelligence system 210 is further configured to predict any subsequent build-up that can accumulate on the surface of the vehicle 202 when the vehicle 202 advances through the primer spray station 112 and the primer oven station 114. For example, the artificial intelligence system 210 is configured to predict any subsequent build-up that can accumulate on the surface of the vehicle 202 based on one or more historical entries stored in the database 212 of the central edge server 206. As another example, the historical entries are based on the previous determination made by the artificial intelligence system 210 regarding the degree of the new defects on the surface of the vehicle 202, previous records, previous sensor data entries, or a combination thereof.

[0040] The central edge server 206 adjusts the one or more predefined robotic cleaning paths of the one or more robots based on the determination by the artificial intelligence system 210 that there is an excessive level of build-up on the surface of the vehicle 202. As yet another example, the central edge server 206 adjusts the one or more predefined robotic cleaning paths of the one or more robots based on the prediction by the artificial intelligence system 210 that there can be a subsequent excessive level of build-up on the surface of the vehicle 202. As an additional example, the one or more predefined robotic cleaning paths of the one or more robots are associated with at least the second robotic dusting station 110b of the pair of robotic stations 110a, 110b.

[0041] The vehicle 202 then proceeds to a second defect sanding / repair station 108b of the pair of defect sanding / repair stations 108a, 108b. The second defect sanding / repair station 108b is a station that is configured to address new defects detected on the surface of the vehicle 202. For example, in instances in which one or more new defects are detected on the surface of the vehicle 202, sanding (e.g., dry sanding) can be performed on the surface of the vehicle 202 such that the one or more new defects can be repaired. As an example, the central edge server 206 can cause the second defect sanding / repair station 108b to apply various pressures and / or various speeds of a sander to the surface of the vehicle 202 based on sensor data received from at least one sensor infrastructure 204 associated with the second defect sanding / repair station 108b. As another example, the sensor data received from at least one sensor infrastructure 204 associated with the second defect sanding / repair station 108b is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring progress of the vehicle 202 through the second defect sanding / repair station 108b.

[0042] The vehicle 202 then proceeds to a second robotic dusting station 110b of the pair of robotic dusting stations 110a, 110b. Similar to the first robotic dusting station 110a, the second robotic dusting station 110b is configured to enable one or more robots to clean any excess debris or buildup from the surface of the vehicle 202. The one or more robots associated with the second robotic dusting station 110b are also configured to operate based on any adjustments to a predefined robotic cleaning path based at least on the artificial intelligence system 210 determining that an excess level of buildup was present on the surface of the vehicle 202 as the vehicle 202 proceeded through at least the primer spraying station 112 and the primer oven station 114. The one or more robots associated with the second robotic dusting station 110b are also configured to operate based on any adjustments to a predefined robotic cleaning path based at least on the artificial intelligence system 210 predicting that a subsequent excess level of buildup can be present on the surface of the vehicle 202 as the vehicle 202 proceeds through at least the primer spraying station 112 and the primer oven station 114.

[0043] The vehicle 202 then proceeds to the enamel spray station 116. The enamel spray station 116 is a station configured to apply enamel paint to the surface of the vehicle 202. For example, the enamel paint can be applied by another sprayer to evenly apply across the entire surface of the vehicle 202. The central edge server 206 can cause the enamel spray station 116 to apply one or more layers of enamel paint to the surface of the vehicle 202 based on sensor data received from the at least one sensor infrastructure 204 associated with the enamel spray station 116. As another example, the sensor data received from the at least one sensor infrastructure 204 associated with the enamel spray station 116 is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring the progress of the vehicle 202 through the enamel spray station 116.

[0044] The vehicle 202 then proceeds to the enamel oven station 118. The enamel oven station 118 is a station configured to cure the enamel paint applied to the surface of the vehicle 202 by baking the surface of the vehicle 202. For example, the baking time can be any duration. As another example, the baking process can occur at any temperature. As an additional example, the central edge server 206 can cause the enamel oven station 118 to change the temperature and / or baking time of the baking process based on sensor data received from the at least one sensor infrastructure 204 associated with the enamel oven station 118. As another example, the sensor data received from the at least one sensor infrastructure 204 associated with the enamel oven station 118 is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring the progress of the vehicle 202 through the enamel oven station 118.

[0045] The vehicle 202 further advances to a third inspection station 106c of the plurality of inspection stations 106a-c. Similar to the first inspection station 106a and the second inspection station 106b, the third inspection station 106c of the plurality of inspection stations 106a-c is configured to perform another inspection of the surface of the vehicle 202. The artificial intelligence system 210 is configured to determine a degree of any further defects on the surface of the vehicle 202 (e.g., additional defects that have appeared since the vehicle 202 advanced through the second robotic dusting station 110b and / or any unresolved defects). For example, the artificial intelligence system 210 is configured to determine the degree of the further defects on the surface of the vehicle 202 based on a level of repair that can be needed to resolve the further defects. As another example, the artificial intelligence system 210 is configured to determine the degree of the further defects on the surface of the vehicle 202 based on one or more records and / or sensor data. It should be appreciated that the artificial intelligence system 210 is configured to determine the degree of the further defects on the surface of the vehicle 202 based on one or more records, sensor data, the degree of the further defects on the surface of the vehicle 202, or a combination thereof.

[0046] The artificial intelligence system 210 is further configured to predict any subsequent build-up that can accumulate on the surface of the vehicle 202 when the vehicle 202 advances through the enamel spray station 116 and the enamel oven station 118. For example, the artificial intelligence system 210 is configured to predict any subsequent build-up that can accumulate on the surface of the vehicle 202 based on one or more historical entries stored in the database 212 of the central edge server 206. As another example, the historical entries are based on a previous determination made by the artificial intelligence system 210 regarding the degree of the further defects on the surface of the vehicle 202, previous records, previous sensor data entries, or a combination thereof.

[0047] The central edge server 206 adjusts the one or more predefined robotic cleaning paths of the one or more robots based on the determination by the artificial intelligence system 210 that there is an excessive level of build-up on the surface of the vehicle 202. As yet another example, the central edge server 206 adjusts the one or more predefined robotic cleaning paths of the one or more robots based on the prediction by the artificial intelligence system 210 that there can be a subsequent excessive level of build-up on the surface of the vehicle 202. As an additional example, the one or more predefined robotic cleaning paths of the one or more robots are associated with at least the second robotic dusting station 110b of the pair of robotic stations 110a, 110b.

[0048] The vehicle 202 then proceeds to the defect wet sanding / polishing station 120. The defect wet sanding / polishing station 120 is a station configured to address any new and / or further defects detected on the surface of the vehicle 202. For example, in cases where one or more defects are detected on the surface of the vehicle 202, the surface of the vehicle 202 can be sanded (e.g., wet sanded) such that the one or more defects can be polished. As an example, the central edge server 206 can cause the defect wet sanding / polishing station 120 to apply various pressures and / or various speeds of a sander to the surface of the vehicle 202 based on sensor data received from at least one sensor infrastructure 204 associated with the defect wet sanding / polishing station 120. As another example, the sensor data received from at least one sensor infrastructure 204 associated with the defect wet sanding / polishing station 120 is based on one or more images acquired by a set of infrastructure sensors 208 associated with monitoring the progress of the vehicle 202 through the defect wet sanding / polishing station 120.

[0049] For example, the central edge server 206 is also configured to determine whether the surface of the vehicle 202 is acceptable for delivery of the vehicle 202 for use by a consumer. As another example, the artificial intelligence system 210 can also be configured to learn what manual operators approve of for delivery of the vehicle 202 for use by a consumer such that the central edge server 206 can autonomously determine whether the surface of the vehicle 202 is acceptable for delivery of the vehicle 202 for use by a consumer. As a further example, the central edge server 206 can also be programmed with parameters that only allow for delivery of the vehicle 202 for use by a consumer if the defect level is below a certain threshold (e.g., substantially non-existent).

[0050] In cases where the central edge server 206 determines that the surface of the vehicle 202 is not acceptable for delivery of the vehicle 202 for use by a consumer, the central edge server 206 can cause the vehicle 202 to proceed back to the second robotic dusting station 110b, the enamel spray station 116, the enamel oven station 118, the third inspection station 106c, and / or the defect wet sanding / polishing station 120. It should be understood that while the vehicle 202 can be described as proceeding through one or more stations of the paint application process in a particular order, the vehicle 202 can proceed through one or more stations of the paint application process in any order. It should also be understood that the paint application process can include any other stations for any other processes associated with the paint application process.

[0051] Figure 4is a flowchart illustrating an example method 400 for optimizing a paint application process. At operation 402, a first set of data is received. For example, the first set of data is received from a first inspection station (e.g., the first inspection station 106a). However, it should be appreciated that the first set of data can be received from any inspection station (e.g., the second inspection station 106b and / or the third inspection station 106c). As another example, the first set of data is associated with a surface condition of a vehicle (e.g., the vehicle 202). As another example, the first set of data includes an amount of defects associated with a first instance of one or more defects, a size of each defect of the first instance of one or more defects, a first instance of one or more defects, or a combination thereof.

[0052] At operation 404, a degree of the first instance of one or more defects on the surface of the vehicle is determined. For example, the degree of the first instance of one or more defects on the surface of the vehicle is determined by an artificial intelligence system. As another example, the determination of the degree of the first instance of one or more defects on the surface of the vehicle is based on the first set of data.

[0053] At operation 406, a path followed by one or more robots is updated. For example, the path followed by the one or more robots is updated based on the determination of the degree of the first instance of one or more defects, as described herein. As another example, the update to the path causes the one or more robots to initiate a remedial action to address the first instance of one or more defects to a target portion of the surface of the vehicle, as described herein. That is, the remedial action, for example, removes the first instance of one or more defects. As an additional example, the remedial action includes a sanding process, a polishing process, or a combination thereof, and wherein the first instance and the second instance of one or more defects include a portion of the surface of the vehicle that includes excess dust, excess dirt, excess debris, or a combination thereof.

[0054] As yet another example, the update to the path can include inserting an additional cleaning step. As another example, in the case of each step of a predefined paint application process, the artificial intelligence system 210 can add an additional cleaning step based on the sensor data. Further, the central edge server 206 can be configured to cause the vehicle 202 to pause progress through the paint application process, stop progress through the paint application process, and / or re-route through the paint application process (e.g., travel to another workstation than the one predefined as part of the paint application process). For example, the central edge server 206 is configured to cause the vehicle 202 to pause progress through the paint application process, stop progress through the paint application process, and / or re-route through the paint application process by transmitting one or more instructions and / or one or more signals to the vehicle 202. As another example, in the case where the vehicle 202 is an autonomous vehicle that is remotely dispatched through a finishing plant process, the one or more instructions and / or one or more signals received from the central edge server 206 can cause the vehicle 202 to pause progress through the paint application process, stop progress through the paint application process, and / or re-route through the paint application process. As an additional example, in the case where the vehicle 202 is a hybrid autonomous vehicle or not an autonomous vehicle at all, the one or more instructions and / or one or more signals received from the central edge server 206 can prompt an operator of the vehicle 202 to manually cause the vehicle 202 to pause progress through the paint application process, stop progress through the paint application process, and / or re-route through the paint application process. As a further example, the update to the path can include any adjustment to the predefined robotic cleaning path based at least on the artificial intelligence system 210 determining that there is an excessive level of buildup on the surface of the vehicle 202.

[0055] In example embodiments, an amount of debris predicted to result from the remedial action is predicted. For example, the amount of debris predicted to result from the remedial action is predicted by the artificial intelligence system. As yet another example, the update to the path followed by the one or more robots is further based on the predicted amount of debris. It will be appreciated that the update to the path followed by the one or more robots is based on the determination of the extent of the first instance of the one or more defects and / or the predicted amount of debris.

[0056] In another example embodiment, a second set of data is received. For example, the second data is received from a second inspection station. As another example, the second set of data is associated with a surface condition of the vehicle. As an additional example, a degree of a second instance of one or more defects on the surface of the vehicle is determined. For example, the degree of the second instance of one or more defects on the surface of the vehicle is determined by the artificial intelligence system. As another example, the determination of the degree of the second instance of one or more defects on the surface of the vehicle is based on the second set of data. As yet another example, the determination of the degree of the first instance of one or more defects on the surface of the vehicle is based on the predicted amount of debris that will result from the remedial action. It will be appreciated that the determination of the degree of the first instance of one or more defects on the surface of the vehicle is based on the second set of data and / or the predicted amount of debris that will result from the remedial action. As an additional example, the path followed by the one or more robots is updated. For example, the path followed by the one or more robots is updated based on the determination of the degree of the second instance of one or more defects. As another example, the update to the path causes the one or more robots to initiate a remedial action to address the second instance of one or more defects to the target portion or another target portion of the surface of the vehicle. That is, the remedial action removes, for example, the second instance of one or more defects. As another example, the second set of data includes an amount of defects associated with the second instance of one or more defects, a size of each defect of the second instance of one or more defects, a location of each defect of the first instance of one or more defects, or a combination thereof.

[0057] Figure 5 is a flowchart illustrating an example method 500 for a paint application process. At operation 502, a set of data is received. For example, the set of data is associated with a surface condition of a vehicle (e.g., vehicle 202). As another example, the set of data is received by an inspection station (e.g., stations 106a-106c). At operation 504, a path followed by one or more robots is updated. For example, the path is updated based on a determination of a degree of a second instance of one or more defects. As another example, the update to the path can cause the one or more robots to initiate a remedial action to address an instance of one or more defects to a target portion of the surface of the vehicle. That is, the remedial action removes, for example, the one or more defects.

[0058] At operation 506, a determination is made as to whether the surface condition of the vehicle is acceptable for delivery. In instances in which the surface condition of the vehicle is acceptable for delivery, the vehicle is delivered for use by a consumer at operation 508. However, in instances in which the surface condition of the vehicle is not acceptable for delivery, each of the operations of the example method 500 are repeated until the surface condition of the vehicle is acceptable for delivery for use by a consumer, as described in greater detail herein.

[0059] Accordingly, one or more examples of the present disclosure provide a means for optimizing a paint application process. For example, by using an artificial intelligence system (e.g., artificial intelligence system 210), targeted cleaning efforts can be applied to the surface of a vehicle (e.g., vehicle 202) as the vehicle progresses through one or more stations associated with the paint application process.

[0060] Unless specifically stated otherwise as apparent from the foregoing disclosure, all measurements, ratings, percentages, and other representations of amounts, dimensions, and / or characteristics of materials, components, and / or properties described herein are understood to be modified by the word "about" or "approximately.” Such modifications are made to allow for variations in, for example, industrial practice, material tolerances, machine and / or human error, and alterations made yet still provide a desired function.

[0061] As used herein, the phrase at least one of A, B, and C should be construed to mean a logical (A OR B OR C) using the non-exclusive logical OR, and should not be construed to mean “A AND B AND C1” or “A AND B OR C” or “A AND B AND NOT C” or “A AND NOT B AND NOT C.”

[0062] In this application, the terms “controller” and / or “module” can refer to, be part of, or include an Application Specific Integrated Circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinational logic circuit; a field programmable gate array (FPGA); a processor circuit (shared, dedicated, or group) that executes code; a memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system-on-chip.

[0063] The term memory is a subset of the term computer-readable medium. The term computer-readable medium, as used herein, does not encompass transitory propagating signals or electromagnetic waves through a medium, such as on a carrier. Thus, the term computer-readable medium can be considered tangible and non-transitory. Non-limiting examples of non-transitory, tangible computer-readable media are nonvolatile memory circuits (such as flash memory circuits, erasable programmable read only memory (EPROM) circuits, or mask read only circuits), volatile memory circuits (such as static random access memory (SRAM) circuits or dynamic random access memory (DRAM) circuits), magnetic storage media (such as analog magnetic tapes or digital magnetic tapes or hard disk drives), and optical storage media (such as optical discs like CDs, DVDs, or Blu-ray discs).

[0064] The apparatus and methods described in this application can be partially or entirely implemented by special purpose computers configured to create a general purpose computer that is configured to perform one or more specific functions embodied in the computer program. The functional blocks, flowchart components, and other elements described above serve as software specifications which can be translated into computer programs by routine work of a skilled programmer or engineer.

[0065] The description of the present disclosure is merely exemplary in nature and, thus, variations that do not depart from the essence of the present disclosure are intended to be within the scope of the present disclosure. Such variations are not to be regarded as a departure from the spirit and scope of the present disclosure.

[0066] According to the present disclosure, one or more non-transitory computer-readable media storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to: receive, from a first inspection workstation, a first set of data associated with a surface condition of a vehicle; determine, by an artificial intelligence system, a degree of a first instance of one or more defects on a surface of the vehicle based on the first set of data; and update a path followed by one or more robots based on the determination of the degree of the first instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate a remedial action to the target portion of the surface of the vehicle to address the first instance of the one or more defects.

[0067] According to one embodiment, the first set of data includes an amount of defects associated with the first instance of the one or more defects, a size of each defect of the first instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof.

[0068] According to one embodiment, the at least one processor is further caused to: predict, by the artificial intelligence system, an amount of debris that will result from the remedial action, wherein the update to the path followed by the one or more robots is further based on the predicted amount of debris.

[0069] According to one embodiment, the at least one processor is further caused to: receive, from a second inspection workstation, a second set of data associated with the surface condition of the vehicle; determine, by the artificial intelligence system, a degree of a second instance of one or more defects on the surface of the vehicle based on the second set of data and a predicted amount of debris that will result from the remedial action; and update the path followed by the one or more robots based on the determination of the degree of the second instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate the remedial action to the at least one of the target portion or another target portion of the surface of the vehicle to address the second instance of the one or more defects.

[0070] According to one embodiment, the second set of data includes an amount of defects associated with the second instance of the one or more defects, a size of each defect of the second instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof.

[0071] According to one embodiment, the remedial action includes a sanding process, a polishing process, or a combination thereof, and wherein the first instance and the second instance of the one or more defects include a portion of the surface of the vehicle that includes an excess amount of dust, an excess amount of dirt, an excess amount of debris, or a combination thereof.

Claims

1. A method comprising: receiving, from a first inspection station, a first set of data associated with a surface condition of a vehicle; determining, by an artificial intelligence system, a degree of a first instance of one or more defects on a surface of the vehicle based on the first set of data; and updating a path followed by one or more robots based on the determination of the degree of the first instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate a remedial action to the target portion of the surface of the vehicle to address the first instance of the one or more defects.

2. The method of claim 1, wherein the first set of data comprises a quantity of defects associated with the first instance of the one or more defects, a size of each defect of the first instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof.

3. The method of claim 1, further comprising: predicting, by the artificial intelligence system, a quantity of debris that will result from the remedial action.

4. The method of claim 3, wherein the update to the path followed by the one or more robots is further based on the predicted quantity of debris.

5. The method of claim 1, further comprising: receiving, from a second inspection station, a second set of data associated with the surface condition of the vehicle; determining, by the artificial intelligence system, a degree of a second instance of one or more defects on the surface of the vehicle based on the second set of data and the predicted quantity of debris that will result from the remedial action; and updating the path followed by the one or more robots based on the determination of the degree of the second instance of the one or more defects.

6. The method of claim 5, wherein the update to the path causes the one or more robots to initiate the remedial action to the target portion or another target portion of the surface of the vehicle to address the second instance of the one or more defects.

7. The method of claim 5, wherein the second set of data comprises a quantity of defects associated with the second instance of the one or more defects, a size of each defect of the second instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof.

8. The method of claim 5, wherein the remedial action comprises a sanding process, a polishing process, or a combination thereof, and wherein the first instance and the second instance of the one or more defects comprise a portion of the surface of the vehicle that includes an excess of dust, an excess of dirt, an excess of debris, or a combination thereof.

9. A system comprising: an infrastructure system configured to: receive, from a first inspection station, a first set of data associated with a surface condition of a vehicle, determine, by an artificial intelligence system, a degree of a first instance of one or more defects on a surface of the vehicle based on the first set of data, update a path followed by one or more robots based on the determination of the extent of the first instance of the one or more defects; the first inspection station is configured to: identify the first set of data; and send the first set of data to the infrastructure system; and the one or more robots are configured to: initiate a remedial action to the target portion of the surface of the vehicle based on the update to the path to address the first instance of the one or more defects.

10. The system of claim 9, wherein the first set of data includes an amount of defects associated with the first instance of the one or more defects, a size of each defect of the first instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof.

11. The system of claim 9, wherein the infrastructure system is further configured to: predict, by the artificial intelligence system, an amount of debris that will result from the remedial action.

12. The system of claim 11, wherein the update to the path followed by the one or more robots is further based on the predicted amount of debris.

13. The system of claim 9, wherein the infrastructure system is further configured to: receive, from a second inspection station, a second set of data associated with the surface condition of the vehicle; determine, by the artificial intelligence system, an extent of a second instance of one or more defects on the surface of the vehicle based on the second set of data and a predicted amount of debris that will result from the remedial action; and update the path followed by the one or more robots based on the determination of the extent of the second instance of the one or more defects, wherein the update to the path causes the one or more robots to initiate the remedial action to at least one of the target portion of the surface of the vehicle or another target portion to address the second instance of the one or more defects.

14. The system of claim 13, wherein the second set of data includes an amount of defects associated with the second instance of the one or more defects, a size of each defect of the second instance of the one or more defects, a location of each defect of the first instance of the one or more defects, or a combination thereof.

15. The system of claim 13, wherein the remedial action includes a sanding process, a polishing process, or a combination thereof, and wherein the first instance and the second instance of the one or more defects include a portion of the surface of the vehicle that includes an excess amount of dust, an excess amount of dirt, an excess amount of debris, or a combination thereof.

Images