Autonomous mass testing system for vehicle

Abstract

A computer-implemented method, when executed by data processing hardware, causes the data processing hardware to perform operations. Operations include: autonomously maneuvering the vehicle along a test track; monitoring, via at least one audio sensor, audio data from the vehicle during maneuvering of the vehicle along the test track; and monitoring, via a monitoring system disposed along the test track, monitoring data of the vehicle along the test track. The operations further include performing a sound detection function of an autonomous test algorithm based on the monitored audio data; detecting erroneous noise via a sound detection function; classifying the detected error noise via a classification function of the autonomous test algorithm; identifying a maintenance station based on the classified error noise; and performing an autonomous path planning function of the autonomous test algorithm in response to the identified maintenance station and the classified error noise.

Description

Technical Field

[0001] The present invention generally relates to an autonomous quality testing system for vehicles, and more specifically, to an audio-based autonomous quality testing system for vehicles. Background Technology

[0002] The information provided in this section is intended to provide a general overview of the background of this disclosure. To the extent described in this section, the work of the currently named inventors, and aspects of the description that may not conform to the prior art at the time of submission, are neither explicitly nor implicitly acknowledged as prior art relative to this disclosure.

[0003] After manufacturing, the vehicle undergoes a series of tests. For example, it may undergo squeaking and clicking tests, during which passengers operate the vehicle around a track and listen for various noises. Noise may indicate that a certain aspect of the vehicle may require repair or further evaluation. However, different operators may have different opinions on what kind of noise qualifies for further evaluation, and / or may have different levels of noise identification. Furthermore, inconsistencies may exist between operators during test execution regarding driving speed, trajectory, and other operational variations. Any variation may cause noise to appear under certain conditions but not under changed conditions. Therefore, consistency is needed in test execution and potential noise detection. Summary of the Invention

[0004] In some aspects, an autonomous quality testing system for a vehicle includes a monitoring system positioned along a test track and configured to capture monitoring data, at least one audio sensor positioned at the vehicle and configured to capture audio data, and one or more vehicle system sensors configured to capture vehicle data. The autonomous quality testing system also includes an onboard controller communicatively coupled to the at least one audio sensor and the one or more vehicle system sensors, and an off-board controller communicatively coupled to each of the onboard controller and the monitoring system. The off-board controller is configured to execute an autonomous testing algorithm based on audio data received from the onboard controller and monitoring data from the monitoring system. The autonomous testing algorithm includes a classification function and is configured to classify noise from the audio data. The autonomous testing algorithm also includes a spontaneous path planning function and is configured to execute the spontaneous path planning function in response to incorrect noise in the classification.

[0005] In some examples, the spontaneous route planning function may include an identification function configured to identify maintenance stations based on classified error noise. The spontaneous route planning function may be configured to generate routes to the identified maintenance stations. Optionally, the onboard controller may be configured to communicate audio data and captured vehicle data with an external controller, and the external controller may be configured to generate a control loop based on the audio data, captured vehicle data, and captured monitoring data. The external controller may be configured to transmit the control loop to the onboard controller to execute vehicle control functions. In some cases, the control functions may include at least one of vehicle speed and vehicle direction functions.

[0006] In other aspects, a computer-implemented method causes data processing hardware to perform operations when executed by data processing hardware. The operations include: autonomously maneuvering a vehicle along a test track; monitoring audio data from the vehicle during maneuvering along the test track via at least one audio sensor; and monitoring monitoring data of the vehicle along the test track via a monitoring system positioned along the test track. The operations also include: performing a sound detection function of an autonomous testing algorithm based on the monitored audio data; detecting erroneous noise via the sound detection function; and classifying the detected erroneous noise via a classification function of the autonomous testing algorithm. The operations further include: identifying maintenance stations based on the classified erroneous noise; and performing a spontaneous path planning function of the autonomous testing algorithm in response to the identified maintenance stations and the classified erroneous noise.

[0007] In other examples, noise detection may include triangulation of the noise via at least three audio sensors. Optionally, performing a spontaneous path planning function may include generating a route to an identified maintenance station based on the classified erroneous noise, and the maintenance station may be configured to resolve the classified erroneous noise. Operation may include calibrating the autonomous testing algorithm based on training data captured by the monitoring system and at least one of the audio sensors. In some cases, calibrating the autonomous testing algorithm may include receiving vehicle data from one or more vehicle system sensors. Optionally, detecting erroneous noise may include identifying noise characteristics, and classifying erroneous noise may include categorizing the erroneous noise based on these characteristics. In a further example, classifying erroneous noise may include comparing the noise characteristics with one or more of the monitoring data and vehicle data captured by one or more vehicle system sensors via the autonomous testing algorithm.

[0008] In a further aspect, an autonomous quality testing system for vehicles includes data processing hardware and memory hardware communicating with the data processing hardware. The memory hardware stores instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations. These operations include: autonomously maneuvering the vehicle along a test track; monitoring audio data from the vehicle during maneuvering along the test track via at least one audio sensor; and monitoring monitoring data of the vehicle along the test track via a monitoring system positioned along the test track. The operations also include: performing a sound detection function of an autonomous testing algorithm based on the monitored audio data; detecting erroneous noise via the sound detection function; and classifying the detected erroneous noise via a classification function of the autonomous testing algorithm. The operations further include: identifying maintenance stations based on the classified erroneous noise; and performing a spontaneous path planning function of the autonomous testing algorithm in response to the identified maintenance stations and the classified erroneous noise.

[0009] In a further example, noise detection may include triangulation of the noise via at least three audio sensors. Optionally, performing a spontaneous path planning function may include generating a route to an identified maintenance station based on the classified erroneous noise, and the maintenance station may be configured to resolve the classified erroneous noise. Operation may include calibrating the autonomous testing algorithm based on training data captured by the monitoring system and at least one of the audio sensors. In some cases, calibrating the autonomous testing algorithm may include receiving vehicle data from one or more vehicle system sensors. Optionally, detecting erroneous noise may include identifying noise characteristics, and classifying the erroneous noise may include categorizing the erroneous noise based on these characteristics. In a further example, classifying the erroneous noise may include comparing the noise characteristics with one or more of the monitoring data and vehicle data captured by one or more vehicle system sensors via the autonomous testing algorithm. Attached Figure Description

[0010] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of this disclosure.

[0011] Figure 1 It is a perspective view of the vehicle based on this disclosure;

[0012] Figure 2 This is a schematic diagram of a vehicle executing an autonomous testing algorithm according to the autonomous quality testing system of this disclosure on a test track;

[0013] Figure 3 This is a block diagram of the autonomous quality testing system based on this disclosure;

[0014] Figure 4 This is a schematic diagram of the autonomous quality testing system based on this disclosure;

[0015] Figure 5This is a schematic diagram of a vehicle including vehicle system sensors according to this disclosure and multiple audio sensors, each sensor communicating with an onboard controller;

[0016] Figure 6A This is a schematic diagram of a vehicle on a test track as part of an autonomous quality testing system according to this disclosure, issuing an alarm from the autonomous quality testing system;

[0017] Figure 6B Is Figure 6A A schematic diagram of the vehicles on the test track; the quality test system responds to the alarm and performs autonomous route selection.

[0018] Figure 6C Is Figure 6B A schematic diagram of the vehicles on the test track, which are sent to a fixed station; and

[0019] Figure 7 This is an example flowchart of the autonomous quality testing system based on this disclosure.

[0020] In all the accompanying drawings, the corresponding reference numerals indicate the corresponding parts. Detailed Implementation

[0021] The example configuration will now be described more fully with reference to the accompanying drawings. The example configuration is provided so that this disclosure will be thorough and will fully communicate the scope of this disclosure to those skilled in the art. Specific details, such as examples of specific components, devices, and methods, are set forth to provide a thorough understanding of the configuration of this disclosure. It will be apparent to those skilled in the art that the specific details are not required, that the example configuration may be implemented in many different forms, and that the specific details and exemplary configuration should not be construed as limiting the scope of this disclosure.

[0022] The terminology used herein is for the purpose of describing specific exemplary configurations only and is not intended to be limiting. As used herein, the singular articles “a,” “an,” and “the” may also be intended to include plural forms unless the context clearly indicates otherwise. The terms “comprising,” “including,” “containing,” and “having” are inclusive, thus specifying the presence of features, steps, operations, elements, and / or components, but not excluding the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof. The method steps, processes, and operations described herein should not be construed as requiring them to be performed in the specific order discussed or shown, unless specifically identified as such. Additional or alternative steps may be employed.

[0023] When an element or layer is referred to as “on another element or layer,” “joined to,” “connected to,” “attached to,” or “linked to” another element or layer, it may be directly on, joined to, connected to, attached to, or linked to the other element or layer, or there may be intermediate elements or layers present. Conversely, when an element is referred to as “directly on another element or layer,” “directly joined to,” “directly connected to,” “directly attached to,” or “directly linked to” another element or layer, there may be no intermediate elements or layers present. Other terms used to describe relationships between elements should be interpreted in a similar manner (e.g., “between” vs. “directly between,” “adjacent” vs. “directly adjacent,” etc.). As used herein, the term “and / or” includes any and all combinations of one or more of the related listed items.

[0024] The terms first, second, third, etc., may be used herein to describe various elements, components, regions, layers, and / or parts. These elements, components, regions, layers, and / or parts should not be limited by these terms. These terms are used only to distinguish individual elements, components, regions, layers, or parts. Terms such as “first,” “second,” and other numerical terms do not imply order or sequence unless the context clearly indicates otherwise. Therefore, the first element, component, region, layer, or part discussed below may be referred to as the second element, component, region, layer, or part without departing from the teachings of the example configuration.

[0025] In this application, including the following definitions, the term "module" may be replaced by the term "circuit". The term "module" may refer to or be a part of an application-specific integrated circuit (ASIC), or include ASICs; digital, analog, or mixed-signal analog / digital discrete circuits; digital, analog, or mixed-signal analog / digital integrated circuits; combinational logic circuits; field-programmable gate arrays (FPGAs); processors (shared, dedicated, or grouped) that execute code; memory (shared, dedicated, or grouped) that stores code executed by the processor; other suitable hardware components that provide the functions described; or some or all of the above, such as in a system-on-a-chip.

[0026] The term "code" as used above can include software, firmware, and / or microcode, and can refer to programs, routines, functions, classes, and / or objects. The term "shared processor" includes a single processor that executes some or all of the code from multiple modules. The term "group processor" includes a processor, in conjunction with an additional processor, that executes some or all of the code from one or more modules. The term "shared memory" includes a single memory that stores some or all of the code from multiple modules. The term "group memory" includes memory, in conjunction with additional memory, that stores some or all of the code from one or more modules. The term "memory" can be a subset of the term "computer-readable medium." The term "computer-readable medium" does not include transient electrical and electromagnetic signals propagating through the medium and can therefore be considered tangible, non-transitory memory. Non-limiting examples of non-transitory memory include tangible computer-readable media, including non-volatile memory, magnetic memory, and optical memory.

[0027] The apparatus and methods described in this application may be implemented, in whole or in part, by one or more computer programs executed by one or more processors. The computer program includes processor-executable instructions stored on at least one non-transitory tangible computer-readable medium. The computer program may also include and / or depend on stored data.

[0028] A software application (i.e., a software resource) can refer to computer software that enables a computing device to perform tasks. In some examples, a software application may be referred to as an "application," "app," or "program." Example applications include, but are not limited to, system diagnostic applications, system management applications, system maintenance applications, word processing applications, spreadsheet applications, messaging applications, media streaming applications, social networking applications, and game applications.

[0029] Non-transitory memory can be a physical device used for temporary or permanent storage of programs (e.g., instruction sequences) or data (e.g., program state information) for use by a computing device. Non-transitory memory can be volatile and / or non-volatile addressable semiconductor memory. Examples of non-volatile memory include, but are not limited to, flash memory and read-only memory (ROM) / programmable read-only memory (PROM) / erasable programmable read-only memory (EPROM) / electrically erasable programmable read-only memory (EEPROM) (e.g., commonly used in firmware, such as bootloaders). Examples of volatile memory include, but are not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), phase-change memory (PCM), and magnetic disks or magnetic tapes.

[0030] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages ​​and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, non-transitory computer-readable medium, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0031] Various implementations of the systems and techniques described herein can be implemented in digital electronic and / or optical circuits, integrated circuits, specially designed ASICs (Application-Specific Integrated Circuits), computer hardware, firmware, software, and / or combinations thereof. These different implementations may include implementations in one or more computer programs executable and / or interpretable on a programmable system, the programmable system including at least one programmable processor, at least one input device, and at least one output device, the programmable processor being dedicated or general-purpose, coupled to receive data and instructions from and send data and instructions to the storage system.

[0032] The processes and logic flows described in this specification can be executed by one or more programmable processors, also known as data processing hardware, which execute one or more computer programs to perform functions by manipulating input data and generating output. These processes and logic flows can also be executed by special-purpose logic circuits, such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits). For example, processors suitable for executing computer programs include general-purpose and special-purpose microprocessors, as well as any one or more processors of any kind of digital computer. Typically, the processor receives instructions and data from read-only memory or random access memory, or both. The basic components of a computer are a processor for executing instructions and one or more storage devices for storing instructions and data. Typically, a computer will also include or be operatively coupled to one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, to receive data from or transfer data to, or both. However, a computer does not need to have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and storage devices, including, for example, semiconductor storage devices such as EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks or removable disks; magneto-optical disks; and CD-ROMs and DVD-ROMs. Processors and memory may be supplemented or incorporated therein by dedicated logic circuitry.

[0033] To provide interaction with the user, one or more aspects of this disclosure can be implemented on a computer having a display device for displaying information to the user, such as a CRT (cathode ray tube), LCD (liquid crystal display) monitor, or touchscreen, and optional keyboard and pointing device, such as a mouse or trackball, through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback, such as visual, auditory, or tactile feedback; and input from the user can be received in any form, including sound, speech, or tactile input. Furthermore, the computer can interact with the user by sending documents to and receiving documents from the device used by the user; for example, by sending a webpage to a web browser on the user's client device in response to a request received from a web browser.

[0034] refer to Figure 1-4The autonomous quality testing system 10 for vehicle 100 includes an onboard controller 102 and an external controller 200 for vehicle 100. The onboard controller 102 and the external controller 200 are communicatively coupled and operable during an autonomously executed test session 300 of vehicle 100. For example, vehicle 100 is maneuvered around test track 302 to execute the autonomous test algorithm 12 of the autonomous quality testing system 10 described herein. Vehicle 100 is configured as an autonomous vehicle 100 and / or a semi-autonomous vehicle 100, such as a software-defined vehicle. For example, the onboard controller 102 of vehicle 100 is communicatively coupled to the external controller 200, which is configured to communicate a control loop 202 with the onboard controller 102 as part of the execution of the autonomous quality testing system 10. Test track 302 is connected to one or more maintenance stations 304 via a walkway 306, which vehicle 100 can access during test session 300.

[0035] The autonomous quality testing system 10 communicatively couples an onboard controller 102, an external controller 200, and a monitoring system 310 positioned around a test track 302. For example, the onboard controller 102 and the external controller 200 may be communicatively coupled via cellular connections, including but not limited to 4G and 5G cellular data. The monitoring system 310 includes one or more imagers and / or light detection and ranging (LIDAR) systems configured to capture monitoring data 312 as the vehicle 100 maneuvers around the test track 302. For example, the monitoring system 310 is located around the test track 302 and monitors the movement of the vehicle 100. The movement of the vehicle 100 is captured as monitoring data 312 and communicates with the external controller 200.

[0036] Monitoring system 310 is configured to monitor the speed and / or orientation of vehicle 100 during test session 300 and communicate monitoring data 312 (e.g., speed and / or orientation) to external controller 200. As described below, external controller 200 utilizes monitoring data 312 when executing autonomous test algorithm 12. Sensors (i.e., imagers and / or LIDAR systems) of monitoring system 310 are fixed sensors mounted around test track 302 to capture the movement of vehicle 100 along test track 302 during test session 300. External controller 200 utilizes monitoring data 312 to execute autonomous test algorithm 12 and communicates control loop 202 with onboard controller 102 in part based on monitoring data 312.

[0037] Now for reference Figure 2-5The vehicle 100 is equipped with at least one audio sensor 104 configured to capture audio data 106. For example, the audio sensor 104 may include a microphone 104 disposed within the interior compartment 108 of the vehicle 100. The audio sensor 104 may include one or more audio sensors 104 (e.g., microphones) permanently installed in the vehicle 100. For example, the audio sensor 104 may be used for telephone conversations performed by the on-board controller 102 during vehicle 100 operation. The audio sensor 104 may be located at any feasible location along the vehicle 100 and / or within the interior compartment 108 of the vehicle 100. In some cases, the audio sensor 104 may be located near the driver's seat 110a, the front passenger seat 110b, and the rear passenger seat 110c. Therefore, the on-board controller 102 can capture and acquire audio data 106 from one or more audio sensors 104 located at different locations within the vehicle 100.

[0038] Vehicle 100 may also be equipped with various vehicle system sensors 112 configured to capture vehicle data 114. For example, vehicle system sensors 112 may include, but are not limited to, cameras, LiDAR, speedometers, pressure sensors, temperature sensors, steering sensors, and other vehicle system sensors 112 that may be equipped with vehicle 100. In addition to audio data 106, the onboard controller 102 may also receive vehicle data 114, which may be used by the autonomous testing algorithm 12 to evaluate vehicle 100 during test session 300, as described in more detail below.

[0039] Still referencing Figure 2-5 The onboard controller 102 is configured to communicate with the external controller 200 via audio data 106 and captured vehicle data 114. The external controller 200 is configured to generate a control loop 202 based on the audio data 106, the captured vehicle data 114, and the captured monitoring data 312. The control loop 202 is a control algorithm generated by the external controller 200, configured to autonomously control the movement of the vehicle 100. For example, the control loop 202 can be transmitted to the onboard controller 102 to execute control functions 120 of the vehicle 100.

[0040] In some examples, control function 120 may include at least one of vehicle 100 speed and vehicle 100 direction functions. For example, control loop 202 may include instructions to increase or decrease the speed of vehicle 100 and / or change the trajectory direction of vehicle 100. As described above, external controller 200 may communicate control loop 202 with onboard controller 102 via a cellular network, and onboard controller 102 executes control function 120 corresponding to control loop 202. In some cases, control loop 202 may include instructions to redirect vehicle 100 toward maintenance station 304 in response to autonomous test algorithm 12, as described below.

[0041] The external controller 200 is configured to execute an autonomous testing algorithm 12 based on audio data 106 received from the onboard controller 102 and monitoring data 312 from the monitoring system 310. The autonomous testing algorithm 12 is executed by the external controller's data processing hardware 204. The external controller 200 may also include memory hardware 206 that communicates with the data processing hardware 204. The memory hardware 206 can store instructions that, when executed on the data processing hardware 204, cause the data processing hardware 204 to perform operations (i.e., execute the autonomous testing algorithm 12). The autonomous testing algorithm 12 includes a sound detection function 14, a classification function 16, and a spontaneous path planning function 18, each of which will be described in detail below.

[0042] Further reference Figure 2-5 The memory hardware 206 can store a calibration model 20 of the autonomous quality testing system 10, which can be used to calibrate the autonomous testing algorithm 12 before executing the test session 300. The calibration model 20 can include training data 22, which includes, but is not limited to, predetermined frequencies and / or amplitudes that can correspond to error noise 30. The autonomous quality testing system 10 is configured to detect and classify error noise 30, such that the training data 22 helps train the autonomous testing algorithm 12 via the calibration model 20. The calibration model 20 can be further used to verify the audio sensor 104 by playing back the training data 22 corresponding to error noise 30 to ensure the detection of the audio sensor 104. Therefore, in addition to training the autonomous testing algorithm 12, the calibration model 20 can also be used to tune and check the audio sensor 104.

[0043] After executing calibration model 20, autonomous testing algorithm 12 is trained to identify various error noises 30. Autonomous testing algorithm 12 can be continuously trained and retrained using calibration model 20 to update and improve the detection of error noises 30. For example, additional error noises 30 can be added to training data 22, allowing autonomous testing algorithm 12 to be retrained by calibration model 20 to update its ability to identify new error noises 30. Therefore, autonomous testing algorithm 12 is pre-trained (i.e., during the initial manufacturing of vehicle 100) and can be retrained (i.e., during or after test session 300, for use in further test sessions 300).

[0044] Still referencing Figure 2-5The external controller 200 is configured to receive audio data 106, monitoring data 312, and vehicle data 114, each of which is evaluated by an autonomous testing algorithm 12. For example, the autonomous testing algorithm 12 monitors the audio data 106 and monitoring data 312 and performs a sound detection function 14 based on the monitored audio data 106. The autonomous testing algorithm 12 uses the sound detection function 14 to parse the audio data 106 to detect erroneous noise 30. The autonomous testing algorithm 12 is configured via the external controller 200 to cooperate with the onboard controller 102 to isolate and / or activate different audio sensors 104 based on the audio data 106. For example, the sound detection function 14 may issue an error flag 40, which may or may not be related to the erroneous noise 30. The external controller 200 may communicate with the onboard controller 102 to perform triangulation on the audio sensors 104, thereby improving the potential detection of erroneous noise 30. Triangulation commands may be included as part of the control loop 202, as described above.

[0045] The autonomous testing algorithm 12 uses monitoring data 312 and vehicle data 114 as reference points for performing the classification function 16. For example, audio data 106, along with monitoring data 312 and vehicle data 114, is aggregated and processed by the autonomous testing algorithm 12. The autonomous testing algorithm 12 can then perform the classification function 16 to classify erroneous noise 30 from the audio data 106. The classification function 16 can use monitoring data 312 and vehicle data 114 to identify the source of the erroneous noise 30. The sound detection function 14 can detect noise characteristics 32, and the classification function 16 can also use noise characteristics 32 to classify the identified erroneous noise 30. For example, the classification function 16 can compare noise characteristics 32 with one or more of the monitoring data 312 and vehicle data 114.

[0046] The autonomous testing algorithm 12 utilizes the classification or categorization error noise 30 to perform the spontaneous path planning function 18. The autonomous testing algorithm 12 identifies maintenance stations 304 corresponding to the categories associated with the classification error noise 30 based on the classification error noise 30. For example, memory hardware 206 can store maintenance categories 34, which can be used as part of the classification function 16 and during the spontaneous path planning function 18. Maintenance categories 34 can be associated with different maintenance stations 304 and the services provided at each corresponding maintenance station 304. Therefore, the spontaneous path planning function 18 is performed in response to the classification error noise 30 and the identified maintenance stations 304.

[0047] The spontaneous path planning function 18 generates a route 36 based on the classification of error noise 30. The spontaneous path planning function 18 executes automatically in response to the classification of error noise 30 and is configured to provide route 36 to maintenance station 304 for repair. The autonomous testing algorithm 12 can be configured to generate an error flag 40 indicating the error probability 42 of error noise 30. For example, the error probability 42 reflects the likelihood (e.g., probability) that error noise 30 is associated with a specific feature, function, or setting used for repair. The spontaneous path planning function 18 uses the error flag 40 and the error probability 42, combined with the classification of error noise 30, to identify maintenance station 304 and generate a route 36 to maintenance station 304. Maintenance station 304 is configured to resolve the classified error noise 30 such that the error noise 30 can be repaired at maintenance station 304. Maintenance station 304 includes multiple maintenance stations 304, which can be located separately or independently, such that the spontaneous path planning function 18 is configured to identify the most suitable maintenance station 304 based on the classified error noise 30. The spontaneous path planning function 18 is also configured to generate a route 36 to maintenance station 304, which is best equipped to resolve error noise 30.

[0048] refer to Figure 3 and 6A -6C illustrates an autonomous quality testing system 10, in which a vehicle 100 maneuvers along a test track 302 during a test session 300. Captured audio data 106 includes error noise 30, shown as an alarm for illustrative purposes. Error noise 30 is captured by the onboard controller 102 and communicated with the external controller 200 for processing by the autonomous testing algorithm 12. Once the autonomous testing algorithm 12 performs the sound detection function 14 and classification function 16 as described above, it generates a route 36 via a spontaneous path planning function 18. As part of a control loop 202, route 36 is transmitted from the external controller 200 to the onboard controller 102. For example, the control loop 202 may include instructions to divert the vehicle 100 to route 36. Figure 6B The image shows vehicle 100 moving towards maintenance station 304. Figure 6C Vehicle 100 at the corresponding maintenance station 304 is shown. Although a single maintenance station 304 is depicted, as stated above, it is conceivable that any number of maintenance stations 304 can be identified and used as part of the autonomous quality testing system 10.

[0049] refer to Figure 1-7 The method 700 for operating the autonomous quality testing system 10 is described. Specifically, method 700 in... Figure 7As shown in the diagram. At 702, vehicle 100 is maneuvered onto test track 302 and accelerated to a predetermined speed. At 704, the autonomous quality testing system 10 begins collecting data, including monitoring data 312, vehicle data 114, and audio data 106. At 706, the external controller 200 performs a status check 24 of the autonomous quality algorithm 12 to assess whether an error flag 40 has been generated. At 708, the external controller 200 filters and samples the audio data 106 through the autonomous testing algorithm 12 to identify potential error noise 30. At 710, the classification function 16 categorizes any potentially identified error noise 30. At 712, the autonomous quality testing system 10 determines whether the audio data 106, including any potential error noise 30, passes or fails the test session 300. If no significant error noise 30 is identified, at 714, the external controller 200 can issue a pass for the audio data 106, and vehicle 100 can proceed to the final check.

[0050] If the error noise 30 is identified and classified, the external controller 200 merges the audio data 106 and the identified error noise 30 at 716, and sends an error flag 40 to the manufacturing execution system of the maintenance station 304 at 718. Then, at 720, the external controller 200 sends a control loop 202, including route 36, to the maintenance station 304. At 722, repair and verification are performed on the vehicle 100. At 724, the repair personnel determine whether the vehicle 100 should be retested using the autonomous quality testing system 10.

[0051] Refer again Figure 1-7 The autonomous quality testing system 10 advantageously automates the testing session 300 after the manufacture of vehicle 100. Audio sensor 104 is used to capture audio data 106 to evaluate vehicle 100, ensuring the consistency of detection of potential error noise 30. Furthermore, the autonomous testing algorithm 12's classification of error noise 30 advantageously allows the autonomous quality testing system 10 to identify maintenance stations 304 associated with the error noise 30. For example, the autonomous testing algorithm 12 can accurately identify error noise 30 corresponding to loose trimming and generate a route 36 using the spontaneous path planning function 18 based on the identified and classified error noise 30. The ability to guide vehicle 100 to the correct maintenance station 304 improves the overall efficiency of identifying potential errors and correcting identified errors. For example, the automated testing process and route generation increase the likelihood of consistent error identification due to the consistent execution of the testing process.

[0052] Many embodiments have been described. However, it should be understood that various modifications can be made without departing from the spirit and scope of this disclosure. Therefore, other embodiments are also within the scope of the following claims.

[0053] The foregoing description has been provided for purposes of illustration and description. It is not intended to be exhaustive or limiting of this disclosure. Individual elements or features of a particular configuration are generally not limited to that particular configuration, but where applicable, they are interchangeable and can be used in selected configurations, even if not specifically shown or described. This can also be varied in many ways. Such variations should not be considered as departing from this disclosure, and all such modifications are intended to be included within the scope of this disclosure.

Claims

1. A computer-implemented method that, when executed by data processing hardware, causes the data processing hardware to perform operations comprising: autonomously maneuvering a vehicle along a test track; monitoring, via at least one audio sensor, audio data from the vehicle during the maneuvering of the vehicle along the test track; monitoring, via a monitoring system disposed along the test track, monitoring data of the vehicle along the test track; performing, by an autonomous test algorithm, a sound detection function based on the monitored audio data; detecting, via the sound detection function, error noise; classifying, via a classification function of the autonomous test algorithm, the detected error noise; identifying, based on the classified error noise, a maintenance station; and performing, in response to the identified maintenance station and the classified error noise, a spontaneous path planning function of the autonomous test algorithm. Detecting the noise includes triangulating the noise via the at least three audio sensors.

2. The method of claim 1, wherein, Performing the spontaneous path planning function includes generating a route to the identified maintenance station based on the classified error noise.

3. The method of claim 1, wherein, The maintenance station is configured to address the classified error noise.

4. The method of claim 3, wherein, 5. The method of claim 1, further comprising calibrating the autonomous test algorithm based on training data captured by each of the monitoring system and the at least one audio sensor. Calibrating the autonomous test algorithm includes receiving vehicle data from one or more vehicle system sensors.

6. The method of claim 5, wherein, Detecting the error noise includes identifying noise characteristics, and classifying the error noise includes categorizing the error noise based on the noise characteristics.

7. The method of claim 1, wherein, Classifying the error noise includes, via the autonomous test algorithm, comparing the noise characteristics to one or more of the monitoring data and the vehicle data captured by the one or more vehicle system sensors.

8. The method of claim 7, wherein, 9. An autonomous quality testing system configured to perform the method of claim 1.

10. A vehicle equipped with the autonomous quality testing system of claim 9. ​

Images