Radar sensor alignment module for a vehicle

Abstract

A sensor alignment module according to an embodiment of the present application includes a processing unit configured to receive radar data sensed by a radar and to configure a correction angle for the radar data by using the radar data, and a communication unit configured to communicate with a cloud server, wherein the processing unit adjusts the correction angle through the cloud server when it is determined that the correction angle for the radar data needs to be adjusted.

Description

Technical Field

[0001] This disclosure relates to power conversion devices, and more specifically, to a sensor alignment module that uses a cloud to align the angle of a radar sensor, and a vehicle that includes the sensor alignment module. Background Technology

[0002] Radar sensors mounted on vehicles transmit radio waves via antennas and receive reflected waves from targets to detect the distance or speed of movement of those targets. Because the radar sensors are mounted externally to the vehicle, vibrations generated during vehicle movement can cause them to shift from their initial position, resulting in misalignment. When a sensor is misaligned, the misalignment angle must be adjusted to correct errors in the sensor data; however, calculating the correction angle required to correct these errors is resource-intensive. Summary of the Invention

[0003] Technical issues

[0004] The purpose of this disclosure is to provide a sensor alignment module and a vehicle including the sensor alignment module, the sensor alignment module using a cloud to align the angle of a radar sensor.

[0005] Technical solutions

[0006] To address this technical problem, according to embodiments of the present disclosure, the sensor alignment module includes: a processing unit configured to receive radar data sensed by radar and use the radar data to set a correction angle for the radar data; and a communication unit configured to communicate with a cloud server, wherein when it is determined that the correction angle for the radar data needs to be adjusted, the processing unit adjusts the correction angle through the cloud server.

[0007] In addition, the processing unit can determine whether the radar data meets the correction angle adjustment conditions, and when the correction angle adjustment conditions are met, calculate the first deformation angle of the radar based on the radar data, determine whether the first correction reflection angle that reflects the currently set correction angle to the first deformation angle is within the first threshold angle, and determine whether to adjust the correction angle based on the result.

[0008] Furthermore, when the first correction response angle deviates from the first threshold angle, the processing unit can send radar data to the cloud server and receive the correction angle to be changed from the cloud server.

[0009] Furthermore, the radar data can be data based on the radar's coordinate system. When the first correction response angle is within the threshold angle, the processing unit can convert the radar data into second data based on the vehicle's coordinate system, calculate the second deformation angle based on the second data, determine whether the second correction response angle that reflects the currently set correction angle in the second deformation angle is within the second threshold angle, and determine whether to adjust the correction angle based on whether the result is the same as the result of determining whether the first correction response angle is within the first threshold angle.

[0010] Furthermore, when the second result determining whether the second correction response angle is within the second threshold angle is different from the first result determining whether the first correction response angle is within the first threshold angle, the processing unit may change the result of using the first result to determine whether to adjust the correction angle.

[0011] Furthermore, when the first correction response angle is within the first threshold angle and the first result is different from the second result, the processing unit can adjust the correction angle through the cloud server. When the first correction response angle deviates from the first threshold angle and the first result is different from the second result, the processing unit can maintain the current correction angle.

[0012] In addition, the processing unit can receive vehicle information from the vehicle and use the vehicle information to determine whether the radar data meets the correction angle adjustment conditions.

[0013] In addition, vehicle information may include at least one of yaw data, acceleration data, and speed data.

[0014] In addition, the communication unit can send radar data, unique identification information of radar data and timestamp to the cloud server, receive data, unique identification information, timestamp and correction angle from the cloud server, and change the correction angle to a new correction angle based on the radar data with a timestamp later than the timestamp corresponding to the earliest time point in the radar data sent to the cloud server.

[0015] In addition, the sensor alignment module also includes a storage unit configured to store radar data and initial sensor position information of the radar. The processing unit can use the radar data stored in the storage unit to adjust the correction angle of the radar data.

[0016] To address the technical problem, according to embodiments of this disclosure, a vehicle includes: a sensing unit including a radar; a storage unit for storing data from the sensing unit; and a processing module for correcting the data from the sensing unit. The processing module includes: a processing unit that receives radar data sensed by the radar and uses the radar data to set a correction angle for the radar data; and a communication unit that communicates with a cloud server. When the processing unit determines that the correction angle for the radar data needs to be adjusted, it adjusts the correction angle via the cloud server.

[0017] Beneficial effects

[0018] According to embodiments of this disclosure, by calculating the sensor correction angle in a cloud environment rather than in the vehicle, the misalignment angle of the sensor can be corrected without using vehicle resources. Furthermore, by utilizing a large amount of data from a cloud server, an accurate correction angle can be calculated. Attached Figure Description

[0019] Figure 1 This is a block diagram illustrating a sensor alignment module according to one embodiment of the present disclosure.

[0020] Figures 2 to 8 This is a diagram illustrating a sensor alignment module according to an embodiment of the present disclosure.

[0021] Figures 9 to 14 This is a diagram illustrating a sensor alignment module according to another embodiment of the present disclosure.

[0022] Figure 15 This is a block diagram illustrating a vehicle according to one embodiment of the present disclosure. Detailed Implementation

[0023] In the following, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0024] However, the technical concept of this disclosure is not limited to some of the embodiments described, but can be implemented in various different forms, and within the scope of the technical concept of this disclosure, one or more components between embodiments can be selectively combined or replaced and used.

[0025] Furthermore, unless explicitly and specifically defined and described, the terms (including technical and scientific terms) used in the embodiments of this disclosure may be interpreted as having a meaning that is generally understood by one of ordinary skill in the art to which this disclosure pertains, and commonly used terms (e.g., terms defined in a dictionary) may be interpreted in light of the contextual meaning of the relevant art.

[0026] Furthermore, the terminology used in the embodiments of this disclosure is intended to describe the embodiments and not to limit the disclosure.

[0027] In this specification, unless otherwise specified in the phrase, the singular may also include the plural, and when it is described as “at least one (or one or more) of A, B, C”, it may include one or more of all combinations that can be combined with A, B, C.

[0028] Furthermore, when describing the components of this embodiment of the present disclosure, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended only to distinguish the components from other components and are not intended to limit the nature, order, or sequence of the components.

[0029] Furthermore, when a component is described as being “connected,” “coupled,” or “accessed” to another component, it can include not only cases where the component is directly “connected,” “coupled,” or “accessed” to other components, but also cases where the component is “connected,” “coupled,” or “accessed” to another component through which the component is connected, coupled, or “accessed” to other components.

[0030] Furthermore, when described as being formed or positioned “above” or “below” each component, “above” and “below” include not only cases where two components are in direct contact with each other, but also cases where one or more other components are formed or positioned between the two components. Additionally, when expressed as “above” or “below”, it can include the meaning of a downward direction and an upward direction based on a component.

[0031] Variations of this embodiment may include some components of each embodiment and some components of other embodiments. In other words, a variation may include one of various embodiments, but omit some components and include some components of corresponding other embodiments. Alternatively, the opposite is also possible. The features, structures, effects, etc., described in the embodiments are included in at least one embodiment, and are not necessarily limited to only one embodiment. Furthermore, the features, structures, effects, etc., exemplified in each embodiment can be combined, modified, and implemented in other embodiments by those skilled in the art to which the embodiments pertain. Therefore, details regarding such combinations and modifications should be interpreted as being included within the scope of the embodiments.

[0032] Figure 1 This is a block diagram illustrating a sensor alignment module according to one embodiment of the present disclosure, and Figures 2 to 8 This is a diagram illustrating a sensor alignment module according to an embodiment of the present disclosure.

[0033] This disclosure includes a processing unit 110 and a communication unit 120 according to embodiments of the present disclosure. A sensor alignment module 100 according to embodiments of the present disclosure can be mounted on a vehicle 600. The vehicle 600 may include a sensing unit 200, which includes a radar 210, and the sensor alignment module 100 can align the sensing unit 200 by correcting misaligned angles. The sensing unit 200 may include radar 210, LiDAR 220, a positioning sensor (GPS) 240, etc., and may include a camera device 230, navigation information (HP map) 250, etc. The vehicle 600 may be an autonomous vehicle or an autonomous robot, and can use data from the sensing unit 200 to generate autonomous driving paths and control the vehicle accordingly. The vehicle 600 may be a software-defined vehicle (SDV), which is a vehicle that uses software to control and manage hardware.

[0034] Radar 210 can be mounted on vehicle 600, and may become misaligned with its mounting position due to vibrations caused by the movement of vehicle 600. To ensure accurate measurements by radar 210, a correction angle must be applied to correct the misalignment. Since the misalignment angle may change continuously due to vibration, the correction angle must also be adjusted accordingly.

[0035] To this end, processing unit 110 receives radar data sensed by radar 210 and uses this radar data to set a correction angle for the radar data. If processing unit 110 determines that a correction angle adjustment is needed, it uses cloud server 400 for correction angle adjustment. The process of adjusting the correction angle will be described in detail below.

[0036] The communication unit 120 can communicate with the cloud server 400. The communication unit 120 can communicate with the cloud server 400 wirelessly. The communication unit 120 can send a correction angle request to the cloud server 400 and receive the correction angle calculated by the cloud server 400.

[0037] When a correction angle adjustment is required, the processing unit 110 can send a correction angle request to the cloud server 400 and can use radar data to determine whether a correction angle adjustment is needed. The radar data generated by the radar 210 is stored in the storage unit 300, and the processing unit 110 can use the radar data stored in the storage unit 300 to determine whether a correction angle adjustment is needed. The storage unit 300 can receive and store data from sensors included in the sensing unit 200. Since the measurement period may be different for each sensor, the storage unit 300 can store the data as an integrated storage unit that integrates data from the sensors. The storage unit 300 can store timestamps for each data collection time.

[0038] The processing unit 110 determines whether the radar data meets the correction angle adjustment conditions. If the correction angle adjustment conditions are met, it calculates the first deformation angle of the radar 210 based on the radar data, determines whether the first correction reflection angle that reflects the currently set correction angle in the first deformation angle is within the first threshold angle, and determines whether to adjust the correction angle based on the result.

[0039] Processing unit 110 can determine whether the radar data first meets the correction angle adjustment conditions. If the radar data includes information that can determine the degree of misalignment of radar 210, the radar data can be used to determine the correction angle adjustment, thereby first determining whether the radar data meets the correction angle adjustment conditions.

[0040] Radar data is collected from radar 210 and may include data obtained by post-processing signals reflected from objects by radar 210 and installation information when the sensor is initially installed. The result of post-processing the reflected signals is represented as points in a coordinate system, and these points may be referred to as a point cloud or detection list. Each point may include range, azimuth, elevation, power, radial velocity, and initial sensor position information. Here, range is the distance to the detection point relative to radar 210, azimuth is the angle of the detection point in the horizontal plane relative to the front of the radar, elevation is the angle of the detection point in the vertical plane relative to the front of the radar, power is the reflected signal strength of the detection point, line-of-sight velocity is the relative velocity of the detection point, and the initial sensor position information is the installation angle used to correct for errors that occurred during installation of each sensor at the factory, and this angle can be used as a relative standard for coordinates used to subsequently calculate the point cloud.

[0041] In the process of converting the coordinate plane of the point cloud of radar 210 to the coordinate plane of the vehicle, the existing installation position of radar 210 is used as a reference. However, due to an accident or major impact, the installed position of radar 210 may differ from the existing installation position. Therefore, if the installation position of radar 210 is not aligned with the existing position, the installation position may be misaligned during the process of converting the coordinate plane of the point cloud, and thus the installation position may be converted to an incorrect coordinate position.

[0042] To eliminate such errors, automatic alignment or angle correction can be performed, and the current misalignment angle of the radar can be calculated using a list of detections from a specific environment (e.g., correction angle adjustment conditions). For example, radar data measured in a road environment where objects with high reflectivity are positioned in a straight line (e.g., a straight guardrail) can be used.

[0043] This process can be referred to as a condition check process. The processing unit 110 can determine that radar data containing information about objects with high reflectivity (such as guardrails) set in a preset number or greater meets the corresponding conditions.

[0044] At this time, processing unit 110 can perform a condition check process by using vehicle information together. Processing unit 110 can use yaw rate, acceleration, and vehicle speed as vehicle information. Yaw rate is information indicating the degree of rotation of the front of vehicle 600.

[0045] The processing unit 110 can determine whether the correction angle adjustment conditions are met when the yaw rate, acceleration, and velocity are under preset conditions. Specifically, the processing unit 110 can determine whether the correction angle adjustment conditions are met when the yaw rate is less than ±4 degrees / second, the acceleration is less than ±0.5 m / s, and the velocity is greater than 30 kmph. In other words, when an object with high reflectivity is positioned on a straight road and the condition of constant linear movement is met, the processing unit 110 can determine whether to use radar data to adjust the correction angle under the corresponding conditions.

[0046] The processing unit 110 can check the 111 correction angle adjustment conditions, and when the conditions are met, calculate the first deformation angle of the radar 210 based on the radar data. Using the results of measuring the radar data and the results derived from the vehicle information, the first deformation angle 114 can be calculated using the difference between the measured angle and the actual angle. This first deformation angle is the misalignment deformation angle of the radar sensor.

[0047] Processing unit 110 can calculate a first correction response angle by reflecting the currently set correction angle onto a calculated first deformation angle, determine whether the first correction response angle is within a first threshold angle, and determine whether to adjust the correction angle based on the result. The first threshold angle can be used to calculate the first correction response angle by reflecting the initial or previously set correction angle onto the first deformation angle, and to determine whether 115 needs to adjust the first correction response angle. The first threshold angle can be an allowable error range, can be set for vehicle safety, or can be set by the user. Here, the first correction response angle can be calculated as follows.

[0048] Angle offset = Original angle offset + Correction angle

[0049] Here, the angular offset is the first correction response angle, the original angular offset is the first deformation angle, and the correction angle is the current correction angle. The first correction response angle indicates the degree of misalignment relative to the initial radar sensor position. If the first correction response angle is within a first threshold angle, the radar 210 is determined to be in an on-position, which is a position without misalignment. If the first correction response angle exceeds the first threshold angle, the radar 210 is determined to be in an off-position, which is a misaligned position. When the current state is determined to be an off-position, the correction angle adjustment can be performed via the cloud server 400.

[0050] When the first correction angle exceeds the first threshold angle, the processing unit 110 determines that the correction angle needs to be adjusted, sends radar data to the cloud server 400, and receives the correction angle to be changed from the cloud server 400. If the first correction angle is outside the first threshold angle, the request for the correction angle can be sent to the cloud server 400 along with the radar data through communication with the cloud server 400.

[0051] Radar data from autonomous vehicles contains a wealth of information, and calculating the correction angle based on this information requires significant resources. Furthermore, the more data utilized, the more accurate the correction angle calculation becomes. The sensor alignment module 100 according to embodiments of this disclosure can calculate the correction angle using a cloud server 400 instead of within the module or the vehicle 600, and the cloud server 400 can utilize substantial resources.

[0052] The cloud server 400 may be a module of software used in a cloud environment outside the vehicle 600. The cloud server 400 may include various algorithms for calculating the correction angle of the radar 210, and may include neural networks trained to calculate the correction angle based on radar data through machine learning. Furthermore, the cloud server 400 may use various methods for calculating the correction angle based on radar data.

[0053] When communicating with the cloud server 400, the communication unit 120 can send radar data, unique identification information of radar data and timestamp to the cloud server 400, and can receive data, unique identification information, timestamp and correction angle from the cloud server 400.

[0054] When radar data is generated from radar 210 and stored in storage unit 300, the timestamp is stored together, and unique identification information can be assigned and stored when the radar data meets the correction angle adjustment conditions. The unique ID is information that can distinguish data that meets the verification conditions, and can be assigned using sequentially assigned frame numbers or the hash value of the incoming data. Here, the hash function is a function that maps data of arbitrary length to data of fixed length, and the hash can refer to the value obtained by the hash function. When communication unit 120 sends radar data to cloud server 400, the communication unit can send the timestamp and unique ID of the radar data together.

[0055] Communication unit 120 can store sensor data, including radar data, in data queue 121 and send multiple stored sensor data sets to cloud server 400. At this time, the number of sensor data sets stored in data queue 121 may be limited. Therefore, to check which sensor data is being sent when sending to cloud server 400, a start timestamp can be set and stored. If the current start timestamp is empty, the timestamp of the first sensor data to be stored can be set as the start timestamp and stored 122. When sensor data stored in data queue 121 is sent to cloud server 400, its validity can be determined by comparing it with the timestamp of data subsequently received from cloud server 400 using the currently set start timestamp.

[0056] The cloud server 400 can use sensor data, including radar data, received via the communication unit 120 to calculate the correction angle of the radar 210. The cloud server 400 may include various algorithms for calculating the correction angle of the radar 210, and may include neural networks trained to calculate the correction angle based on radar data through machine learning. Furthermore, the cloud server 400 can use various methods for calculating the correction angle based on radar data.

[0057] The cloud server 400 can send sensor data, unique identifiers and timestamps of the sensor data, and the correction angle calculated based on the sensor data to the communication unit 120.

[0058] The communication unit 120 can change the correction angle to a new correction angle based on radar data sent to the cloud server 400 that has a timestamp later than the start timestamp corresponding to the earliest radar data. The communication unit 120 compares the timestamp of the received sensor data with the currently set start timestamp. If the timestamp of the currently received sensor data is before the currently set start timestamp, then the currently received sensor data is not data for adjusting the correction angle; therefore, in this case, the process can be terminated without adjusting the correction angle. If the timestamp of the currently received sensor data is before the currently set start timestamp, then the currently received sensor data is data for adjusting the correction angle; therefore, the processing unit 110 can adjust the correction angle by changing the correction angle using the correction angle calculated based on the corresponding sensor data.

[0059] When the first correction angle is within a first threshold angle, the processing unit 110 can convert the radar data into second data based on the vehicle's coordinate system. The processing unit 110 can determine that the radar 210 is in an aligned position, which is the position where the radar 210 is not misaligned. Since the radar data is based on the radar 210's coordinate system, if it is determined that it corresponds to an aligned position in the radar coordinate system, the processing unit 110 can perform a further check to see if any correction angle adjustment is needed in the vehicle's coordinate system. For this purpose, coordinate transformation 112 can be performed to convert the radar coordinate system into the vehicle's coordinate system.

[0060] Subsequently, if the first correction response angle is within the threshold angle, the processing unit 110 converts the radar data into second data according to the vehicle's coordinate system, calculates the second deformation angle according to the second data, determines whether the second correction response angle that reflects the currently set correction angle in the second deformation angle is within the second threshold angle, and determines whether to adjust the correction angle based on whether the result is the same as the result of determining whether the first correction response angle is within the first threshold angle.

[0061] Calculate the second deformation angle in the vehicle coordinate system, calculate the second correction response angle that reflects the currently set correction angle, and determine that the second correction response angle is within the second threshold angle. Based on the result, it can be checked whether it is the same as the previously determined current state.

[0062] Angle offset_2 = Original angle offset_2 + Correction angle_2

[0063] Here, angular offset_2 is the second correction response angle, original angular offset_2 is the second deformation angle, and correction angle_2 is the current correction angle. The second correction response angle can represent the degree of misalignment in the vehicle coordinate system, and if the second correction response angle is within the second threshold angle, the vehicle is determined to be in a correct position, which is a position without misalignment in the vehicle coordinate system, and a correct angle flag can be set. If the second correction response angle exceeds the second threshold angle, the correct angle flag can be cleared.

[0064] When the second result determining whether the second correction response angle is within the second threshold angle is different from the first result determining whether the first correction response angle is within the first threshold angle, repeated a preset number of times or more, the processing unit 110 may change the result used to determine whether to adjust the correction angle using the first result. By comparing the first result determining whether the first correction response angle is within the first threshold angle with the second result determining whether the second correction response angle is within the second threshold angle, it can be verified whether the first result is an accurate determination.

[0065] At this point, it can be determined whether the first result for determining whether the first correction response angle is within the first threshold angle is derived from normal radar data or from radar data with incorrect measurements or containing errors. To this end, the first result and the second result are compared multiple times, and if the first result differs from the second result a preset number of times or more, the result used to determine whether to adjust the correction angle can be changed. In other words, even if the first result is determined to be in the correct position, if the first result differs from the second result a preset number of times or more, the current state is changed to an off-center position, and the correction angle can be adjusted via the cloud server 400 based on the off-center position. Conversely, even if the first result is determined to be in the off-center position, if the first result differs from the second result a preset number of times or more, the current state can be changed to the correct position, and the correction angle can be adjusted via the cloud server 400 without adjusting the off-center position.

[0066] In other words, state determination 113 can be performed using coordinate-transformed data from coordinate transformation 112.

[0067] like Figure 7 As shown, a comparison can be made to see if the first result and the second result are the same. If the first result and the second result are different, the different state counter value can be increased, and if the first result and the second result are the same, the different state counter can be reset. After increasing the different state counter value due to the difference between the first result and the second result, if the number of times the different state counter is increased exceeds the number of times the state has been changed, the current state can be changed depending on whether the correction angle is adjusted.

[0068] If the first correction response angle is within the first threshold angle and the first result differs from the second result, and this is repeated a preset number of times or more, the processing unit 110 can adjust the correction angle via the cloud server 400. In other words, when the first result is in a positive position or changes to an off-position through repeated comparisons of the first and second results, the correction angle can be adjusted via the cloud server 400.

[0069] When the first correction response angle is misaligned with the first threshold angle and the first result differs from the second result a preset number of times or more, the processing unit 110 can maintain the current correction angle. In other words, if the first result is an off-center position or changes to a positive position by repeatedly comparing the first result with the second result, the correction angle does not need to be adjusted.

[0070] State determination 113 is a process used to prevent malfunctions caused by value spikes due to hits or misses, and various state determination methods can be used. For example, if a sequence of hit, miss, hit, hit occurs, a change can be made if a hit occurs twice consecutively. Since radar data collected in a real-world environment may contain false positives, misalignment can be determined if a specified number of consecutive occurrences is exceeded.

[0071] Furthermore, a temporary current state and the current state can be distinguished by comparing the unique ID of the data used for coordinate transformation 112 and state determination 113 with the most recent unique ID. A comparison of the unique ID can be performed to check that all data stored on the cloud server 400 has been reflected to the latest data when the installation state is in an off-center position. When the installation state is in a positive position, the current state can also be updated immediately because the unique ID of the data is the most recent unique ID.

[0072] For example, when the current state is in the positive position, the current unique ID is 5, the state change threshold is 3, the mismatch count is 0, and the correction angle and unique ID value are consecutively (true, 1), (false, 2), (false, 3), (false, 4), and (false, 5). When (false, 5) is received, the mismatch count exceeds the state change threshold. Therefore, the current state is temporarily changed to the off-center position, and the mismatch count is reset. Since the current unique ID and the unique ID of the last processed data are both 5, the current state can also be changed to the off-center position.

[0073] As another example, when the current state is in an off-center position, the current unique ID is 6, the state change threshold is 2, and the mismatch count is 0. The correction angle and unique ID values ​​are consecutively (true, 1), (true, 2), (true, 3), (false, 4), (false, 5), and (false, 6). When (true, 3) is received, because the mismatch count exceeds the state change threshold, the temporary current state is changed to a positive position, the mismatch count is reset, and since the current unique ID and the unique ID of the last processed data are different (6 and 3), the current state can be maintained in an off-center position. Later, when (false, 6) is received, the inconsistency count exceeds the number of state changes, so the temporary current state is changed to an off-center position, and the different state counter is initialized to 0. Since the current unique identifier and the unique identifier of the last processed data are the same (6), the current state can be maintained in an off-center position based on the temporary current state, and the correction angle can be adjusted via the cloud server 400 based on the off-center position.

[0074] Figures 9 to 14 This is a diagram illustrating a sensor alignment module according to another embodiment of the present disclosure. Figures 9 to 14 The detailed description of each component in the document corresponds to Figures 1 to 8 Detailed descriptions of each component are omitted below, as redundant descriptions will be omitted.

[0075] The sensor alignment module according to embodiments of this disclosure may be an automatic alignment module 510. Vehicle information and radar data received from the vehicle 260 and the sensing unit 200 including radar 210 may be stored in a storage device (intermediate storage device) 310. Here, the sensor receives data, the storage device 310 is an integrated storage device for sensor data collected at different intervals, the automatic alignment module 510 is included in a software module used within the vehicle, and the cloud 410 may be a software module used in a cloud environment other than the vehicle. Since the data collection interval may be different for each sensor, the storage device 310 may store the latest information collected for each sensor and store the collection time together.

[0076] Vehicle information (Vehicle Info) is the information provided by default by Vehicle 600 and may include yaw rate, acceleration, and velocity collected from each sensor in the vehicle.

[0077] Radar sensor information, or radar Info, is information collected from radar 210 and may include information obtained by post-processing signals reflected from objects from radar 210, as well as installation information at the time of initial sensor installation. Radar sensor information may include a detection list in which the results of post-processing of the reflected signals are represented as points in a coordinate system, and each point may include range, azimuth, elevation, power, radial velocity, and initial sensor position.

[0078] As the trend shifts towards Software-Defined Vehicles (SDV), Software-Defined Components (SDCs) are also increasing. This creates constraints where individual components / modules cannot utilize the limited vehicle memory / storage space independently, necessitating improved efficiency. The automatic alignment module 510, according to embodiments of this disclosure, applies the data and algorithms required for automatic alignment (auto-alignment) to a cloud (cloud 410) based on the SDV concept. By using cloud 410, the increased computing resources are significantly greater than before, allowing the use of more complex but accurate automatic alignment algorithms. Furthermore, data that can be used for complex algorithms (e.g., LiDAR, HDMap, etc. for radar auto-alignment) can be sent to cloud 410 and used together.

[0079] At this point, data can be acquired only under specific conditions (e.g., a straight line in the guardrail or a road in which objects with high reflectivity are arranged in a straight line) (condition check, 511), and methods for distinguishing data using unique IDs and timestamps can be applied (state determination 513 and cloud communication 520), while using the cloud 410 as data storage without wasting data.

[0080] The sensor updates each collected data point to storage device 310, and the automatic alignment module 510 performs a condition check 511 on the radar and vehicle information in the updated data in storage device 310 to determine whether the environment meets the conditions. A meeting environment is a straight road and includes environments with reflective objects such as guardrails on the left and right sides. If the conditions are met, valid data = true is returned; if the conditions are not met, valid data = false is returned. If the environment meets the conditions, the original angle offset is calculated 514, a unique ID is assigned to the data, and the unique ID number of the most recently collected data (recently unique ID, 517) is stored. Depending on the current state of the radar, angle adjustment 512 or cloud communication 520 is performed.

[0081] "Original angular offset" is the misalignment angle of the radar before the correction angle is added, and the unique identification information (unique ID) can be a value that can distinguish data that has passed condition check 511. For example, the unique identification information can be a sequentially assigned frame number or a hash value of the incoming data, where the hash function is a function that maps data of arbitrary length to data of fixed length, and the hash can refer to the value obtained by the hash function. If the degree of misalignment relative to the initial sensor position as the standard when the radar was manufactured (angular offset = original angular offset + correction angle) is within the specified misalignment allowable threshold (offset limit), the installation state (current state) is called the positive position; if it is outside the specified misalignment allowable threshold, the installation state (current state) is called the off-center position.

[0082] In the correct position, during angle adjustment 512, the process of converting the radar coordinate system to the vehicle coordinate system calculates the coordinates of the object detected by the radar according to the vehicle's relative coordinates, and these values ​​can be used to return whether misalignment (correct angle flag) exists based on the data. The presence of misalignment (correct angle flag) indicates whether the sum of the degree of misalignment calculated based on the data (original angle offset) and the currently used correction angle (correction angle) is within the allowable misalignment threshold (offset limit), and can be true or false. The presence of misalignment (correct angle flag) is a value derived based on a single piece of currently processed data, while the installation status is a value derived by accumulating the misalignment values ​​of continuous data in status determination 513, and can represent different values. The returned current angle flag can be used to perform installation status determination (status determination) 513.

[0083] In the case of an off-center position, cloud communication 520 is performed to receive the correction value (correction angle) by performing automatic alignment (angle correction) 411 in cloud 410. After receiving the value returned from cloud 410 via cloud communication, the angle adjustment 512 and status determination 153 are checked again to correctly correct whether the returned correction angle is misaligned. When all the data accumulated during the off-center position is processed to the latest data, the installation status (current status) can be updated by the final result.

[0084] like Figure 11 As shown, condition check 511 can use yaw rate, acceleration, and velocity to set valid data flags, and as... Figure 12 As shown, angle adjustment 512 can set the correct angle flag by determining whether the angle offset = original angle offset + correction angle is within the offset limit. For example... Figure 13As shown, considering that radar data collected in a real-world environment may contain false positives, if a specified number of consecutive occurrences occur, status determination 513 can determine whether misalignment exists. Furthermore, the temporary current state (temporary installation state) and the current state (installation state) can be distinguished by comparing the unique ID of the data used in angle adjustment 512 + status determination 513 with the most recent unique ID. Performing the unique ID comparison verifies that all data stored in the cloud when the equipment is in an off-center position has been reflected in the latest data. When the installation state is in a positive position, the unique ID of the data used in angle adjustment + status determination becomes the most recent unique ID, thus the current state can also be updated immediately. Figure 14 As shown, in cloud communication 520, when the installation state is in an off-center position, the received data includes data that has passed condition check 511. When the first data is received, if the start timestamp is not stored, the timestamp of the incoming data can be stored as the start timestamp in storage 522. Here, the start timestamp refers to the time (timestamp) of collecting the first data received when the installation state changes from the upright position to the off-center position. When the equipment state changes from the off-center position to the upright position in state determination 513, the start timestamp can be initialized to a null value.

[0085] Data received via cloud communication 520 is stored in data queue 521. Due to the limited memory within the vehicle, data cannot accumulate indefinitely; therefore, only the latest N pre-designed data points can be accumulated. When connected to cloud 410, the data that has been in data queue 521 for the longest time can be sent to cloud 410.

[0086] The data sent to and received from the cloud 410 can be as follows: Unique identification information (unique ID) is required for data identification and needs to be verified in status determination 513 to ensure the data is up-to-date when data is returned later. Sensor data includes the data required for calculating the correction angle in the cloud 410 and can include the original angle offset if angle adjustment is needed. Other data, such as vehicle information, radar information and additional LiDAR information, and camera device information, can be modified based on the data required by the automatic alignment (angle correction) algorithm. A timestamp is the timestamp at which the current data was collected; when data is returned later, only data after the start timestamp needs to be filtered. Timestamps can be added to prevent the data order from shifting or changing due to communication errors or errors on the cloud side 410. The correction angle is the correction angle value calculated and returned by the cloud 410 and can be included only in the returned information. The correction angle calculated and received by the cloud 410 is used to check the installation status via angle adjustment 512 and status determination 513, and for this purpose, a unique ID and original angle offset may be required.

[0087] As mentioned above, by calculating the sensor correction angle in a cloud environment rather than in the vehicle, the misalignment angle of the sensor can be corrected without using the vehicle's resources. Furthermore, by utilizing a large amount of data from the cloud server, an accurate correction angle can be calculated.

[0088] Figure 15 This is a block diagram illustrating a vehicle according to an embodiment of the present disclosure. Figure 15 The detailed description of each component in the document corresponds to Figures 1 to 8 Each component or Figures 9 to 14 A detailed description of each component is required; therefore, redundant descriptions will be omitted below.

[0089] The vehicle 600 according to an embodiment of the present disclosure includes a sensing unit 200, a storage unit 300, and a processing module 100, and the processing module 100 may include a processing unit 110 and a communication unit 120.

[0090] The sensing unit 200 includes a radar 210, the storage unit 300 stores data from the sensing unit 200, and the processing module 100 corrects the data from the sensing unit 200.

[0091] The processing module 100 receives radar data sensed by the radar 210 and includes a processing unit 110 that uses the radar data to set a correction angle for the radar data, and a communication unit 120 that communicates with the cloud server 400. When the processing unit 110 determines that the correction angle for the radar data needs to be adjusted, the processing unit adjusts the correction angle through the cloud server 400.

[0092] The processing unit 110 determines whether the radar data meets the correction angle adjustment conditions. If the correction angle adjustment conditions are met, it calculates the first deformation angle of the radar based on the radar data, determines whether the first correction reflection angle that reflects the currently set correction angle in the first deformation angle is within the first threshold angle, and determines whether to adjust the correction angle based on the result.

[0093] If the first correction response angle deviates from the first threshold angle, the processing unit 110 sends the radar data to the cloud server 400 and receives the correction angle to be changed from the cloud server 400.

[0094] The radar data is based on the radar coordinate system. When the first correction response angle is within the threshold angle, the processing unit 110 converts the radar data into second data based on the vehicle coordinate system, calculates the second deformation angle based on the second data, determines whether the second correction response angle that reflects the currently set correction angle in the second deformation angle is within the second threshold angle, and determines whether to adjust the correction angle based on whether the result is the same as the result of determining whether the first correction response angle is within the first threshold angle.

[0095] When the second result of determining whether the second correction response angle is within the second threshold angle is different from the first result of determining whether the first correction response angle is within the first threshold angle, the processing unit 110 may change the result of determining whether to adjust the correction angle using the first result if the result is repeated a preset number of times or more.

[0096] If the first correction response angle is within the first threshold angle and the first result is different from the second result, the above-mentioned preset number of times or more are repeated, then the processing unit 110 can adjust the correction angle through the cloud server 400. If the first correction response angle deviates from the first threshold angle and the first result is different from the second result, the above-mentioned preset number of times or more are repeated, then the processing unit 110 can maintain the current correction angle.

[0097] The processing unit 110 can receive vehicle information and use the vehicle information to determine whether the radar data meets the correction angle adjustment conditions, and the vehicle information may include at least one of yaw data, acceleration data and speed data.

[0098] The communication unit 120 sends radar data, unique identification information of radar data and timestamp to the cloud server 400, receives data, unique identification information, timestamp and correction angle from the cloud server 400, and can change the correction angle to a new correction angle based on the radar data sent to the cloud server that has a timestamp later than the timestamp corresponding to the earliest radar data.

[0099] Furthermore, embodiments of this disclosure can be implemented as computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system.

[0100] Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage devices, etc. Furthermore, computer-readable recording media can be distributed across networked computer systems, thereby allowing for the distributed storage and execution of computer-readable code. Additionally, the functional programs, code, and code segments used to implement this disclosure can be readily deduced by programmers skilled in the art to which this disclosure pertains.

[0101] As described above, this disclosure has been illustrated with specific details such as particular components, limited embodiments, and drawings; however, this is provided merely to aid in a more complete understanding of the disclosure, and the disclosure is not limited to the embodiments described above. Various modifications and variations can be made by those skilled in the art based on this description.

[0102] Therefore, the scope of this disclosure is not limited to the described embodiments, and all things that are equivalent to or have equivalent variations of the appended claims, as well as the appended claims themselves, should be considered to fall within the scope of the concept of this disclosure.

Claims

1. A sensor alignment module, comprising: A processing unit configured to receive radar data sensed by the radar and use the radar data to set a correction angle for the radar data; as well as A communication unit configured to communicate with a cloud server. When it is determined that the correction angle for the radar data needs to be adjusted, the processing unit adjusts the correction angle through the cloud server.

2. The sensor alignment module according to claim 1, in, The processing unit determines whether the radar data meets the correction angle adjustment conditions, and when the correction angle adjustment conditions are met, it calculates the first deformation angle of the radar based on the radar data, determines whether the first correction reflection angle that reflects the currently set correction angle to the first deformation angle is within the first threshold angle, and determines whether to adjust the correction angle based on the result.

3. The sensor alignment module according to claim 2, in, When the first correction response angle deviates from the first threshold angle, the processing unit sends the radar data to the cloud server and receives the correction angle to be changed from the cloud server.

4. The sensor alignment module according to claim 2, in, The radar data is based on the radar's coordinate system, and Specifically, when the first correction response angle is within the first threshold angle, the processing unit converts the radar data into second data according to the vehicle's coordinate system, calculates the second deformation angle based on the second data, determines whether the second correction response angle that reflects the currently set correction angle to the second deformation angle is within the second threshold angle, and determines whether to adjust the correction angle based on whether the result is the same as the result of determining whether the first correction response angle is within the first threshold angle.

5. The sensor alignment module according to claim 4, in, When the second result determining whether the second correction response angle is within the second threshold angle is different from the first result determining whether the first correction response angle is within the first threshold angle, the processing unit changes the result of using the first result to determine whether to adjust the correction angle.

6. The sensor alignment module according to claim 5, in, When the first correction response angle is within the first threshold angle and the first result is different from the second result, the processing unit adjusts the correction angle through the cloud server. When the first correction response angle deviates from the first threshold angle and the first result is different from the second result, the processing unit maintains the current correction angle.

7. The sensor alignment module according to claim 2, in, The processing unit receives vehicle information from the vehicle and uses the vehicle information to determine whether the radar data meets the correction angle adjustment conditions.

8. The sensor alignment module according to claim 7, in, The vehicle information includes at least one of yaw data, acceleration data, and speed data.

9. The sensor alignment module according to claim 1, in, The communication unit sends the radar data, the unique identifier information of the radar data, and the timestamp to the cloud server, receives the radar data, the unique identifier information, the timestamp, and the correction angle from the cloud server, and changes the correction angle to a new correction angle based on the radar data sent to the cloud server that has a timestamp later than the timestamp corresponding to the earliest time point.

10. The sensor alignment module according to claim 1, comprising: A storage unit configured to store the radar data and the radar's initial sensor position information. The processing unit uses the radar data stored in the storage unit to adjust the correction angle of the radar data.

Images