System and method for evaluating external quality of vehicle

Abstract

The invention provides a system and a method for evaluating external quality of a vehicle. A method is disclosed. An infrastructure system for obtaining a first set of images of an exterior of one or more vehicles, determining a condition of the exterior of the one or more vehicles by an automated vehicle grouping algorithm of the infrastructure system, and causing the one or more vehicles to navigate toward a waypoint and capture one or more characteristics associated with the one or more vehicles.

Description

Technical Field

[0001] The present disclosure relates to the assessment of the condition of the exterior of a formation vehicle. More specifically, the present disclosure relates to systems and methods for forming vehicle formations to specific waypoints based on the condition of the exterior of the formation vehicle. Background Art

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

[0003] During vehicle development and use, there may be inefficiencies associated with identifying exterior quality issues at multiple points. For example, manual inspection of vehicles at a manufacturing plant may potentially result in inadvertently missing exterior quality inspections and / or not inspecting the exterior of the vehicle as frequently as needed. As another example, failure to report problems with vehicles in a dealership warehouse may result in exterior quality issues with the vehicles going unreported, which may lead to delays in repairs. As an additional example, inspection of the exterior quality of a vehicle before and / or after a rental car or car valet service may lead to issues regarding determination of the party at fault in the event of any quality issues associated with the exterior of the vehicle. Such issues may be caused, for example, by problems with documentation related to the exterior of the vehicle at various points of ownership.

[0004] The present disclosure addresses these and other problems related to the assessment and / or documentation of the condition of the exterior quality of a vehicle and vehicle formation. Summary of the Invention

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

[0006] The present disclosure provides a method, the method comprising: obtaining, by one or more sensors of an infrastructure system, a first image set of the exterior of one or more vehicles; determining, by an automated vehicle marshalling algorithm of the infrastructure system, the condition of the exterior of one or more vehicles, wherein the determination of the condition of the exterior of one or more vehicles is based on the first image set; and causing, based on the condition of the exterior of one or more vehicles not meeting a quality inspection, one or more vehicles to navigate towards a waypoint and capture one or more characteristics associated with one or more vehicles; the method further comprising: determining whether the condition meets the quality inspection; wherein the condition of one or more vehicles includes the condition of vehicle painting, one or more vehicle dents, misalignment of vehicle exterior parts, incorrect decorative packaging associated with one or more vehicles, or a combination thereof; the method further comprising: transmitting, based on the condition of the exterior of one or more vehicles not meeting the quality inspection, the marshalling status of one or more vehicles to a vehicle manufacturing cloud system; and causing, based on the transmission of the marshalling status of one or more vehicles, the vehicle manufacturing cloud system to store the first image set of the exterior of one or more vehicles; the method further comprising: receiving, from one or more vehicles, one or more characteristics, wherein the one or more characteristics are used as investigation evidence associated with the condition of the exterior of one or more vehicles, and wherein the one or more characteristics include the position associated with one or more vehicles, a snapshot record of the exterior of one or more vehicles, or a combination thereof; the method further comprising: obtaining, by one or more sensors of the infrastructure system, a second image set of the exterior of one or more vehicles; comparing the first image set with the second image set by the automated vehicle marshalling algorithm and a neural network module of the infrastructure system; and determining, based on the comparison of the first image set with the second image set, the difference between the first image set and the second image set, wherein the result of the determination of the difference between the first image set and the second image set is saved in a database associated with the infrastructure system, and wherein the saved result is used as investigation evidence associated with the condition of the exterior of one or more vehicles; wherein the one or more characteristics associated with one or more vehicles are captured via one or more vehicle sensors.

[0007] The present disclosure provides a system, the system comprising: an infrastructure system configured to: obtain a first image set of the exterior of one or more vehicles via one or more sensors of the infrastructure system; determine the condition of the exterior of the one or more vehicles through an automated vehicle marshalling algorithm of the infrastructure system, wherein the determination of the condition of the exterior of the one or more vehicles is based on the first image set; and cause the one or more vehicles to navigate towards a waypoint and capture one or more characteristics associated with the one or more vehicles based on the condition of the exterior of the one or more vehicles not meeting a quality inspection; a vehicle manufacturing cloud system configured to: receive the marshalling status of the one or more vehicles and store the first image set of the exterior of the one or more vehicles; and one or more vehicles configured to: capture one or more characteristics via one or more vehicle sensors and transmit the one or more characteristics; further comprising: determining whether the condition meets a quality inspection; wherein the condition of the one or more vehicles includes the condition of vehicle painting, one or more vehicle dents, misalignment of vehicle exterior parts, incorrect decorative packaging associated with the one or more vehicles, or a combination thereof; wherein the infrastructure system is further configured to: transmit the marshalling status of the one or more vehicles based on the condition of the exterior of the one or more vehicles not meeting a quality inspection; and cause the vehicle manufacturing cloud system to store the first image set of the exterior of the one or more vehicles based on the transmission of the marshalling status of the one or more vehicles; wherein the infrastructure system is further configured to: receive one or more characteristics, wherein the one or more characteristics are used as investigative evidence associated with the condition of the exterior of the one or more vehicles, and wherein the one or more characteristics include the position associated with the one or more vehicles, a snapshot record of the exterior of the one or more vehicles, or a combination thereof; wherein the infrastructure system is further configured to: obtain a second image set of the exterior of the one or more vehicles via one or more sensors of the infrastructure system; compare the first image set with the second image set through the automated vehicle marshalling algorithm and a neural network module of the infrastructure system; and determine the difference between the first image set and the second image set based on the comparison of the first image set with the second image set, wherein the result of the determination of the difference between the first image set and the second image set is saved in a database associated with the infrastructure system, and wherein the saved result is used as investigative evidence associated with the condition of the exterior of the one or more vehicles.

[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: obtain a first set of images of the exterior of one or more vehicles via one or more sensors of an infrastructure system; determine a condition of the exterior of the one or more vehicles via an automated vehicle marshalling algorithm of the infrastructure system, wherein the determination of the condition of the exterior of the one or more vehicles is based on the first set of images; and cause the one or more vehicles to navigate towards a waypoint and capture one or more characteristics associated with the one or more vehicles based on the condition of the exterior of the one or more vehicles not meeting a quality check; wherein the at least one processor is further caused to: determine whether the condition meets the quality check; wherein the condition of the one or more vehicles includes a condition of vehicle painting, one or more vehicle dents, misalignment of vehicle exterior parts, incorrect decorative packaging associated with the one or more vehicles, or a combination thereof; wherein the at least one processor is further caused to: transmit a marshalling status of the one or more vehicles to a vehicle manufacturing cloud system based on the condition of the exterior of the one or more vehicles not meeting the quality check; and cause the vehicle manufacturing cloud system to store the first set of images of the exterior of the one or more vehicles based on the transmission of the marshalling status of the one or more vehicles; wherein the at least one processor is further caused to: receive one or more characteristics from the one or more vehicles, wherein the one or more characteristics serve as investigative evidence associated with the condition of the exterior of the one or more vehicles, and wherein the one or more characteristics include a location associated with the one or more vehicles, a snapshot record of the exterior of the one or more vehicles, or a combination thereof; wherein the at least one processor is further caused to: obtain a second set of images of the exterior of the one or more vehicles via one or more sensors of the infrastructure system; compare the first set of images with the second set of images via the automated vehicle marshalling algorithm and a neural network module of the infrastructure system; and determine a difference between the first set of images and the second set of images based on the comparison of the first set of images with the second set of images, wherein a result of the determination of the difference between the first set of images and the second set of images is saved in a database associated with the infrastructure system, and wherein the saved result serves as investigative evidence associated with the condition of the exterior of the one or more vehicles, and wherein the one or more characteristics associated with the one or more vehicles are captured via one or more vehicle sensors.

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

[0010] For a better understanding of the present disclosure, various forms of the present disclosure will now be described by way of example with reference to the accompanying drawings, in which:

[0011] Figure 1 shows an overall system for automated vehicle platooning according to various embodiments;

[0012] Figure 2 shows an example system for platooning one or more vehicles according to various embodiments;

[0013] Figure 3 shows according to various embodiments associated with Figure 1 and Figure 2 the example vehicle associated with the system shown;

[0014] Figures 4 to 7 shows additional example systems for platooning one or more vehicles according to various embodiments; and

[0015] Figure 8 is a flowchart showing an example method for evaluating the external condition of any one of one or more vehicles according to various embodiments.

[0016] The figures described herein are for illustrative purposes 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 figures, corresponding reference numerals indicate the same or corresponding parts and features.

[0018] The present disclosure provides a means for infrastructure-based sensing that facilitates autonomous functions while obtaining additional information related to the state of the exterior of a vehicle. For example, in a manufacturing facility, multiple (e.g., repeated) quality checks associated with the exterior of a vehicle are performed by one or more sensors of at least one infrastructure system, rather than a single manual visual inspection. Quality checks associated with the exterior of a vehicle can result in a more accurate process than a single manual visual inspection. As another example, by leveraging one or more sensors, reliance on a driver to timely report vehicle issues that ultimately lead to repair delays is eliminated within a dealership warehouse. As other examples, automatic inspections of a vehicle are performed immediately when the vehicle departs a rental car agency and when the vehicle returns, creating an objective comparison at different points in time. As yet another example, customer concerns can be alleviated by performing an automated visual inspection of a vehicle when the vehicle arrives at and departs from an automated parking depot, which can also reduce the likelihood of an incorrect insurance claim being filed by a vehicle owner and / or a parking depot owner. For example, when a vehicle approaches a charging station, the exterior quality or condition of the vehicle can be inspected during alignment of the vehicle with the automated charging station. In this way, evidence (e.g., documentation) can be provided that no quality issues associated with the exterior of the vehicle have occurred, for example, at an autonomous charging station.

[0019] Figure 1 A schematic block diagram illustration of an autonomous vehicle marshalling (AVM) system 100 is shown. In one or more examples, the AVM system 100 marshals one or more autonomous vehicles traveling at low speed. However, it should be understood that the AVM system 100 can marshal one or more vehicles traveling at any speed. It should also be understood that the AVM system 100 can marshal semi-autonomous vehicles and / or fully autonomous vehicles.

[0020] The AVM system 100 generally includes a vehicle manufacturing cloud system 102, a vehicle delivery manager cloud system 104, a vehicle customer website portal account cloud system 106, an infrastructure system 108, and autonomous vehicles 110. The vehicle manufacturing cloud system 102 operates as a central cloud system that manages and / or facilitates any manufacturing processes associated with the autonomous vehicles 110. The vehicle manufacturing cloud system 102 communicates wirelessly with the vehicle delivery manager cloud system 104 and the infrastructure system 108. The vehicle manufacturing cloud system 102 also communicates directly wirelessly with the autonomous vehicles 110. One or more examples provide improved external vehicle quality assessment and / or documentation using one or more of the systems.

[0021] The vehicle manufacturing cloud system 102 includes an AVM algorithm 112a. The AVM algorithm 112a processes state information associated with at least the autonomous vehicle 110 among one or more autonomous vehicles. It should be understood that the AVM algorithm 112a processes state information associated with each of the one or more autonomous vehicles. The vehicle manufacturing cloud system 102 is configured to cause the infrastructure system 108 to monitor the progress of one or more autonomous vehicles (e.g., the autonomous vehicle 110) as it moves through, for example, a factory floor or a parking lot. The vehicle manufacturing cloud system 102 is also configured to cause the infrastructure system 108 to communicate with any one of the one or more autonomous vehicles. For example, the vehicle manufacturing cloud system 102 uses the AVM algorithm 112a to send instructions to the infrastructure system 108 and / or process information received from the infrastructure system 108. The vehicle manufacturing cloud system 102 is configured to cause the vehicle delivery manager cloud system 104 to facilitate the delivery of one or more autonomous vehicles to various locations. For example, the vehicle manufacturing cloud system 102 uses the AVM algorithm 112a to send instructions to the vehicle delivery manager cloud system 104 and / or process information received from the vehicle delivery manager cloud system 104.

[0022] The vehicle manufacturing cloud system 102 is also configured to cause one or more autonomous vehicles to start, stop, or pause their progress through, for example, a factory floor or a parking lot. The vehicle manufacturing cloud system 102 is also configured to control the formation speed of any one of the one or more autonomous vehicles as it passes through, for example, a factory floor or a parking lot. In some examples, the vehicle manufacturing cloud system 102 uses the AVM algorithm 112a to send instructions to the autonomous vehicle 110 and / or process information received from the autonomous vehicle 110.

[0023] The infrastructure system 108 includes an AVM algorithm 112b, one or more sensors 114, and a sensor component 116. The sensor component 116 provides communication between one or more infrastructure and one or more autonomous vehicles. For example, the sensor component 116 can utilize GPS, Wi-Fi, satellite, 3G / 4G / 5G, and / or Bluetooth TMto communicate with one or more autonomous vehicles. The sensor component 116 also communicates with one or more sensors 114 (such as, for example, one or more of cameras, lidar, radar, and / or ultrasonic devices). When one or more autonomous vehicles pass through, for example, a factory floor or a parking lot, the one or more sensors 114 monitor the movement of the autonomous vehicles. As an example, the infrastructure system 108 utilizes the AVM algorithm 112b to process information and send the information to the vehicle manufacturing cloud system 102 and / or process information received from the vehicle manufacturing cloud system 102. As another example, the infrastructure system 108 utilizes the AVM algorithm 112b to process information and send the information directly to the autonomous vehicle 110 and / or process information received from the autonomous vehicle 110. It should be understood that the infrastructure system 108 may forward instructions received from the vehicle manufacturing cloud system 102 to the autonomous vehicle 110. However, it should also be understood that the infrastructure system 108 may send instructions directly to the autonomous vehicle 110.

[0024] In addition, the infrastructure system 108 includes an infrastructure controller 115. The infrastructure controller 115 is configured to centrally control the operation of the autonomous vehicle 110. For example, the operation of the autonomous vehicle 110 includes propulsion, braking, and steering of the autonomous vehicle 110. It should be understood that the infrastructure controller 115 may be provided within the infrastructure system 108 or be external to the infrastructure system 108. For example, in a marshalling environment, the infrastructure system 108 wirelessly broadcasts marshalling infrastructure messages to the autonomous vehicle 110. As another example, marshalling infrastructure messages are broadcast via a vehicle-to-everything (V2X) protocol. However, it should be understood that any communication means (including any communication protocol) may be used to broadcast marshalling infrastructure messages.

[0025] The autonomous vehicle 110 includes one or more systems or components that implement or use the AVM algorithm 112c, a wireless transmission module 118, a vehicle central gateway module 120, a vehicle infotainment system 122, one or more vehicle sensors 124, a vehicle battery 126, a vehicle global navigation satellite system (GNSS) 128, a vehicle navigation map 130, and a vehicle CAN bus 132. The wireless transmission module 118 may be a transmission control unit. The wireless transmission module 118 includes one or more sensors configured to collect data and send signals to other components of the autonomous vehicle 110. One or more sensors of the wireless transmission module 118 may include a vehicle speed sensor (not shown) configured to determine the current speed of the autonomous vehicle 110; a wheel speed sensor (not shown) configured to determine whether the autonomous vehicle 110 is traveling uphill or downhill; a throttle position sensor (not shown) that determines whether a downshift or upshift of one or more gears associated with the autonomous vehicle 110 is required in the current state of the autonomous vehicle 110; and / or a turbine speed sensor (not shown) configured to send data associated with the rotational speed of the torque converter of the autonomous vehicle 110. The wireless transmission module 118 transmits the information obtained by the one or more sensors to the AVM algorithm 112c. For example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the information collected by the one or more sensors and send the information to the infrastructure system 108. As another example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the information obtained by the one or more sensors and send the information directly to the vehicle manufacturing cloud system 102. The AVM algorithm 112c is configured to transmit the information and / or instructions received from the infrastructure system 108 and / or the vehicle manufacturing cloud system 102 to the wireless transmission module 118.

[0026] The vehicle central gateway module 120 operates as an interface between various vehicle domain bus systems, such as an engine compartment bus (not shown), an interior bus (not shown), an optical bus for multimedia (not shown), a diagnostic bus for maintenance (not shown), or the vehicle CAN bus 132. The vehicle central gateway module 120 is configured to distribute data transmitted to the vehicle central gateway module 120 by each of the various domain bus systems to other components of the autonomous vehicle 110. The vehicle central gateway module 120 is further configured to distribute information received from the AVM algorithm 112c to the various domain bus systems. The vehicle central gateway module 120 is further configured to send information received from the various domain bus systems to the AVM algorithm 112c. For example, the autonomous vehicle 110 utilizes the AVM algorithm 112c to process the information received from the vehicle central gateway module 120 and send the information to the infrastructure system 108. As another example, the autonomous vehicle 110 utilizes the AVM algorithm 112c to process the information received from the vehicle central gateway module 120 and send the information directly to the vehicle manufacturing cloud system 102. The AVM algorithm 112c is configured to transmit information and / or instructions received from the infrastructure system 108 and / or the vehicle manufacturing cloud system 102 to the vehicle central gateway module 120.

[0027] The vehicle infotainment system 122 is a system that delivers a combination of information, entertainment content, and / or services to the operator 144 of the autonomous vehicle 110. It should be understood that in some examples, the vehicle infotainment system 122 may deliver entertainment content to the operator 144 of the autonomous vehicle 110. It should also be understood that in some examples, the vehicle infotainment system 122 may deliver information services to the operator 144 of the autonomous vehicle 110. In one or more examples, the vehicle infotainment system 122 includes an in-vehicle computer that combines one or more functions, such as a digital radio, a built-in camera, and / or a television. The vehicle infotainment system 122 transmits information associated with the in-vehicle computer or processor to the AVM algorithm 112c. For example, the autonomous vehicle 110 utilizes the AVM algorithm 112c to process the information received from the vehicle infotainment system 122 and send the information to the infrastructure system 108. As another example, the autonomous vehicle 110 utilizes the AVM algorithm 112c to process the information received from the vehicle infotainment system 122 and send the information directly to the vehicle manufacturing cloud system 102. The AVM algorithm 112c is configured to transmit information and / or instructions received from the infrastructure system 108 and / or the vehicle manufacturing cloud system 102 to the vehicle infotainment system 122.

[0028] One or more vehicle sensors 124 can be, for example, one or more of a camera, lidar, radar, and / or ultrasonic device. For example, an ultrasonic device used as one or more vehicle sensors 124 emits high-frequency sound waves that strike an object (e.g., a wall or another vehicle) and then are reflected back to the autonomous vehicle 110. Based on the amount of time it takes for the sound waves to return to the autonomous vehicle 110, the autonomous vehicle 110 can determine the distance between one or more vehicle sensors 124 and the object. As another example, a camera device used as one or more vehicle sensors 124 provides a visual indication of the space around the autonomous vehicle 110. As an additional example, a radar device used as one or more vehicle sensors 124 emits an electromagnetic wave signal that strikes an object and then is reflected back to the autonomous vehicle 110. Based on the amount of time it takes for the electromagnetic wave to return to the autonomous vehicle 110, the autonomous vehicle 110 can determine the range, speed, and angle of the autonomous vehicle 110 relative to the object.

[0029] One or more vehicle sensors 124 transmit information associated with the position and / or distance of the autonomous vehicle 110 relative to an object to the AVM algorithm 112c. For example, the vehicle 110 utilizes the AVM algorithm 112c to process the information received from one or more vehicle sensors 124 and send the information to the infrastructure system 108. As another example, the autonomous vehicle 110 utilizes the AVM algorithm 112c to process the information received from one or more vehicle sensors 124 and send the information to the vehicle manufacturing cloud system 102. The AVM algorithm 112c is configured to transmit information and / or instructions received from the infrastructure system 108 and / or the vehicle manufacturing cloud system 102 to one or more vehicle sensors 124.

[0030] The vehicle battery 126 is controlled by a battery management system (not shown) that provides instructions to the vehicle battery 126. For example, the battery management system provides instructions to the vehicle battery 126 based on the temperature of the vehicle battery 126. The battery management system ensures that the current mode of the vehicle battery 126 is acceptable. For example, an acceptable current mode prevents overvoltage, overcharging, and / or overheating of the vehicle battery 126. As another example, the temperature of the vehicle battery 126 indicates to the battery management system whether any of the acceptable current modes are within an acceptable temperature range. The battery management system associated with the vehicle battery 126 transmits information associated with the temperature of the vehicle battery 126 to the AVM algorithm 112c. For example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the received information about the vehicle battery 126 and send the information to the infrastructure system 108. As another example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the information about the vehicle battery 126 and send the information directly to the vehicle manufacturing cloud system 102. The AVM algorithm 112c is configured to transmit to the vehicle battery 126 the information and / or instructions received from the infrastructure system 108 and / or the vehicle manufacturing cloud system 102.

[0031] The vehicle GNSS 128 is configured to communicate with satellites such that the autonomous vehicle 110 can determine the specific location of the autonomous vehicle 110. The vehicle navigation map 130 can display the specific location of the autonomous vehicle 110 to the operator 144 via a display screen (not shown). The vehicle GNSS 128 transmits geographical information associated with the autonomous vehicle 110 to the AVM algorithm 112c. For example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the information received from the vehicle GNSS 128 and send the information to the infrastructure system 108. As another example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the information from the vehicle GNSS 128 and send the information directly to the vehicle manufacturing cloud system 102. The AVM algorithm 112c is configured to transmit to the vehicle GNSS 128 the information and / or instructions received from the infrastructure system 108 and / or the vehicle manufacturing cloud system 102. As another example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the information associated with the vehicle navigation map 130 and send the information to the infrastructure system 108. As another example, the autonomous vehicle 110 uses the AVM algorithm 112c to process the information from the vehicle navigation map 130 and send the information directly to the vehicle manufacturing cloud system 102. The AVM algorithm 112c is configured to transmit to the vehicle navigation map 130 the information and / or instructions received from the infrastructure system 108 and / or the vehicle manufacturing cloud system 102.

[0032] The Delivery Manager Cloud System 104 communicates wirelessly (e.g., receives and / or sends instructions and / or information) with one or more of the Rental Agency Cloud System 134, the Valet Parking Agency Cloud System 136, the Insurance Agency Cloud System 138, and / or the Dealer 140. For example, the Delivery Manager Cloud System 104 can facilitate delivering one or more autonomous vehicles to any of the Rental Agency Cloud System 134, the Valet Parking Agency Cloud System 136, the Insurance Agency Cloud System 138, and / or the Dealer 140. The Delivery Manager Cloud System 104 also communicates wirelessly with the Vehicle Customer Website Portal Account Cloud System 106. It should be understood that in one or more examples, other cloud systems may be included.

[0033] The Delivery Manager Cloud System 104 communicates wirelessly with a user device 142 such as a mobile device, a display panel, and / or a computer. The autonomous vehicle 110 also communicates directly wirelessly with the user device 142. As an example, the autonomous vehicle 110 is configured to process information and / or instructions received from the user device 142. For example, the operator 144 interacts with the user device 142 via an application that organizes any information and / or instructions received from the Vehicle Customer Website Portal Account Cloud System 106 and / or the autonomous vehicle 110. As another example, the operator 144 can send one or more instructions to the Vehicle Customer Website Portal Account Cloud System 106, such as selecting which vehicle the operator 144 wants to receive from any of a rental agency (not shown) associated with the Rental Agency Cloud System 134, a valet parking agency (not shown) associated with the Valet Parking Agency Cloud System 136, an insurance agency (not shown) associated with the Insurance Agency Cloud System 138, and / or the Dealer 140.

[0034] Figure 2Shows a first example of a marshalling environment 200 that facilitates interaction between one or more autonomous vehicles 202a - 202d (e.g., autonomous vehicle 110) and one or more infrastructure systems 204a - 204e (e.g., infrastructure system 108). For example, this first example of the marshalling environment 200 is located inside or associated with a manufacturing plant. Generally, the AVM central server edge 206 (e.g., edge processor) is configured to receive one or more signals from one or more roadside units (RSUs) 208a - 208c and / or from one or more sensor infrastructure systems 204a - 204e (e.g., infrastructure system 108), while communicating with the vehicle manufacturing cloud system 102. Each of the autonomous vehicles 202a - 202d is wirelessly connected to a corresponding RSU among the one or more RSUs 208a - 208c, where each of the autonomous vehicles 202a - 202d is configured to communicate with the one or more RSUs 208a - 208c. Additionally, each of the autonomous vehicles 202a - 202d communicates wirelessly with the vehicle manufacturing cloud system 102, thereby providing each of the autonomous vehicles 202a - 202d with the ability to communicate directly with the vehicle manufacturing cloud system 102.

[0035] In some examples, one or more of the RSUs 208a - 208c are equipped with a cellular vehicle - to - infrastructure communication system (referred to as a "CV2X system"). As an example, one or more of the RSUs 208a - 208c are equipped with PC5 - based C - V2X that uses RF sidelink communication to enable low - latency vehicle sensor connections. One or more of the RSUs 208a - 208c are configured to broadcast, to one or more autonomous vehicles 202a - 202d, for example, infrastructure sensor data via one or more wireless communication protocols such as the CV2X protocol, proprietary and / or public cellular protocols, Wi - Fi protocol, remote (LoRA) signal protocol, Bluetooth protocol, and / or UWB protocol. One or more of the RSUs 208a - 208c are also configured to receive messages from one or more autonomous vehicles 202a - 202d. Thus, one or more of the RSUs 208a - 208c can include various components for performing the operations described herein, such as but not limited to transceivers, processor circuits, memory circuits, routers, and / or input / output interface hardware.

[0036] Each of one or more infrastructure systems 204a - 204e includes one or more infrastructure sensors 210 (e.g., one or more sensors 114), which may be image sensors that provide image data of the environment (e.g., a manufacturing environment) to the AVM central server edge 206. For example, one or more infrastructure sensors 210 may include, but are not limited to: two - dimensional (2D) cameras, three - dimensional (3D) cameras, infrared sensors, radar scanners, lidar scanners, light detection and ranging (lidar) sensors, ultrasonic sensors, etc. In one form, one or more infrastructure systems 204a - 204e provide pose, route, and obstacle data (and other data) of the manufacturing environment to the AVM central server edge 206. In one form, one or more infrastructure systems 204a - 204e are integrated within infrastructure elements (such as towers, light poles, buildings, signs, and other fixed elements of the manufacturing environment) that are part of the manufacturing environment. In one form, one or more infrastructure systems 204a - 204e are integrated within a movable element (such as an unmanned aerial vehicle (UAV)) as part of the manufacturing environment.

[0037] Figure 2 A plurality of workstations 212a - 212d are further shown. Each of the plurality of workstations 212a - 212d represents various assembly points in the manufacturing facility. For example, each of the workstations within the plurality of workstations 212a - 212d may specifically correspond to (e.g., be associated with) one or more particular infrastructure systems among one or more infrastructure systems 204a - 204e. As an example, infrastructure system 204a corresponds to workstation 212a. As another example, infrastructure system 204b corresponds to workstation 212b. As an additional example, infrastructure systems 204c and 204d correspond to workstation 212c. As yet another example, infrastructure system 204e corresponds to workstation 212d. It should be understood that multiple systems may correspond to one workstation and / or multiple workstations may correspond to one system, as well as other combinations.

[0038] As one or more autonomous vehicles 202a-202d are marshaled past each of a plurality of workstations 212a-212d, one or more infrastructure sensors 210 associated with a corresponding infrastructure system among one or more infrastructure systems 204a-204e acquire one or more images (and / or other sensed data) of an exterior of each of the one or more autonomous vehicles 202a-202d. In some examples, each of the one or more infrastructure systems 204a-204e includes an artificial intelligence (AI) / neural network module (e.g., AVM algorithm 112b). For example, the AI / neural network module is a pre-trained module. However, it should be understood that the AI / neural network module can utilize machine learning techniques to train itself in real time based at least on the one or more images.

[0039] Each of one or more infrastructure systems 204a - 204e is configured to utilize an AI / neural network module to identify a vehicle mass or condition associated with each of one or more autonomous vehicles 202a - 202d (e.g., associated with the outer surface of one or more autonomous vehicles 202a - 202d), detect a vehicle mass or condition associated with each of one or more autonomous vehicles 202a - 202d, verify a vehicle mass or condition associated with each of one or more autonomous vehicles 202a - 202d, or a combination thereof. As an example, the AI / neural network module identifies, detects, and / or verifies a vehicle mass associated with each of one or more autonomous vehicles 202a - 202d based on one or more images and / or information related to each of one or more autonomous vehicles 202a - 202d provided by the vehicle manufacturing cloud system 102. As another example, the AI / neural network module identifies, detects, and / or verifies a vehicle mass associated with each of one or more autonomous vehicles 202a - 202d based on one or more images and / or information related to each of one or more autonomous vehicles 202a - 202d provided by any component of the AVM system 100. As yet another example, the identification, detection, and / or verification associated with the exterior of any one of one or more autonomous vehicles 202a - 202d can be done as part of a quality inspection of the exterior of any one of one or more autonomous vehicles 202a - 202d. The quality inspection of the exterior of any one of one or more autonomous vehicles 202a - 202d can include determination of the condition of vehicle paint, one or more vehicle dents, misalignment of vehicle exterior parts, incorrect decorative packaging associated with a particular autonomous vehicle of one or more autonomous vehicles 202a - 202d, or a combination thereof, and other exterior conditions and / or quality issues. For example, the determination of the condition of the exterior of any one of one or more autonomous vehicles 202a - 202d can be based on a threshold level of any quality issues associated with the exterior of any one of one or more autonomous vehicles 202a - 202d. As another example, the threshold level of any quality issues associated with the exterior of any one of one or more autonomous vehicles 202a - 202d can include any level and / or quantity of quality issues.

[0040] Once one or more infrastructure systems 204a - 204e have completed quality checks, one or more infrastructure systems 204a - 204e notify the vehicle manufacturing cloud system 102 of the status (e.g., external status) of each of the one or more autonomous vehicles 202a - 202d. For example, any particular infrastructure system among one or more infrastructure systems 204a - 204e corresponding to any particular workstation among multiple workstations 212a through 212d can report the status of a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102. As another example, one or more infrastructure systems 204a - 204e can report an aggregated status of a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102 based on a combination of one or more images obtained at each of the multiple workstations 212a - 212d. It should be understood that the quality checks and / or determination of the status of one or more autonomous vehicles 202a - 202d can relate to any external status and, in some examples, can include one or more internal statuses of one or more autonomous vehicles 202a - 202d that affect the external quality of one or more autonomous vehicles 202a - 202d.

[0041] Reports received by the vehicle manufacturing cloud system 102 associated with the status of one or more autonomous vehicles 202a - 202d allow the vehicle manufacturing cloud system 102 to determine whether any of the one or more autonomous vehicles 202a - 202d should be grouped to a repair workstation (e.g., a repair bay located within a manufacturing facility). For example, an autonomous vehicle among one or more autonomous vehicles 202a - 202d is grouped to a repair workstation in response to the status of the autonomous vehicle not meeting a quality check of a quality based at least on status data obtained as described in more detail herein.

[0042] Based on a determination of whether any one of one or more autonomous vehicles 202a - 202d should be marshaled to a maintenance workstation, the vehicle manufacturing cloud system 102 may instruct any one of one or more autonomous vehicles 202a - 202d to obtain one or more documentation records associated with the condition external to a particular autonomous vehicle among one or more vehicles 202a - 202d. As an example, an instruction sent by the vehicle manufacturing cloud system 102 is wirelessly transmitted to any one of one or more autonomous vehicles 202a - 202d via any one of one or more RSUs 208a to 208c by utilizing the CV2X - PCS messaging protocol. As another example, an instruction sent by the vehicle manufacturing cloud system 102 is wirelessly transmitted to any one of one or more autonomous vehicles 202a - 202d by utilizing the cellular - Uu messaging protocol. As yet another example, one or more documentation records may include the geographical location of a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d, one or more snapshot records from a 360 - degree sensor of a particular vehicle (e.g., one or more vehicle sensors 124), or a combination thereof and other information (e.g., timestamp information, etc.).

[0043] In a case where one or more documentation records associated with the condition external to a particular autonomous vehicle among one or more vehicles 202a - 202d have been successfully obtained, the particular autonomous vehicle among one or more vehicles 202a - 202d transmits the one or more documentation records to one or more infrastructure systems 204a - 204e. For example, one or more infrastructure systems 204a - 204e may store the one or more documentation records in a local database, a remote database, a storage cloud, or a combination thereof. As another example, the saved one or more documentation records may later facilitate the identification and / or confirmation of the condition of any one of one or more autonomous vehicles 202a - 202d at different locations and / or time points, such as through a law enforcement investigation related to the condition of any one of one or more autonomous vehicles 202a - 202d at any given time.

[0044] Reference Figure 3, in various forms, each of the one or more autonomous vehicles 202a - 202d (e.g., autonomous vehicle 110) can be powered in various ways, such as by an electric motor and / or an internal combustion engine. As a non - limiting example, the one or more autonomous vehicles 202a - 202d can be any type of vehicle powered by an electric motor and / or an internal combustion engine, such as a car, a truck, a robot, an airplane, and / or a boat. Each of the one or more autonomous vehicles 202a - 202d includes a vehicle controller 300, one or more actuators 302, a plurality of on - vehicle sensors 304, and a human - machine interface (HMI) 306. Each of the one or more autonomous vehicles 202a - 202d also has a reference point 308, i.e., a designated point within the space defined by the vehicle body, such as a geometric center point, where the respective longitudinal and lateral center axes of a particular one of the one or more autonomous vehicles 202a - 202d intersect. The reference point 308 identifies the position of a particular one of the one or more autonomous vehicles 202a - 202d, e.g., the point at which a particular vehicle is located when it is navigating towards a waypoint.

[0045] In some examples, the vehicle controller 300 is configured or programmed to control the operation of braking, propulsion, steering, climate control, interior lights, and / or exterior lights, etc., of the autonomous vehicles 202a - 202d, and to determine whether and when the vehicle controller 300 (instead of a human operator) controls such operations. It should be understood that any operation associated with the one or more autonomous vehicles 202a - 202d can be facilitated via an automated, semi - automated, or manual mode. For example, the automated mode can facilitate any operation being fully controlled by the vehicle controller 300 without user assistance. As another example, the semi - automated mode can facilitate any operation being at least partially controlled by the vehicle controller 300 and / or the user. As other examples, the manual mode can facilitate any operation being fully controlled by the user.

[0046] The vehicle controller 300 includes or can be communicatively coupled (e.g., via a vehicle communication bus) to one or more processors, such as controllers included in the one or more autonomous vehicles 202a - 202d for monitoring and / or controlling various vehicle controllers, such as a powertrain controller, a brake controller, a steering controller, etc. The vehicle controller 300 is typically arranged to communicate over a vehicle communication network, which can include a bus in each of the one or more autonomous vehicles 202a - 202d, such as a controller area network (CAN), etc., and / or other wired and / or wireless mechanisms.

[0047] The vehicle controller 300 transmits messages to and / or receives messages from various devices in any of the one or more autonomous vehicles 202a - 202d via a vehicle network, where the various devices are, for example, one or more actuators 302, the HMI 306, etc. Alternatively or additionally, in the case where the vehicle controller 300 includes multiple devices, the vehicle communication network is used to represent communication between the devices represented as the vehicle controller 300 in the present disclosure. Further, as discussed below, various other controllers and / or sensors provide data to the vehicle controller 300 via the vehicle communication network.

[0048] Additionally, the vehicle controller 300 is configured to communicate with other traffic objects (e.g., vehicles, infrastructure, pedestrians, etc.) via a wireless vehicle communication interface, such as via a vehicle - to - vehicle communication network. The vehicle controller 300 is also configured to communicate via a vehicle - to - infrastructure communication network, such as with the infrastructure controller 115 of the infrastructure system 108. The vehicle communication network represents one or more mechanisms through which the vehicle controller 300 of any of the one or more autonomous vehicles 202a - 202d can communicate with other traffic objects and can be one or more of the wireless communication mechanisms, which include any desired combination of wireless (e.g., cellular, wireless, satellite, microwave, and radio frequency) communication mechanisms and any desired network topology (or multiple topologies when multiple communication mechanisms are used). Examples of vehicle communication networks include cellular, IEEE 802.11, dedicated short - range communication (DSRC), and / or wide - area network (WAN) (including the Internet), etc.

[0049] The vehicle actuator 302 is implemented via circuits, chips, or other electronic and / or mechanical components that can actuate various vehicle subsystems according to appropriate control signals. The vehicle actuator 302 can be used to control the braking, acceleration, and / or steering of one or more autonomous vehicles 202a - 202d. The vehicle controller 300 can be programmed to actuate the vehicle actuator 302 (including propulsion, steering, and / or braking) based on the planned acceleration or deceleration of one or more autonomous vehicles 202a - 202d.

[0050] The sensor 304 includes various devices to provide data to the vehicle controller 300. For example, the sensor 304 may include object detection sensors, such as lidar sensors disposed on or in one or more autonomous vehicles 202a - 202d, which provide the relative position, size, and shape of one or more targets (e.g., additional vehicles, bicycles, pedestrians, robots, drones, etc.) traveling beside, in front of, and / or behind one or more autonomous vehicles 202a - 202d around the one or more autonomous vehicles 202a - 202d. As another example, one or more of the sensors may be radar sensors fixed to one or more bumpers of one or more autonomous vehicles 202a - 202d, which may provide the position of a target relative to each of the one or more autonomous vehicles 202a - 202d.

[0051] The object detection sensor may include a camera sensor, for example, to provide a front view, side view, rear view, etc., and the camera sensor provides an image from an area around one or more autonomous vehicles 202a - 202d. For example, the vehicle controller 300 may be programmed to receive sensor data from the camera sensor and implement image processing techniques to detect roads, infrastructure elements, etc. The vehicle controller 300 may also be programmed to determine the current vehicle position based on position coordinates (e.g., GPS coordinates) received from one or more autonomous vehicles 202a - 202d and indicating the position of any of the one or more autonomous vehicles 202a - 202d from the GPS sensor.

[0052] The HMI 306 is configured to receive information from a user (such as a human operator) during the operation of one or more autonomous vehicles 202a - 202d. In addition, the HMI 306 is configured to present information to a user (such as an occupant of any of the one or more autonomous vehicles 202a - 202d). In some variations, the vehicle controller 300 is programmed to receive destination data, such as position coordinates, from the HMI 306.

[0053] Accordingly, a combination of infrastructure sensors 210 and vehicle sensors (e.g., on-vehicle sensors 304) can be used to autonomously guide one or more autonomous vehicles 202a-202d towards a waypoint. Route selection can be accomplished using vehicle position, travel distance, queuing for vehicle platooning, etc. One or more autonomous vehicles 202a-202d that require additional power / fuel can be prepared before joining the queue. Other autonomous vehicles among the one or more autonomous vehicles 202a-202d going to a specific waypoint operate in the same manner, enabling the coordination of the movement of the entire vehicle fleet. The movement of the entire vehicle fleet is coordinated by a central vehicle fleet management system that guides all traffic and logistics from the assembly plant to the waypoint. For example, vehicles within the vehicle fleet can be organized in a pre-sorted order, controlled to move to certain positions, and removed from the order, such as for repair or further analysis of detected quality issues or conditions, etc.

[0054] In various examples, a centralized vehicle fleet management application has complete knowledge of one or more autonomous vehicles 202a-202d (e.g., current location, destination, special instructions, etc.) under its control, which increases the responsibility and traceability of the allocation process. Coordinate vehicle fleet management within and / or across sites to optimize the delivery timing of each of one or more autonomous vehicles 202a-202d to the waypoint. Several logistics applications can be used, which can involve a combination of infrastructure systems (e.g., infrastructure system 108) integrated with traffic management algorithms to queue vehicles in real-time and eliminate conflicts. Accordingly, the vehicle fleet management application queues one or more autonomous vehicles 202a-202d based on unique characteristics (how far a particular vehicle among one or more autonomous vehicles 202a-202d needs to travel, traffic conditions along the route, when a particular vehicle among one or more autonomous vehicles 202a-202d needs to reach a particular location to queue in the correct order, etc.).

[0055] Reference Figure 4 , a second example of a platooning environment 400 is shown. For example, this second example of the platooning environment 400 is located outside a manufacturing plant (e.g., a parking lot). Figure 4 Further shown therein are a plurality of checkpoints 412a-412d associated with change points across the parking lot. For example, each of the checkpoints among the plurality of checkpoints 412a-412d can specifically correspond to one or more particular infrastructure systems among one or more infrastructure systems 204a-204e. As an example, infrastructure system 204a corresponds to a first area 412a within the parking lot where quality inspections are performed and within the scope of infrastructure system 204a (e.g., the first checkpoint 412a among the plurality of checkpoints 412a-412d).

[0056] As another example, infrastructure system 204b corresponds to a second area 412b within the scope of the infrastructure system 204b of the parking lot (e.g., the second checkpoint 412b among the multiple checkpoints 412a - 412d). As an additional example, infrastructure systems 204c and 204d correspond to a third area 412c within the scope of the infrastructure systems 204c and 204d of the parking lot (e.g., the third checkpoint 412c among the multiple checkpoints 412a - 412d). As yet another example, infrastructure system 204e corresponds to a fourth area 412d within the scope of the infrastructure system 204e where one or more of the vehicles 202a - 202d are waiting for transportation (e.g., the fourth checkpoint 412d among the multiple checkpoints 412a - 412d). It should be understood that multiple systems can correspond to one area of the parking lot and / or multiple areas of the parking lot can correspond to one system, as well as other combinations.

[0057] When one or more autonomous vehicles 202a - 202d are marshaled past each of the multiple checkpoints 412a - 412d, one or more infrastructure sensors 210 associated with the corresponding infrastructure system among the one or more infrastructure systems 204a - 204e acquire one or more external images (and / or other sensing data) associated with each of the one or more autonomous vehicles 202a - 202d. Then, the one or more images are used as a basis for quality inspection performed by the one or more infrastructure systems 204a - 204e.

[0058] Once the one or more infrastructure systems 204a - 204e have completed the quality inspection, the one or more infrastructure systems 204a - 204e notify the vehicle manufacturing cloud system 102 of the status of each autonomous vehicle among the one or more autonomous vehicles 202a - 202d. For example, any particular infrastructure system among the one or more infrastructure systems 204a - 204e corresponding to any particular checkpoint among the multiple checkpoints 412a - 412d can report the status of a particular autonomous vehicle among the one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102. As another example, the one or more infrastructure systems 204a - 204e can report the aggregated status of a particular autonomous vehicle among the one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102 based on a combination of the one or more images obtained at each of the one or more checkpoints 412a - 412d.

[0059] Reports received by the vehicle manufacturing cloud system 102 associated with the condition of one or more autonomous vehicles 202a - 202d allow the vehicle manufacturing cloud system 102 to determine whether any of the one or more autonomous vehicles 202a - 202d should be grouped to a maintenance workstation (not shown) or other workstations (e.g., workstations outside the normal autonomous process). For example, in the case where the condition of an autonomous vehicle among the one or more autonomous vehicles 202a - 202d does not meet a quality inspection, the autonomous vehicle among the one or more autonomous vehicles 202a - 202d is grouped to a maintenance workstation. Based on the determination of whether any of the one or more autonomous vehicles 202a - 202d should be grouped to a maintenance workstation, the vehicle manufacturing cloud system 102 may instruct any of the one or more autonomous vehicles 202a - 202d to obtain one or more documentation records associated with the condition outside a particular autonomous vehicle among the one or more vehicles 202a - 202d. For example, one or more documentation records (e.g., reports) may include the geographical location of a particular autonomous vehicle among the one or more autonomous vehicles 202a - 202d, one or more snapshot records from a 360 - degree sensor of a particular vehicle (e.g., one or more vehicle sensors 124), or a combination thereof.

[0060] The report may also include status information regarding whether a particular autonomous vehicle among the one or more autonomous vehicles 202a - 202d is ready for transport. The report may also provide instructions to the vehicle manufacturing cloud system 102 to store one or more images. For example, the stored images may later be used for comparisons that a dealer and / or customer may make regarding the condition of the exterior of any of the one or more autonomous vehicles 202a - 202d at any time. As an example, one or more images taken of a particular autonomous vehicle when the particular autonomous vehicle leaves the fourth area 412d of a parking lot may be used to determine the party at fault for any quality issues associated with the exterior of the particular autonomous vehicle. For example, the determination of the party at fault may be based on a comparison of one or more images representing a first condition of the exterior of the particular autonomous vehicle at the time of or after delivery of the particular autonomous vehicle to a customer and a second condition of the exterior of the particular autonomous vehicle when the particular autonomous vehicle leaves the fourth area 412d of the parking lot. As another example, the determination of the party at fault may help support an insurance claim that any relevant party may make regarding the condition of the exterior of a particular autonomous vehicle as evidence.

[0061] Figure 5 A third example of a grouping environment 500 is shown. For example, this third example of the grouping environment 500 is located within a dealer / warehouse environment (e.g., an automobile dealership). Figure 5Further shown in [the figure] are a plurality of checkpoints 512a - 512d associated with change points across the dealership parking lot. For example, each of the checkpoints among the plurality of checkpoints 512a - 512d can specifically correspond to one or more particular infrastructure systems among one or more infrastructure systems 204a - 204e. As an example, infrastructure system 204a corresponds to a first area 512a (e.g., the first checkpoint 512a among the plurality of checkpoints 512a - 512d) within the scope of infrastructure system 204a of the dealership / warehouse parking lot.

[0062] As another example, infrastructure system 204b corresponds to a second area 512b (e.g., the second checkpoint 512b among the plurality of checkpoints 512a - 512d) within the scope of infrastructure system 204b of the dealership / warehouse parking lot. As an additional example, infrastructure systems 204c and 204d correspond to a third area 512c (e.g., the third checkpoint 512c among the plurality of checkpoints 512a - 512d) where a final inspection is performed and within the scope of infrastructure systems 204c and 204d of the dealership / warehouse parking lot. As yet another example, infrastructure system 204e corresponds to a fourth area 512d (e.g., the fourth checkpoint 512d among the plurality of checkpoints 512a - 512d) where one or more of the vehicles 202a - 202d are waiting to be delivered from the dealership / warehouse parking lot to a customer and within the scope of infrastructure system 204e of the dealership / warehouse parking lot. It should be understood that multiple systems can correspond to one checkpoint and / or multiple checkpoints can correspond to one system, as well as other combinations.

[0063] When one or more autonomous vehicles 202a - 202d are marshaled past each of the plurality of checkpoints 512a - 512d, one or more infrastructure sensors 210 associated with the corresponding infrastructure system among one or more infrastructure systems 204a - 204e acquire one or more images (and / or other sensing data) of the exterior of each of the one or more autonomous vehicles 202a - 202d. Then, the one or more images are used as a basis for quality inspections performed by one or more infrastructure systems 204a - 204e.

[0064] Once one or more infrastructure systems 204a - 204e have completed quality inspections, one or more infrastructure systems 204a - 204e notify the vehicle manufacturing cloud system 102 of the status of each autonomous vehicle among one or more autonomous vehicles 202a - 202d. For example, any particular infrastructure system among one or more infrastructure systems 204a - 204e corresponding to any particular checkpoint among multiple checkpoints 512a - 512d can report the status of a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102. As another example, one or more infrastructure systems 204a - 204e can report the collective status of a particular set of autonomous vehicles among one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102 based on a combination of one or more images captured at each of one or more checkpoints 512a - 512d.

[0065] Reports received by the vehicle manufacturing cloud system 102 associated with the status of one or more autonomous vehicles 202a - 202d allow the vehicle manufacturing cloud system 102 to determine whether any of one or more autonomous vehicles 202a - 202d should be grouped to a repair workstation (not shown). For example, in the case where the status of an autonomous vehicle among one or more autonomous vehicles 202a - 202d does not meet the quality inspection, the autonomous vehicle among one or more autonomous vehicles 202a - 202d is grouped to a repair workstation. Based on the determination of whether any of one or more autonomous vehicles 202a - 202d should be grouped to a repair workstation, the vehicle manufacturing cloud system 102 can instruct any of one or more autonomous vehicles 202a - 202d to obtain one or more documentation records associated with the status external to a particular autonomous vehicle among one or more vehicles 202a - 202d. For example, one or more documentation records can include the geographical location of a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d, one or more snapshot records from a 360 - degree sensor of a particular vehicle (e.g., one or more vehicle sensors 124), or a combination thereof.

[0066] The report may also include status information regarding whether a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d is ready for transport. The report may also provide instructions to the vehicle manufacturing cloud system 102 to store one or more images. For example, the stored images may later be used for comparisons that a dealer and / or customer may make regarding the condition of the exterior of any one of the one or more autonomous vehicles 202a - 202d at any time. As an example, one or more images taken of a particular autonomous vehicle as the particular autonomous vehicle leaves the fourth area 512d of a dealer / warehouse parking lot may be used to determine the party at fault for any quality issues associated with the exterior of the particular autonomous vehicle. For example, the determination of the party at fault may be based on a comparison of one or more images representing a first condition of the exterior of the particular autonomous vehicle at the time of or after delivery of the particular autonomous vehicle to a customer and a second condition of the exterior of the particular autonomous vehicle as the particular autonomous vehicle leaves the fourth area 512d of the dealer / warehouse parking lot. As another example, the determination of the party at fault may help support an insurance claim that any interested party may make regarding the condition of the exterior of the particular autonomous vehicle as evidence.

[0067] Figure 6 A third example of a marshalling environment 600 is shown. For example, this third example of the marshalling environment 600 is located within an automotive-rental environment (e.g., a rental agency). Figure 6 Also shown are a plurality of checkpoints 612a - 612d associated with change points across an automotive-rental parking lot. For example, each of the checkpoints among the plurality of checkpoints 612a - 612d may specifically correspond to one or more particular infrastructure systems among one or more infrastructure systems 204a - 204e. As an example, infrastructure system 204a corresponds to a first area 612a within the scope of infrastructure system 204a of the automotive-rental parking lot (e.g., the first checkpoint 612a among the plurality of checkpoints 612a - 612d).

[0068] As another example, infrastructure system 204b corresponds to a second region 612b within the scope of the infrastructure system 204b of the car-rental parking lot (e.g., the second checkpoint 612b among the multiple checkpoints 612a - 612d). As an additional example, infrastructure systems 204c and 204d correspond to a third region 612c within the scope of the infrastructure systems 204c and 204d of the car-rental parking lot where a final inspection is performed (e.g., the third checkpoint 612c among the multiple checkpoints 612a - 612d). As yet another example, infrastructure system 204e corresponds to a fourth region 612d within the scope of the infrastructure system 204e of the car-rental parking lot where one or more of the vehicles 202a - 202d are waiting to be delivered from the car-rental parking lot to a customer (e.g., the fourth checkpoint 612d among the multiple checkpoints 612a - 612d). It should be understood that multiple systems can correspond to one region of the car-rental parking lot and / or multiple regions of the car-rental parking lot can correspond to one system, as well as other combinations.

[0069] When one or more autonomous vehicles 202a - 202d are marshaled past each of the multiple checkpoints 612a - 612d, one or more infrastructure sensors 210 associated with the corresponding infrastructure system among one or more infrastructure systems 204a - 204e acquire one or more images (and / or other sensing data) of the exterior of each of the one or more autonomous vehicles 202a - 202d. Then, the one or more images are used as a basis for quality inspection performed by one or more infrastructure systems 204a - 204e. The AI / neural network module utilized by one or more infrastructure systems 204a - 204e to perform quality inspection can also perform pre-comparison and post-comparison analysis on the one or more images. For example, the pre-comparison and post-comparison analysis can include the identification, classification, and / or detection of any issues associated with the condition of the exterior of any of the one or more autonomous vehicles 202a - 202d.

[0070] Once one or more infrastructure systems 204a - 204e have completed quality inspections, one or more infrastructure systems 204a - 204e notify the vehicle manufacturing cloud system 102 of the status of each autonomous vehicle of one or more autonomous vehicles 202a - 202d. For example, any particular infrastructure system among one or more infrastructure systems 204a - 204e corresponding to any particular checkpoint among multiple checkpoints 612a - 612d can report the status of a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102. As another example, one or more infrastructure systems 204a - 204e can report the collective status of a particular set of autonomous vehicles among one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102 based on a combination of one or more images captured at each of one or more checkpoints 612a - 612d.

[0071] Reports received by the vehicle manufacturing cloud system 102 associated with the status of one or more autonomous vehicles 202a - 202d allow the vehicle manufacturing cloud system 102 to determine whether any of one or more autonomous vehicles 202a - 202d should be marshaled to a repair workstation (not shown). For example, in the case where the status of an autonomous vehicle among one or more autonomous vehicles 202a - 202d does not meet the quality inspection, the autonomous vehicle among one or more autonomous vehicles 202a - 202d is marshaled to a repair workstation. Based on the determination of whether any of one or more autonomous vehicles 202a - 202d should be marshaled to a repair workstation, the vehicle manufacturing cloud system 102 can instruct any of one or more autonomous vehicles 202a - 202d to obtain one or more documentation records associated with the status external to a particular autonomous vehicle among one or more vehicles 202a - 202d. For example, one or more documentation records can include the geographical location of a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d, one or more snapshot records from a 360 - degree sensor of a particular vehicle (e.g., one or more vehicle sensors 124), or a combination thereof.

[0072] The report may also include status information related to whether a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d is ready for transportation. The report may also provide instructions to the vehicle manufacturing cloud system 102 to store one or more images. For example, the stored images may later be used for comparisons that a dealer and / or customer may make related to the condition of the exterior of any one of the one or more autonomous vehicles 202a - 202d at any time. As an example, one or more images taken of a particular autonomous vehicle as the particular autonomous vehicle leaves the fourth area 612d of a car - rental parking lot may be used to determine the party at fault for any quality issues associated with the exterior of the particular autonomous vehicle. For example, the determination of the party at fault may be based on a comparison of one or more images representing a first condition of the exterior of the particular autonomous vehicle and a second condition of the exterior of the particular autonomous vehicle when the particular autonomous vehicle was delivered to the customer or after delivery, taken as the particular autonomous vehicle leaves the fourth area 612d of the car - rental parking lot. As another example, the determination of the party at fault may help support an insurance claim that any relevant party may make regarding the condition of the exterior of the particular autonomous vehicle as evidence.

[0073] Figure 7 A fifth example of a marshalling environment 700 is shown. For example, this fifth example of the marshalling environment 700 is located within a valet parking service environment (e.g., a parking lot where valet parking operations occur). Figure 7 Also shown are a plurality of checkpoints 712a - 712d associated with change points across a valet parking - operated parking lot. For example, each of the checkpoints among the plurality of checkpoints 712a - 712d may specifically correspond to one or more particular infrastructure systems among one or more infrastructure systems 204a - 204e. As an example, infrastructure system 204a corresponds to a first area 712a within the scope of infrastructure system 204a (e.g., the first checkpoint 712a among the plurality of checkpoints 712a - 712d) associated with the valet parking service entry location of the valet parking - operated parking lot.

[0074] As another example, infrastructure system 204b corresponds to a second region 712b within the scope of the infrastructure system 204b of a valet parking operation's parking lot (e.g., the second checkpoint 712b among a plurality of checkpoints 712a - 712d). As an additional example, infrastructure systems 204c and 204d correspond to a third region 712c within the scope of the infrastructure systems 204c and 204d of a valet parking operation's parking lot (e.g., the third checkpoint 712c among a plurality of checkpoints 712a - 712d). As yet another example, infrastructure system 204e corresponds to a fourth region 712d within the scope of the infrastructure system 204e associated with the valet parking service departure location of a valet parking operation's parking lot (e.g., the fourth checkpoint 712d among a plurality of checkpoints 712a - 712d). It should be understood that multiple systems can correspond to one region of a valet parking operation's parking lot and / or multiple regions of a valet parking operation's parking lot can correspond to one system, as well as other combinations.

[0075] When one or more autonomous vehicles 202a - 202d are marshaled past each of a plurality of checkpoints 712a - 712d, one or more infrastructure sensors 210 associated with the corresponding infrastructure system among one or more infrastructure systems 204a - 204e acquire one or more images (and / or other sensing data) of the exterior of each of the one or more autonomous vehicles 202a - 202d. Then, the one or more images are used as a basis for quality inspection performed by one or more infrastructure systems 204a - 204e. The AI / neural network module utilized by one or more infrastructure systems 204a - 204e to perform quality inspection can also perform pre - comparison and post - comparison analysis on the one or more images. For example, the pre - comparison and post - comparison analysis can include the identification, classification, and / or detection of any issues associated with the condition of the exterior of any of the one or more autonomous vehicles 202a - 202d.

[0076] Once one or more of the infrastructure systems 204a - 204e have completed quality inspections, one or more of the infrastructure systems 204a - 204e notify the vehicle manufacturing cloud system 102 of the status of each of the one or more autonomous vehicles 202a - 202d. For example, any particular infrastructure system among one or more of the infrastructure systems 204a - 204e corresponding to any particular checkpoint among the multiple checkpoints 712a - 712d can report the status of a particular autonomous vehicle among the one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102. As another example, one or more of the infrastructure systems 204a - 204e can report the collective status of a particular set of autonomous vehicles among the one or more autonomous vehicles 202a - 202d to the vehicle manufacturing cloud system 102 based on a combination of one or more images captured at each of the one or more checkpoints 712a - 712d.

[0077] Reports received by the vehicle manufacturing cloud system 102 associated with the status of one or more autonomous vehicles 202a - 202d allow the vehicle manufacturing cloud system 102 to determine whether any of the one or more autonomous vehicles 202a - 202d should be marshaled to a repair workstation (not shown). For example, in the case where the status of an autonomous vehicle among the one or more autonomous vehicles 202a - 202d does not meet the quality inspection, the autonomous vehicle among the one or more autonomous vehicles 202a - 202d is marshaled to a repair workstation. Based on the determination of whether any of the one or more autonomous vehicles 202a - 202d should be marshaled to a repair workstation, the vehicle manufacturing cloud system 102 can instruct any of the one or more autonomous vehicles 202a - 202d to obtain one or more documentation records associated with the status of the exterior of a particular autonomous vehicle among the one or more vehicles 202a - 202d. For example, the one or more documentation records can include the geographical location of a particular autonomous vehicle among the one or more autonomous vehicles 202a - 202d, one or more snapshot records from the 360 - degree sensors (e.g., one or more vehicle sensors 124) of a particular vehicle, or a combination thereof.

[0078] The report may also include status information regarding whether a particular autonomous vehicle among one or more autonomous vehicles 202a - 202d is ready for transportation. The report may also provide instructions to the vehicle manufacturing cloud system 102 to store one or more images. For example, the stored images may later be used for comparisons that can be made by a dealership and / or a customer related to the condition of the exterior of any one of the one or more autonomous vehicles 202a - 202d at any time. As an example, one or more images taken of a particular autonomous vehicle when the particular autonomous vehicle leaves the fourth area 712d of a valet parking operation's parking lot may be used to determine the party at fault for any quality issues associated with the exterior of the particular autonomous vehicle. For example, the determination of the party at fault may be based on a comparison of one or more images representing a first condition of the exterior of the particular autonomous vehicle at the time of or after delivering the particular autonomous vehicle to a customer and a second condition of the exterior of the particular autonomous vehicle. As another example, the determination of the party at fault may help support an insurance claim that any relevant party may file regarding the condition of the exterior of the particular autonomous vehicle as evidence.

[0079] Figure 8 is a flowchart showing an example method 800 for evaluating the condition of the exterior of a platooned vehicle. At operation 802, a first set of images of the exterior of one or more vehicles (e.g., autonomous vehicle 110) is obtained. For example, the first set of images of the exterior of one or more vehicles is obtained by one or more sensors (e.g., one or more sensors 114) of an infrastructure system (e.g., infrastructure system 108).

[0080] At operation 804, the condition of the exterior of the one or more vehicles is determined. For example, the determination of the condition of the exterior of the one or more vehicles is based on the first set of images. As another example, the condition of the exterior of the one or more vehicles is determined by an automated vehicle platooning algorithm (e.g., AVM algorithm 112b) of the infrastructure system. As other examples, the condition of the one or more vehicles includes the condition of vehicle paint, one or more vehicle dents, misalignment of vehicle exterior parts, incorrect trim packages associated with the one or more vehicles, or a combination thereof.

[0081] At operation 806, cause one or more vehicles to navigate towards a waypoint and / or cause one or more vehicles to capture one or more characteristics associated with the one or more vehicles. As another example, based on the condition of the exterior of one or more vehicles not meeting a quality inspection, cause one or more vehicles to navigate towards a waypoint and / or cause one or more vehicles to capture one or more characteristics associated with the one or more vehicles. As other examples, capture one or more characteristics associated with one or more vehicles via one or more vehicle sensors (e.g., one or more vehicle sensors 124). As an additional example, a waypoint can be any point towards which one or more vehicles are marshaled, such as the repair cost of a manufacturing facility.

[0082] In one or more examples, determine whether the condition meets a quality inspection. In another embodiment, transmit the marshaling state of one or more vehicles. For example, the marshaling state of one or more vehicles is transmitted to a vehicle manufacturing cloud system (e.g., manufacturing cloud system 102). As another example, based on the condition of the exterior of one or more vehicles not meeting (not conforming to) a quality inspection, transmit the marshaling state of one or more vehicles. Additionally, cause the vehicle manufacturing cloud system to store a first image set of the exterior of one or more vehicles. For example, based on the transmission of the marshaling state of one or more vehicles, cause the vehicle manufacturing cloud system to store a first image set of the exterior of one or more vehicles.

[0083] In some examples, receive one or more characteristics. For example, receive one or more characteristics from one or more vehicles. As another example, one or more characteristics are used as investigative evidence associated with the condition of the exterior of one or more vehicles. As other examples, one or more characteristics include the location associated with one or more vehicles, a snapshot record of the exterior of one or more vehicles, or a combination thereof.

[0084] In some examples, obtain a second image set of the exterior of one or more vehicles. For example, the second image set of the exterior of one or more vehicles is obtained by one or more sensors of an infrastructure system. Additionally, compare the first image set with the second image set. For example, the comparison of the first image set with the second image set is performed by an automated vehicle marshaling algorithm and / or a neural network module of the infrastructure system. Furthermore, determine the difference between the first image set and the second image set. For example, based on the comparison of the first image set and the second image set (e.g., an analysis using one or more image analysis techniques), determine the difference between the first image set and the second image set. As another example, the result of the determination of the difference between the first image set and the second image set is saved in a database associated with the infrastructure system. As yet another example, the saved result is used as investigative evidence associated with the condition of the exterior of one or more vehicles.

[0085] Accordingly, one or more examples of the present disclosure provide a means for evaluating the condition of the exterior of a vehicle in various marshalling environments. For example, such an evaluation can include performing one or more quality inspections, where an algorithm is capable of identifying, detecting, and validating any vehicle exterior issues based on at least one or more images captured of the vehicle as it is marshalled through the environment.

[0086] Unless expressly indicated otherwise herein, all numerical values indicating mechanical / thermal properties, compositional percentages, dimensions, and / or tolerances or other characteristics should be understood to be modified by the word "about" or "approximately" when describing the scope of the present disclosure. This modification is desired for various reasons, including industrial practices, material, manufacturing, and assembly tolerances, and testing capabilities.

[0087] As used herein, the phrase "at least one of A, B, and C" should be interpreted to represent the logic (A or B or C) using non-exclusive logic "or", and should not be interpreted to mean "at least one of A, at least one of B, and at least one of C".

[0088] In this application, the terms "controller" and / or "module" can refer to, be part of, or include the following: application specific integrated circuit (ASIC); digital, analog, or mixed analog / digital discrete circuits; digital, analog, or mixed analog / digital integrated circuits; combinational logic circuits; field programmable gate array (FPGA); processor circuits (shared, dedicated, or grouped) that execute code; memory circuits (shared, dedicated, or grouped) that store code executed by the processor circuits; other suitable hardware components that provide the described functionality (e.g., operational amplifier circuit integrators as part of a heat flux data module); or a combination of some or all of the above, such as in a system-on-chip.

[0089] The term memory is a subset of the term computer-readable medium. As used herein, the term computer-readable medium does not cover transient electrical or electromagnetic signals propagated through a medium (such as on a carrier wave); thus, the term computer-readable medium can be considered tangible and non-transitory. Non-limiting examples of non-transitory tangible computer-readable media are non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital magnetic tape or hard disk drives), and optical storage media (such as CDs, DVDs, or Blu-ray discs).

[0090] The devices and methods described in this application can be implemented, in part or in whole, by a special-purpose computer created by configuring a general-purpose computer to execute one or more specific functions embodied in a computer program. Functional blocks, flowchart components, and other elements described above serve as software specifications that can be translated into a computer program by routine work of a technician or programmer.

[0091] 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 should not be regarded as departing from the spirit and scope of the present disclosure.

[0092] According to the present invention, one or more non-transitory computer-readable media are provided, the non-transitory computer-readable media storing processor-executable instructions having instructions that, when executed by at least one processor, cause the at least one processor to: obtain a first set of images of the exterior of one or more vehicles via one or more sensors of an infrastructure system; determine a condition of the exterior of the one or more vehicles via an automated vehicle marshalling algorithm of the infrastructure system, wherein the determination of the condition of the exterior of the one or more vehicles is based on the first set of images; and cause the one or more vehicles to navigate towards a waypoint and capture one or more characteristics associated with the one or more vehicles based on the condition of the exterior of the one or more vehicles not meeting a quality check.

[0093] According to an embodiment, the at least one processor is further caused to: determine whether the condition meets the quality check.

[0094] According to an embodiment, the condition of the one or more vehicles includes a condition of vehicle painting, one or more vehicle dents, misalignment of vehicle exterior parts, an incorrect decorative package associated with the one or more vehicles, or a combination thereof.

[0095] According to an embodiment, the at least one processor is further caused to: transmit a marshalling status of the one or more vehicles to a vehicle manufacturing cloud system based on the condition of the exterior of the one or more vehicles not meeting the quality check; and cause the vehicle manufacturing cloud system to store the first set of images of the exterior of the one or more vehicles based on the transmission of the marshalling status of the one or more vehicles.

[0096] According to an embodiment, the at least one processor is further caused to: receive one or more characteristics from the one or more vehicles, wherein the one or more characteristics serve as investigative evidence associated with the condition of the exterior of the one or more vehicles, and wherein the one or more characteristics include a location associated with the one or more vehicles, a snapshot record of the exterior of the one or more vehicles, or a combination thereof.

[0097] According to an embodiment, also causing at least one processor to: obtain a second image set of the exterior of one or more vehicles via one or more sensors of an infrastructure system; compare the first image set with the second image set via an automated vehicle marshalling algorithm and a neural network module of the infrastructure system; and determine a difference between the first image set and the second image set based on the comparison of the first image set and the second image set, wherein a result of the determination of the difference between the first image set and the second image set is saved in a database associated with the infrastructure system, and wherein the saved result is used as investigatory evidence associated with the condition of the exterior of one or more vehicles.

[0098] According to an embodiment, one or more characteristics associated with one or more vehicles are captured via one or more vehicle sensors.

Claims

1. A method, comprising: Obtaining a first set of images of the exterior of one or more vehicles via one or more sensors of an infrastructure system; Determining, via an automated vehicle marshalling algorithm of the infrastructure system, a condition of the exterior of the one or more vehicles, wherein the determination of the condition of the exterior of the one or more vehicles is based on the first set of images; And Causing the one or more vehicles to navigate towards a waypoint and capture one or more characteristics associated with the one or more vehicles based on the condition of the exterior of the one or more vehicles not meeting a quality inspection.

2. The method according to claim 1, further comprising: Determining whether the condition meets the quality inspection.

3. The method according to claim 1, wherein the condition of the one or more vehicles comprises a condition of vehicle painting, one or more vehicle dents, misalignment of external vehicle parts, incorrect decorative packaging associated with the one or more vehicles, or a combination thereof.

4. The method according to claim 1, further comprising: Transmitting a marshalling state of the one or more vehicles to a vehicle manufacturing cloud system based on the condition of the exterior of the one or more vehicles not meeting the quality inspection; And Causing the vehicle manufacturing cloud system to store the first set of images of the exterior of the one or more vehicles based on the transmission of the marshalling state of the one or more vehicles.

5. The method according to claim 1, further comprising: Receiving the one or more characteristics from the one or more vehicles, wherein the one or more characteristics are used as investigative evidence associated with the condition of the exterior of the one or more vehicles, and wherein the one or more characteristics comprise a location associated with the one or more vehicles, a snapshot record of the exterior of the one or more vehicles, or a combination thereof.

6. The method according to claim 1, further comprising: Obtaining a second set of images of the exterior of the one or more vehicles via the one or more sensors of the infrastructure system; Comparing the first set of images with the second set of images via the automated vehicle marshalling algorithm and a neural network module of the infrastructure system; And Determining a difference between the first set of images and the second set of images based on the comparison of the first set of images and the second set of images.

7. The method according to claim 6, wherein a result of the determination of the difference between the first set of images and the second set of images is saved in a database associated with the infrastructure system, and wherein the saved result is used as investigative evidence associated with the condition of the exterior of the one or more vehicles.

8. The method according to claim 1, wherein the one or more characteristics associated with the one or more vehicles are captured via one or more vehicle sensors.

9. A system, comprising: An infrastructure system configured to: Obtain a first set of images of the exterior of one or more vehicles via one or more sensors of the infrastructure system, Determine the external condition of the one or more vehicles through an automated vehicle marshalling algorithm of the infrastructure system, wherein the determination of the external condition of the one or more vehicles is based on the first image set, and Cause the one or more vehicles to navigate towards a waypoint and capture one or more characteristics associated with the one or more vehicles based on the external condition of the one or more vehicles not meeting a quality inspection; A vehicle manufacturing cloud system, the vehicle manufacturing cloud system being configured to: Receive the marshalling status of the one or more vehicles, and Store the first image set of the exterior of the one or more vehicles; And The one or more vehicles, the one or more vehicles being configured to: Capture the one or more characteristics via one or more vehicle sensors, and Transmit the one or more characteristics.

10. The system according to claim 9, wherein the infrastructure system is further configured to: Determine whether the condition meets the quality inspection.

11. The system according to claim 9, wherein the condition of the one or more vehicles includes the condition of vehicle painting, one or more vehicle dents, misalignment of vehicle exterior parts, incorrect decorative packaging associated with the one or more vehicles, or a combination thereof.

12. The system according to claim 9, wherein the infrastructure system is further configured to: Transmit the marshalling status of the one or more vehicles based on the external condition of the one or more vehicles not meeting the quality inspection; and Cause the vehicle manufacturing cloud system to store the first image set of the exterior of the one or more vehicles based on the transmission of the marshalling status of the one or more vehicles.

13. The system according to claim 9, wherein the infrastructure system is further configured to: Receive the one or more characteristics, wherein the one or more characteristics are used as investigative evidence associated with the external condition of the one or more vehicles, and wherein the one or more characteristics include the position associated with the one or more vehicles, a snapshot record of the exterior of the one or more vehicles, or a combination thereof.

14. The system according to claim 9, wherein the infrastructure system is further configured to: Obtain a second image set of the exterior of the one or more vehicles through the one or more sensors of the infrastructure system; Compare the first image set with the second image set through the automated vehicle marshalling algorithm and the neural network module of the infrastructure system; and Determine the difference between the first image set and the second image set based on the comparison of the first image set and the second image set.

15. The system according to claim 9, wherein the result of the determination of the difference between the first image set and the second image set is saved in a database associated with the infrastructure system, and wherein the saved result is used as investigative evidence associated with the external condition of the one or more vehicles.

Images