Method, device and equipment for determining vehicle state of autonomous vehicle, and computer program product

Abstract

The invention discloses a vehicle state determination method, device and equipment for an automatic driving vehicle and a computer program product. The method comprises the steps that the chassis speed and multi-source positioning data of the automatic driving vehicle are acquired; determining a first state identifier of the autonomous vehicle according to the chassis speed; determining a second state identifier of the autonomous vehicle according to the multi-source positioning data; and determining the current driving state of the autonomous vehicle according to the first state identifier of the autonomous vehicle and the second state identifier of the autonomous vehicle, wherein the current driving state is a static state or a moving state. The driving state of the vehicle is determined by combining the chassis speed and the multi-source positioning data, the advantages of different data sources are fully utilized, and errors and uncertainty possibly existing in a single data source are effectively reduced, so that the accuracy of judgment of the driving state of the vehicle is improved, a reliable basis is provided for decision and control of an automatic driving system, and the driving safety of the vehicle is improved. And the positioning robustness and safety of the automatic driving vehicle are improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device and equipment for determining the vehicle state of an autonomous driving vehicle, and a computer program product. Background Art

[0002] With the rapid development of intelligent transportation and autonomous driving technologies, high-precision positioning technology is crucial for ensuring safe and efficient vehicle operation. Fusion positioning, a technology that integrates information from multiple sensors (such as the Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU), wheel speedometers, LiDAR, and cameras) to improve positioning accuracy and reliability, has gained widespread application.

[0003] Accurately determining the vehicle's state is crucial during fusion positioning, particularly determining whether the vehicle is at zero speed (idling). This accurate determination of the vehicle's zero speed is crucial for initializing the fusion positioning algorithm, assigning data fusion weights, and correcting errors. For example, during the initialization phase, accurate zero speed determination helps the positioning system quickly and stably establish the initial coordinate system and attitude information. During data fusion, dynamically adjusting the fusion weights of each sensor data based on the vehicle's varying states improves the accuracy and stability of positioning results.

[0004] However, in some scenarios, the existing vehicle speed judgment methods have the problem of insufficient accuracy, which in turn affects the accuracy and robustness of fusion positioning. Summary of the Invention

[0005] The embodiments of the present application provide a method, apparatus, and device for determining the vehicle state of an autonomous vehicle, as well as a computer program product, to improve the accuracy of judging the driving state of the autonomous vehicle, thereby improving the positioning robustness and safety of the autonomous vehicle.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for determining a vehicle state of an autonomous vehicle, wherein the method for determining a vehicle state of an autonomous vehicle includes:

[0008] Obtain chassis speed and multi-source positioning data of autonomous vehicles;

[0009] determining a first state indicator of the autonomous driving vehicle based on the chassis speed;

[0010] determining a second state identifier of the autonomous driving vehicle based on the multi-source positioning data;

[0011] The current driving state of the autonomous driving vehicle is determined based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle, and the current driving state is a stationary state or a moving state.

[0012] Optionally, determining the first state identifier of the automatic driving vehicle according to the chassis speed includes:

[0013] Determining whether the chassis speed is 0;

[0014] If so, determining that the first state identifier of the autonomous driving vehicle is a stationary state identifier;

[0015] Otherwise, it is determined that the first state identifier of the automatic driving vehicle is a motion state identifier.

[0016] Optionally, the multi-source positioning data includes IMU data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes:

[0017] Calculate the variance and mean of the IMU data based on the IMU data within the preset time period;

[0018] If the variance and the mean of the IMU data are respectively less than the first threshold and the second threshold, determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier;

[0019] Otherwise, it is determined that the second state identifier of the automatic driving vehicle is a motion state identifier.

[0020] Optionally, the multi-source positioning data includes laser SLAM positioning data and visual SLAM positioning data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes:

[0021] Calculate the deviation between each two adjacent frames of laser SLAM positioning data based on the laser SLAM positioning data within a preset time period, and calculate the deviation between each two adjacent frames of visual SLAM positioning data based on the visual SLAM positioning data within a preset time period;

[0022] If the deviation between each two adjacent frames of laser SLAM positioning data and / or the deviation between each two adjacent frames of visual SLAM positioning data is less than a third threshold, determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier;

[0023] Otherwise, it is determined that the second state identifier of the automatic driving vehicle is a motion state identifier.

[0024] Optionally, the multi-source positioning data includes RTK positioning data and GNSS raw positioning data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes:

[0025] Calculate the deviation between each two adjacent frames of RTK positioning data based on the RTK positioning data within a preset time period, and calculate the deviation between each two adjacent frames of GNSS raw positioning data based on the GNSS raw positioning data within a preset time period;

[0026] If the deviation between each two adjacent frames of RTK positioning data and / or the deviation between each two adjacent frames of GNSS raw positioning data is less than a fourth threshold, determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier;

[0027] Otherwise, it is determined that the second state identifier of the automatic driving vehicle is a motion state identifier.

[0028] Optionally, the second state identifier of the autonomous driving vehicle includes a plurality of identifiers, and determining the current driving state of the autonomous driving vehicle according to the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle includes:

[0029] If the first state identifier of the autonomous driving vehicle is a stationary state identifier, and at least a preset number of second state identifiers among the plurality of second state identifiers are stationary state identifiers, determining that the current driving state of the autonomous driving vehicle is a stationary state;

[0030] Otherwise, it is determined that the current driving state of the automatic driving vehicle is a moving state.

[0031] Optionally, the method for determining the vehicle state of the autonomous driving vehicle further includes:

[0032] When the current driving state of the autonomous driving vehicle is a stationary state, setting the speed observation information of the autonomous driving vehicle to 0;

[0033] Update the estimated value of the IMU zero bias based on the speed observation information of the autonomous driving vehicle.

[0034] In a second aspect, an embodiment of the present application further provides a vehicle state determination device for an autonomous vehicle, wherein the vehicle state determination device for an autonomous vehicle includes:

[0035] an acquisition unit, configured to acquire chassis speed and multi-source positioning data of the autonomous driving vehicle;

[0036] a first determining unit, configured to determine a first state identifier of the automatic driving vehicle according to the chassis speed;

[0037] a second determining unit, configured to determine a second state identifier of the autonomous driving vehicle based on the multi-source positioning data;

[0038] The third determination unit is used to determine the current driving state of the autonomous driving vehicle based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle, where the current driving state is a stationary state or a moving state.

[0039] In a third aspect, an embodiment of the present application further provides a device, including:

[0040] A processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform any of the aforementioned methods for determining the vehicle state of an autonomous vehicle.

[0041] In a fourth aspect, an embodiment of the present application further provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements any of the aforementioned methods for determining the vehicle state of an autonomous driving vehicle.

[0042] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the vehicle state determination method of the autonomous driving vehicle in the embodiments of the present application first obtains the chassis speed and multi-source positioning data of the autonomous driving vehicle; then determines the first state identifier of the autonomous driving vehicle based on the chassis speed; then determines the second state identifier of the autonomous driving vehicle based on the multi-source positioning data; finally, determines the current driving state of the autonomous driving vehicle based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle, and the current driving state is a stationary state or a moving state. The vehicle state determination method of the autonomous driving vehicle in the embodiments of the present application determines the driving state of the vehicle by combining the chassis speed and multi-source positioning data, making full use of the advantages of different data sources, effectively reducing the errors and uncertainties that may exist in a single data source, thereby improving the accuracy of the vehicle driving state judgment, providing a reliable basis for the decision-making and control of the autonomous driving system, and improving the positioning robustness and safety of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 A schematic flow chart of a method for determining a vehicle state of an autonomous vehicle according to an embodiment of the present application;

[0045] Figure 2This is a schematic structural diagram of a vehicle state determination device for an autonomous driving vehicle in an embodiment of the present application;

[0046] Figure 3 This is a structural diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0047] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0049] The embodiment of the present application provides a method for determining the vehicle state of an autonomous vehicle, such as Figure 1 As shown, a flow chart of a method for determining the vehicle state of an autonomous vehicle in an embodiment of the present application is provided. The method for determining the vehicle state of an autonomous vehicle includes the following steps S110 to S140:

[0050] Step S110: Acquire chassis speed and multi-source positioning data of the autonomous driving vehicle.

[0051] The chassis of autonomous vehicles is typically equipped with devices such as wheel speed sensors, which measure wheel rotational speed in real time. By calculating the measured wheel speed (taking into account factors such as wheel radius), the vehicle's chassis speed can be calculated. Chassis speed reflects the actual movement of the vehicle's wheels during driving and is an important indicator of the vehicle's motion state.

[0052] Multi-source positioning data is primarily acquired based on various positioning technologies implemented in autonomous vehicles, such as GNSS (Global Navigation Satellite System) positioning, IMU (Inertial Measurement Unit), laser SLAM positioning, and visual SLAM positioning. GNSS provides the vehicle's position in a global coordinate system, while the IMU measures acceleration and angular velocity to infer the vehicle's position and attitude. Laser SLAM and visual SLAM positioning utilize environmental features for high-precision positioning. By combining data from these various positioning sources, more comprehensive and accurate vehicle position and attitude information can be obtained.

[0053] Step S120: Determine a first state identifier of the automatic driving vehicle based on the chassis speed.

[0054] A speed threshold is set in advance, which can be used to determine whether the vehicle is in motion. For example, the speed threshold can be set to 0.1m / s (the specific value can be adjusted according to actual needs and vehicle characteristics). The obtained chassis speed is compared with the set speed threshold. If the chassis speed is greater than the speed threshold, the vehicle is considered to be in motion, and the first state flag is set to the flag indicating the motion state (such as flag = 1); if the chassis speed is less than or equal to the speed threshold, the vehicle is considered to be stationary, and the first state flag is set to the flag indicating the stationary state (such as flag = 0).

[0055] Step S130: Determine a second state identifier of the autonomous driving vehicle based on the multi-source positioning data.

[0056] The multi-source positioning data is processed to analyze changes in the vehicle's position and attitude over a period of time. For example, the magnitude of the position change can be measured by calculating the distance difference between the vehicle's positions at adjacent moments. The second state flag of the autonomous vehicle is then determined based on the position and attitude changes. If the multi-source positioning data determines that the vehicle is in motion, the second state flag is set to indicate motion (e.g., flag1 = 1). If the multi-source positioning data determines that the vehicle is stationary, the second state flag is set to indicate stationary (e.g., flag1 = 0).

[0057] Step S140: Determine the current driving state of the autonomous driving vehicle based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle, where the current driving state is a stationary state or a moving state.

[0058] The current driving state of the vehicle is finally determined by combining the above-mentioned first state identifier and second state identifier. The specific comprehensive judgment rules can be flexibly set according to actual needs, and the embodiment of the present application does not make specific limitations on this.

[0059] The vehicle state determination method of the autonomous driving vehicle in the embodiment of the present application determines the driving state of the vehicle by combining chassis speed and multi-source positioning data, fully utilizing the advantages of different data sources and effectively reducing the errors and uncertainties that may exist in a single data source, thereby improving the accuracy of the vehicle driving state judgment, providing a reliable basis for the decision-making and control of the autonomous driving system, and improving the positioning robustness and safety of the autonomous driving vehicle.

[0060] In some embodiments of the present application, determining the first state identifier of the autonomous driving vehicle based on the chassis speed includes: determining whether the chassis speed is 0; if so, determining that the first state identifier of the autonomous driving vehicle is a stationary state identifier; otherwise, determining that the first state identifier of the autonomous driving vehicle is a moving state identifier.

[0061] Chassis speed data is obtained from the autonomous vehicle's chassis sensor system. Chassis sensors typically include wheel speed sensors, which monitor wheel rotation in real time and convert this information into speed data. The acquired chassis speed data is preprocessed to eliminate potential noise and interference. For example, filtering algorithms (such as low-pass filtering) can be used to smooth the speed data and remove high-frequency noise, making the speed data more stable and reliable.

[0062] A determination is made as to whether the pre-processed chassis speed data is 0 or a value close to 0 (e.g., less than a certain speed threshold), and a first state flag is set based on the determination result. If the chassis speed is equal to or close to 0, the first state flag is set to indicate a stationary state, such as setting flag1 = 1 to indicate a stationary state. If the chassis speed is not equal to or close to 0, the first state flag is set to indicate a moving state, such as setting flag1 = 0 to indicate a moving state.

[0063] The vehicle chassis speed is the basic data for judging the vehicle's motion state. Further combining it with other multi-source positioning data to comprehensively judge the vehicle's motion state can improve the accuracy of the vehicle's driving state judgment.

[0064] In some embodiments of the present application, the multi-source positioning data includes IMU data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes: calculating the variance and mean of the IMU data based on the IMU data within the preset time period; if the variance and mean of the IMU data are respectively less than a first threshold and a second threshold, determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier; otherwise, determining that the second state identifier of the autonomous driving vehicle is a moving state identifier.

[0065] Multi-source positioning data includes IMU data within a preset time period. The IMU sensor in an autonomous vehicle outputs IMU data at a certain frequency. An IMU typically includes an accelerometer and gyroscope, which measure acceleration and angular velocity along the vehicle's three axes. The preset time period can be set to meet specific needs, such as 1 second or 2 seconds, to capture a continuous stream of IMU data within that time period.

[0066] The acquired IMU data is preprocessed to remove noise and outliers. For example, filtering algorithms such as Kalman filtering can be used to smooth the acceleration and angular velocity data to improve data quality and reliability.

[0067] Calculate the variance and mean of the IMU's acceleration data along each of the three axes (e.g., X, Y, and Z) over a preset time period. The variance reflects the degree of dispersion in the acceleration data, while the mean reflects the average level of the acceleration data. Similarly, calculate the variance and mean of the angular velocity data along each of the three axes.

[0068] The calculated variance and mean of the acceleration and angular velocity data are compared with a preset first and second thresholds, respectively. The first threshold is used to determine whether the data dispersion is sufficiently small, while the second threshold is used to determine whether the average level of the data is close to the value at rest. For example, a comprehensive judgment condition can be set: when the variance of the three axial acceleration data is less than the first threshold T1 and the mean is less than the second threshold T2, and the variance of the three axial angular velocity data is also less than the first threshold T1 and the mean is less than the second threshold T2, the vehicle is considered to be at rest.

[0069] If the above judgment conditions are met, the second state flag of the autonomous driving vehicle is set to the stationary state flag, such as setting flag2=1 to indicate the stationary state; otherwise, it is set to the moving state flag, such as setting flag2=0.

[0070] By calculating the variance and mean of IMU data and setting appropriate thresholds for judgment, the vehicle's motion state can be accurately reflected from two dimensions: the degree of data dispersion and the average level. When the vehicle is stationary, the acceleration and angular velocity data measured by the IMU should be relatively stable, with a small variance and a mean close to the theoretical value at rest. However, when the vehicle is in motion, the data will show greater fluctuations, with an increased variance and a mean that deviates from the stationary value. Therefore, IMU data can further assist in determining whether the vehicle is stationary, improving the accuracy of vehicle driving status judgment.

[0071] In some embodiments of the present application, the multi-source positioning data includes laser SLAM positioning data and visual SLAM positioning data within a preset time period, and determining the second state identification of the autonomous driving vehicle based on the multi-source positioning data includes: calculating the deviation between each two adjacent frames of laser SLAM positioning data based on the laser SLAM positioning data within the preset time period, and calculating the deviation between each two adjacent frames of visual SLAM positioning data based on the visual SLAM positioning data within the preset time period; if the deviation between each two adjacent frames of laser SLAM positioning data and / or the deviation between each two adjacent frames of visual SLAM positioning data is less than a third threshold, then determining that the second state identification of the autonomous driving vehicle is a stationary state identification; otherwise, then determining that the second state identification of the autonomous driving vehicle is a moving state identification.

[0072] The autonomous vehicle's laser SLAM positioning module and visual SLAM positioning module, respectively, can acquire laser SLAM positioning data and visual SLAM positioning data within a preset time period. The laser SLAM positioning module uses a lidar to scan the surrounding environment and calculate the vehicle's position and posture through algorithms such as point cloud matching. The visual SLAM positioning module captures images through a camera and determines the vehicle's position and posture using methods such as image feature matching. The preset time period can also be set according to actual needs, such as 1 second or 2 seconds, to acquire continuous laser SLAM positioning data frames and visual SLAM positioning data frames within this time period.

[0073] For the laser SLAM positioning data within a preset time period, the deviation between each two adjacent frames of data is calculated in sequence. The deviation can be calculated in a variety of ways, such as calculating the Euclidean distance between the vehicle positions represented by two adjacent frames of positioning data, or calculating the difference between attitudes (such as rotation angles). Similarly, for visual SLAM positioning data, the deviation between each two adjacent frames of data is also calculated in sequence. The calculation method is similar to that of laser SLAM. The position deviation and attitude deviation between two adjacent frames can be calculated based on the position and attitude information represented by the visual SLAM positioning data.

[0074] The calculated deviation between each two adjacent frames of laser SLAM positioning data and the deviation between each two adjacent frames of visual SLAM positioning data are compared with a preset third threshold. The third threshold is a value set based on the actual application scenario and system accuracy requirements, and is used to determine whether the vehicle is stationary. For example, when the deviation is less than the third threshold, it is considered that the change between the two adjacent frames of positioning data is small, and the vehicle may be stationary; when the deviation is greater than or equal to the third threshold, it is considered that the change between the two adjacent frames of positioning data is large, and the vehicle may be in motion.

[0075] If the deviation between each two adjacent frames of laser SLAM positioning data and / or the deviation between each two adjacent frames of visual SLAM positioning data is less than a third threshold, the second state identifier of the autonomous driving vehicle is set to a stationary state identifier, such as setting flag3 = 1 to indicate a stationary state; otherwise, it is set to a moving state identifier, such as setting flag3 = 0. The "and / or" here means that as long as the deviation of all adjacent frames of at least one positioning data among the laser SLAM positioning data and the visual SLAM positioning data is less than the third threshold, the second state identifier of the autonomous driving vehicle can be set to a stationary state identifier. Of course, more stringent conditions can also be set according to actual needs, such as the second state identifier of the autonomous driving vehicle is set to a stationary state identifier only when the deviation of adjacent frames of both positioning data is less than the third threshold.

[0076] In practical applications, autonomous vehicles face a variety of complex environmental conditions, such as urban roads, tunnels, and parking lots. Different environments affect laser SLAM and visual SLAM differently, but by combining the two positioning data, they can effectively assist in determining the vehicle's status in various environments. Furthermore, if either laser SLAM or visual SLAM fails or experiences data anomalies, the other positioning data can still be used to assist in determining the vehicle's driving status, thereby improving the accuracy and robustness of vehicle driving status judgment.

[0077] In some embodiments of the present application, the multi-source positioning data includes RTK positioning data and GNSS raw positioning data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes: calculating the deviation between each two adjacent frames of RTK positioning data based on the RTK positioning data within the preset time period, and calculating the deviation between each two adjacent frames of GNSS raw positioning data based on the GNSS raw positioning data within the preset time period; if the deviation between each two adjacent frames of RTK positioning data and / or the deviation between each two adjacent frames of GNSS raw positioning data is less than a fourth threshold, then determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier; otherwise, determining that the second state identifier of the autonomous driving vehicle is a moving state identifier.

[0078] Receives RTK (Real-Time Kinematic) positioning data and GNSS (Global Navigation Satellite System) raw positioning data from the autonomous vehicle's RTK and GNSS positioning modules, respectively, within a preset time period. RTK positioning data refers to high-precision positioning information obtained through RTK real-time dynamic differential technology and third-party integrated navigation algorithms, while raw GNSS positioning data refers to the original RTK positioning data that has not been processed by third-party integrated navigation algorithms.

[0079] For RTK positioning data within a preset time period, the deviation between each two adjacent frames of data is calculated sequentially. As in the previous embodiment, the deviation can also be calculated in various ways, such as calculating the Euclidean distance between the vehicle positions represented by two adjacent frames of positioning data, or calculating the difference between the attitudes (such as heading angles). Similarly, for GNSS raw positioning data, the deviation between each two adjacent frames of data is also calculated sequentially.

[0080] The calculated deviation between each two adjacent frames of RTK positioning data and the deviation between each two adjacent frames of GNSS raw positioning data are compared with a preset fourth threshold. The fourth threshold is also set based on the actual application scenario and system accuracy requirements, and is used to determine whether the vehicle is stationary. For example, when the deviation is less than the fourth threshold, it is considered that the change between the two adjacent frames of positioning data is small, and the vehicle may be stationary. When the deviation is greater than or equal to the fourth threshold, it is considered that the change between the two adjacent frames of positioning data is large, and the vehicle may be in motion.

[0081] If the deviation between two adjacent frames of RTK positioning data and / or the deviation between two adjacent frames of GNSS raw positioning data is less than a fourth threshold, the second state flag of the autonomous driving vehicle is set to a stationary state flag, such as flag4 = 1, to indicate a stationary state; otherwise, the second state flag is set to a moving state flag, such as flag4 = 0. The "and / or" here means that as long as the adjacent frame deviation of at least one of the RTK positioning data and the GNSS raw positioning data is less than the fourth threshold, the vehicle can be determined to be stationary.

[0082] Both RTK positioning data and GNSS raw positioning data are derived from RTK real-time dynamic differential (DDT) technology. The primary difference lies in the fact that RTK positioning data is further processed by a third-party integrated navigation system, while GNSS raw positioning data is the direct output of the RTK real-time differential algorithm. The two types of positioning data may exhibit varying accuracy in different scenarios. Therefore, combining these two types of positioning data to determine vehicle status leverages their complementary nature, reducing potential errors from a single data source and improving the accuracy and reliability of status assessment.

[0083] In some embodiments of the present application, the second state identifier of the autonomous driving vehicle includes multiple ones, and determining the current driving state of the autonomous driving vehicle based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle includes: if the first state identifier of the autonomous driving vehicle is a stationary state identifier, and at least a preset number of second state identifiers among the multiple second state identifiers are stationary state identifiers, then determining that the current driving state of the autonomous driving vehicle is a stationary state; otherwise, determining that the current driving state of the autonomous driving vehicle is a moving state.

[0084] The first state identifier is a preliminary state judgment of the autonomous vehicle, which is mainly derived from the judgment result of the vehicle chassis speed information. The second state identifier is a plurality of auxiliary state judgment results calculated based on multi-source positioning data using different methods or algorithms. For example, in the previous embodiment, the second state identifier can be a state identifier calculated based on multiple data sources such as IMU data, laser SLAM positioning data and visual SLAM positioning data, RTK and GNSS raw positioning data.

[0085] The preset number is a key parameter used to determine how many of the multiple second-state indicators must be stationary for the vehicle to be considered stationary. The preset number can be adjusted based on system reliability and safety requirements. For example, if there are three second-state indicators, the preset number can be set to two or three.

[0086] If the first state identifier of the autonomous vehicle is a stationary state identifier, and at least a preset number of the multiple second state identifiers are stationary state identifiers, the current driving state of the autonomous vehicle is determined to be a stationary state. Otherwise, it is determined to be a moving state. For example, assuming the preset number is two, if the first state identifier is stationary and two or three of the three second state identifiers are stationary, the final state is stationary; otherwise, it is moving.

[0087] By combining the results of the first state identification and multiple second state identifications, this solution fully utilizes the advantages of multi-source data and avoids the errors and uncertainties that may be caused by a single data source or a single judgment method. The fusion of multi-source data can improve the accuracy and reliability of state judgment.

[0088] By setting a preset number of constraints, the system will only be judged as stationary if at least a preset number of the multiple second-state identifiers support the stationary state. This mechanism effectively reduces misjudgments caused by noise or errors in individual data sources. If a sensor or algorithm fails, resulting in an inaccurate second-state identifier, the state identifiers of other functioning sensors or algorithms can still be used. By using these constraints, the system can tolerate individual sensor failures to a certain extent, maintaining robust state judgment.

[0089] In some embodiments of the present application, the vehicle state determination method of the autonomous driving vehicle also includes: when the current driving state of the autonomous driving vehicle is a stationary state, setting the speed observation information of the autonomous driving vehicle to 0; and updating the estimated value of the IMU zero bias based on the speed observation information of the autonomous driving vehicle.

[0090] Based on the aforementioned embodiment, the current driving state of the autonomous vehicle is determined by combining the first state identifier and multiple second state identifiers of the autonomous vehicle. When the comprehensive determination indicates that the current driving state is stationary, the subsequent operations of setting the velocity observation information to zero and updating the IMU zero bias estimate are triggered.

[0091] Autonomous vehicles are typically equipped with a variety of sensors to obtain speed information, such as wheel speed sensors and IMUs (inertial measurement units). Once the vehicle is determined to be stationary, the speed observations from these sensors are uniformly processed. Regardless of the actual speed value measured by the sensor (which may be inaccurate due to noise, errors, and other factors), the speed observations are uniformly set to 0.

[0092] An IMU is a sensor used to measure a vehicle's acceleration and angular velocity. However, in practice, IMUs exhibit bias errors. This means that even without acceleration or angular velocity input, the IMU still outputs a non-zero value. This bias error varies over time and with environmental factors, necessitating real-time estimation and compensation.

[0093] When the vehicle is stationary, the acceleration and angular velocity measured by the IMU should theoretically be zero (ignoring noise). In this case, the acceleration and angular velocity values ​​actually measured by the IMU can be used to estimate the bias error by using the velocity observation information after it is reset to zero. Specifically, the acceleration and angular velocity values ​​output by the IMU can be used as estimates of the acceleration bias and angular velocity bias, respectively.

[0094] To improve the accuracy and stability of bias estimation, a filtering algorithm can be used to estimate the IMU bias. For example, a Kalman filter algorithm can be used to set the velocity observation information to zero as the system's observation information. Combined with the IMU's measurement model and state equation, the IMU's bias state can be estimated and updated in real time. After each velocity observation is set to zero, the new observation information is input into the filtering algorithm, updating the filter state to obtain a more accurate IMU bias estimate.

[0095] When the vehicle is stationary, the IMU's measurements should theoretically reflect its bias error. By setting the velocity observations to zero and using this state information to update the IMU bias estimate, the IMU's bias characteristics can be captured more accurately. Compared to bias estimation while the vehicle is in motion, estimating the bias while stationary eliminates interference from the vehicle's acceleration and angular velocity, thereby improving estimation accuracy.

[0096] As a vehicle's operating time increases and environmental factors change, the IMU's zero bias will change. By updating the IMU's zero bias estimate in real time when the vehicle is stationary and compensating the IMU's measurement data promptly, we can ensure that the IMU provides accurate acceleration and angular velocity information throughout the entire operation process, improving the positioning and navigation accuracy of the autonomous driving system.

[0097] The embodiment of the present application also provides a vehicle state determination device 200 for an autonomous driving vehicle, such as Figure 2 As shown, a schematic diagram of the structure of a vehicle state determination device for an autonomous vehicle in an embodiment of the present application is provided. The vehicle state determination device 200 for an autonomous vehicle includes: an acquisition unit 210, a first determination unit 220, a second determination unit 230, and a third determination unit 240, wherein:

[0098] an acquisition unit 210 for acquiring chassis speed and multi-source positioning data of the autonomous driving vehicle;

[0099] A first determining unit 220 is configured to determine a first state identifier of the autonomous driving vehicle according to the chassis speed;

[0100] A second determining unit 230 is configured to determine a second state identifier of the autonomous driving vehicle based on the multi-source positioning data;

[0101] The third determination unit 240 is used to determine the current driving state of the autonomous driving vehicle based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle, where the current driving state is a stationary state or a moving state.

[0102] In some embodiments of the present application, the first determination unit 220 is specifically used to: determine whether the chassis speed is 0; if so, determine that the first state identifier of the autonomous driving vehicle is a stationary state identifier; otherwise, determine that the first state identifier of the autonomous driving vehicle is a moving state identifier.

[0103] In some embodiments of the present application, the multi-source positioning data includes IMU data within a preset time period, and the second determination unit 230 is specifically used to: calculate the variance and mean of the IMU data based on the IMU data within the preset time period; if the variance and mean of the IMU data are respectively less than the first threshold and the second threshold, then determine that the second state identifier of the autonomous driving vehicle is a stationary state identifier; otherwise, determine that the second state identifier of the autonomous driving vehicle is a moving state identifier.

[0104] In some embodiments of the present application, the multi-source positioning data includes laser SLAM positioning data and visual SLAM positioning data within a preset time period, and the second determination unit 230 is specifically used to: calculate the deviation between each two adjacent frames of laser SLAM positioning data based on the laser SLAM positioning data within the preset time period, and calculate the deviation between each two adjacent frames of visual SLAM positioning data based on the visual SLAM positioning data within the preset time period; if the deviation between each two adjacent frames of laser SLAM positioning data and / or the deviation between each two adjacent frames of visual SLAM positioning data is less than a third threshold, then determine that the second state identifier of the autonomous driving vehicle is a stationary state identifier; otherwise, determine that the second state identifier of the autonomous driving vehicle is a moving state identifier.

[0105] In some embodiments of the present application, the multi-source positioning data includes RTK positioning data and GNSS original positioning data within a preset time period, and the second determination unit 230 is specifically used to: calculate the deviation between each two adjacent frames of RTK positioning data based on the RTK positioning data within the preset time period, and calculate the deviation between each two adjacent frames of GNSS original positioning data based on the GNSS original positioning data within the preset time period; if the deviation between each two adjacent frames of RTK positioning data and / or the deviation between each two adjacent frames of GNSS original positioning data is less than a fourth threshold, then determine that the second state identifier of the autonomous driving vehicle is a stationary state identifier; otherwise, determine that the second state identifier of the autonomous driving vehicle is a moving state identifier.

[0106] In some embodiments of the present application, the second state identifier of the autonomous driving vehicle includes multiple ones, and the third determination unit 240 is specifically used to: if the first state identifier of the autonomous driving vehicle is a stationary state identifier, and at least a preset number of second state identifiers among the multiple second state identifiers are stationary state identifiers, then determine that the current driving state of the autonomous driving vehicle is a stationary state; otherwise, determine that the current driving state of the autonomous driving vehicle is a moving state.

[0107] In some embodiments of the present application, the vehicle state determination device 200 of the autonomous driving vehicle also includes: a setting unit, used to set the speed observation information of the autonomous driving vehicle to 0 when the current driving state of the autonomous driving vehicle is a stationary state; and an updating unit, used to update the estimated value of the IMU zero bias according to the speed observation information of the autonomous driving vehicle.

[0108] It can be understood that the vehicle state determination device of the above-mentioned autonomous driving vehicle can implement the various steps of the vehicle state determination method of the autonomous driving vehicle provided in the aforementioned embodiments. The relevant explanations on the vehicle state determination method of the autonomous driving vehicle are applicable to the vehicle state determination device of the autonomous driving vehicle and will not be repeated here.

[0109] Figure 3 This is a schematic diagram of the structure of a device in the embodiment of the present application. Figure 3 As shown, the device includes one or more processors (or processing units), may further include one or more memories coupled to the processors, and may further include a communication module coupled to the processors.

[0110] The communication module can be used to communicate with other devices or apparatuses, such as sending or receiving data and / or signals. The communication module can include at least one communication module for communication. The communication module can include any interface necessary for communicating with other devices. Exemplarily, the communication module can be a transceiver, circuit, bus, module, or other type of communication module.

[0111] The processor may include, but is not limited to, at least one of the following: a general-purpose computer, a special-purpose computer, a microcontroller, a digital signal processor (DSP), or one or more of a controller-based multi-core controller architecture. A device may have multiple processors, such as application-specific integrated circuit chips, which are time-slave to a clock synchronized with a main processor.

[0112] The memory may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, at least one of the following: read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), or other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, at least one of the following: random access memory (RAM), or other volatile memories that do not persist during a power outage.

[0113] A computer program includes computer-executable instructions that are executed by an associated processor. The program may be stored in ROM. The processor may perform any suitable actions and processes by loading the program into RAM.

[0114] The possible implementation of the present application can be realized by means of a program, so that the communication device can perform any process discussed in the above embodiments. The possible implementation of the present application can also be realized by hardware or by a combination of software and hardware.

[0115] In some embodiments, the program may be tangibly contained in a computer-readable storage medium that may be included in the device (such as in a memory) or other storage device accessible by the device. The program may be loaded from the computer-readable storage medium into RAM for execution. The computer-readable storage medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc.

[0116] The present application also provides a computer-readable storage medium having computer instructions or program codes stored thereon, which, when executed by a processor, causes the processor to perform the methods and functions described in any of the above embodiments. A computer-readable medium may be any tangible medium containing or storing a program for or related to an instruction execution system, apparatus, or device. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. Computer-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrated therein. More detailed examples of computer-readable storage media include electrical connections with one or more wires, magnetic media (e.g., magnetic disks, floppy disks, hard disks, tapes, magnetic storage devices), optical media (e.g., optical storage devices, DVDs), semiconductor media (e.g., solid-state drives), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), or any suitable combination thereof.

[0117] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The embodiments of the present application also provide at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes one or more computer-executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the processes, methods and functions involved in any of the above embodiments. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) method.

[0118] The present application also provides a computer program product, including a computer program or instructions, which, when run on a computer, causes the computer to perform the processes, methods, and functions in the above-described embodiments. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of the program modules can be combined or divided between program modules as needed. The machine executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, the program modules can be located in local and remote storage media.

[0119] In general, various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software, which can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that the blocks, devices, systems, techniques, or methods described herein can be implemented as, by way of non-limiting example, hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0120] It should be noted that although the embodiments of the present application are described above in conjunction with the accompanying drawings, the above embodiments are not independent of each other, and they can also be combined to obtain other embodiments. The methods, situations, categories, and divisions of the embodiments in the embodiments of the present application are only for the convenience of description and should not constitute special limitations. The features of the various methods, categories, situations, and embodiments can be combined with each other when they are logical. The various embodiments of the present application can be combined arbitrarily to achieve different technical effects. The embodiments of the present application no longer list various combinations.

[0121] In addition, although the operations of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart can change the order of execution. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps. It should also be noted that the features and functions of two or more devices according to the present disclosure can be embodied in one device. Conversely, the features and functions of a device described above can be further divided into being embodied by multiple devices.

[0122] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0123] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for determining a vehicle state of an autonomous vehicle, wherein: The vehicle state determination method of the autonomous driving vehicle includes: Obtain chassis speed and multi-source positioning data of autonomous vehicles; determining a first state indicator of the autonomous driving vehicle based on the chassis speed; determining a second state identifier of the autonomous driving vehicle based on the multi-source positioning data; The current driving state of the autonomous driving vehicle is determined based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle, and the current driving state is a stationary state or a moving state.

2. The method for determining the vehicle state of an autonomous vehicle according to claim 1, wherein: Determining the first state identifier of the automatic driving vehicle according to the chassis speed includes: Determining whether the chassis speed is 0; If so, determining that the first state identifier of the autonomous driving vehicle is a stationary state identifier; Otherwise, it is determined that the first state identifier of the automatic driving vehicle is a motion state identifier.

3. The method for determining the vehicle state of an autonomous vehicle according to claim 1, wherein: The multi-source positioning data includes IMU data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes: Calculate the variance and mean of the IMU data based on the IMU data within the preset time period; If the variance and the mean of the IMU data are respectively less than the first threshold and the second threshold, determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier; Otherwise, it is determined that the second state identifier of the automatic driving vehicle is a motion state identifier.

4. The method for determining the vehicle state of an autonomous vehicle according to claim 1, wherein: The multi-source positioning data includes laser SLAM positioning data and visual SLAM positioning data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes: Calculate the deviation between each two adjacent frames of laser SLAM positioning data based on the laser SLAM positioning data within a preset time period, and calculate the deviation between each two adjacent frames of visual SLAM positioning data based on the visual SLAM positioning data within a preset time period; If the deviation between each two adjacent frames of laser SLAM positioning data and / or the deviation between each two adjacent frames of visual SLAM positioning data is less than a third threshold, determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier; Otherwise, it is determined that the second state identifier of the automatic driving vehicle is a motion state identifier.

5. The method for determining the vehicle state of an autonomous vehicle according to claim 1, wherein: The multi-source positioning data includes RTK positioning data and GNSS raw positioning data within a preset time period, and determining the second state identifier of the autonomous driving vehicle based on the multi-source positioning data includes: Calculate the deviation between each two adjacent frames of RTK positioning data based on the RTK positioning data within a preset time period, and calculate the deviation between each two adjacent frames of GNSS raw positioning data based on the GNSS raw positioning data within a preset time period; If the deviation between each two adjacent frames of RTK positioning data and / or the deviation between each two adjacent frames of GNSS raw positioning data is less than a fourth threshold, determining that the second state identifier of the autonomous driving vehicle is a stationary state identifier; Otherwise, it is determined that the second state identifier of the automatic driving vehicle is a motion state identifier.

6. The method for determining the vehicle state of an autonomous vehicle according to claim 1, wherein: The second state identifier of the autonomous driving vehicle includes a plurality of identifiers, and determining the current driving state of the autonomous driving vehicle according to the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle includes: If the first state identifier of the autonomous driving vehicle is a stationary state identifier, and at least a preset number of second state identifiers among the plurality of second state identifiers are stationary state identifiers, determining that the current driving state of the autonomous driving vehicle is a stationary state; Otherwise, it is determined that the current driving state of the automatic driving vehicle is a moving state.

7. The method for determining the vehicle state of an autonomous vehicle according to claim 1, wherein: The method for determining the vehicle state of the autonomous driving vehicle further includes: When the current driving state of the autonomous driving vehicle is a stationary state, setting the speed observation information of the autonomous driving vehicle to 0; Update the estimated value of the IMU zero bias based on the speed observation information of the autonomous driving vehicle.

8. A vehicle state determination device for an autonomous vehicle, wherein: The vehicle state determination device of the autonomous driving vehicle includes: an acquisition unit, configured to acquire chassis speed and multi-source positioning data of the autonomous driving vehicle; a first determining unit, configured to determine a first state identifier of the automatic driving vehicle according to the chassis speed; a second determining unit, configured to determine a second state identifier of the autonomous driving vehicle based on the multi-source positioning data; The third determination unit is used to determine the current driving state of the autonomous driving vehicle based on the first state identifier of the autonomous driving vehicle and the second state identifier of the autonomous driving vehicle, where the current driving state is a stationary state or a moving state.

9. A device comprising: processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to execute the vehicle state determination method for an autonomous driving vehicle according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the vehicle state determination method of any one of claims 1 to 7 is implemented.

Images