Positioning method, device and electronic equipment of autonomous vehicle, and storage medium

Abstract

This application discloses a localization method, device, electronic device, and storage medium for an autonomous vehicle. The method includes: acquiring measurement data from a second sensor, including IMU measurement data and first wheel speed measurement data, when multiple first sensors are in a failed state; determining the driving state based on the IMU measurement data; determining the current speed measurement noise based on the driving state and a speed measurement noise fitting result, wherein the speed measurement noise fitting result is obtained for different driving states and when at least one first sensor is in an effective state; and performing localization based on the measurement data from the second sensor and the speed measurement noise. This application provides assisted localization based on IMU and wheel speed measurement when multi-sensor localization fails, and uses the fitted speed measurement noise fitting results for different driving states to determine the current speed measurement noise, thereby performing localization estimation and improving the localization accuracy and stability in multi-sensor localization failure scenarios.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a positioning method, device, electronic device, and storage medium for an autonomous vehicle. Background Technology

[0002] With the development of autonomous driving technology and automotive-grade hardware, multi-sensor fusion positioning technologies such as GNSS (Global Navigation Satellite System) / RTK (Real-time kinematic) + IMU (Inertial Measurement Unit) + laser / visual positioning have gradually replaced traditional integrated navigation technologies such as GNSS / RTK + IMU positioning technologies, becoming the mainstream positioning solution for autonomous vehicles.

[0003] Due to the influence of signal quality, GNSS / RTK cannot provide effective positioning information at all times. Therefore, in multi-sensor fusion positioning schemes that use Kalman filtering as the fusion framework, laser positioning or visual positioning is used as an auxiliary positioning method. When GNSS / RTK fails, it can provide additional observation information to the filter to ensure the smoothness and stability of positioning.

[0004] Relying on high-precision maps or pre-established point cloud maps, visual positioning or laser positioning can, under ideal conditions, provide high-confidence positioning information at 10 Hz in real time. Under good road, vehicle, and environmental conditions, it can provide centimeter-level positioning for autonomous vehicles, comparable to GNSS / RTK accuracy.

[0005] However, in various extreme situations, such as snow accumulation, sensor interference, road damage, and tunnel areas, visual positioning or laser positioning may fail, resulting in poor fusion positioning. In such cases, the positioning of autonomous vehicles can only rely on IMU and wheel speedometers, but the measurement information at this time contains a lot of noise, resulting in low positioning accuracy and stability of autonomous vehicles. Summary of the Invention

[0006] This application provides a positioning method, device, electronic device, and storage medium for autonomous vehicles to improve the positioning accuracy and stability of autonomous vehicles in special scenarios.

[0007] The embodiments of this application adopt the following technical solutions:

[0008] In a first aspect, embodiments of this application provide a method for locating an autonomous vehicle, wherein the method includes:

[0009] When the positioning status of multiple first sensors of an autonomous vehicle is in a failed state, the measurement data of the second sensor is acquired. The measurement data of the second sensor includes IMU measurement data and first wheel speed measurement data.

[0010] The driving status of the autonomous vehicle is determined based on the IMU measurement data;

[0011] The current speed measurement noise is determined based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and under the condition that the positioning state of at least one first sensor is in an effective state.

[0012] The location of the autonomous vehicle is obtained by performing localization based on the measurement data from the second sensor and the speed measurement noise.

[0013] Optionally, the first wheel speed measurement data includes the speed output by the wheel speed meter, and the step of locating the autonomous vehicle based on the measurement data from the second sensor and the speed measurement noise includes:

[0014] The first observed speed of the autonomous vehicle is constructed based on the speed and non-integrity constraints output by the wheel speedometer.

[0015] The location of the autonomous vehicle is obtained by performing localization based on the IMU measurement data, the first observed speed of the autonomous vehicle, and the speed measurement noise.

[0016] Optionally, constructing the first observed speed of the autonomous vehicle based on the speed and non-integrity constraints output by the wheel speedometer includes:

[0017] The speed output by the wheel speed meter is used as the forward speed of the autonomous vehicle.

[0018] The lateral and vertical velocities of the autonomous vehicle are constrained by non-holonomic constraints to obtain the non-holonomically constrained lateral and vertical velocities.

[0019] The first observed velocity of the autonomous vehicle is constructed based on its forward velocity and its lateral and vertical velocities after non-integrity constraints.

[0020] Optionally, the velocity measurement noise fitting result is obtained in the following way:

[0021] Determine the positioning status of multiple primary sensors and the driving status of the autonomous vehicle;

[0022] When the positioning status of the target first sensor is in an effective state, the measurement data of the target first sensor and the second wheel speed measurement data under different driving states are obtained according to the driving state of the autonomous vehicle. The target first sensor is at least one of a plurality of first sensors.

[0023] Based on the measurement data from the first sensor and the second wheel speed measurement data, a preset fitting algorithm is used to fit the speed measurement noise corresponding to different driving states, thereby obtaining the speed measurement noise fitting results for different driving states.

[0024] Optionally, acquiring the target first sensor measurement data and second wheel speed measurement data under different driving states according to the driving state of the autonomous vehicle includes:

[0025] If the autonomous vehicle is in a straight-line driving state, then acquire the target first sensor measurement data and second wheel speed measurement data in a continuous multi-frame straight-line driving state within a first preset time period.

[0026] If the autonomous vehicle is in a turning state, then the measurement data of the first sensor and the second wheel speed measurement data of the target in the turning state are acquired in multiple consecutive frames within a second preset time period.

[0027] Optionally, the step of fitting the speed measurement noise corresponding to different driving states using a preset fitting algorithm based on the measurement data of the first sensor and the second wheel speed measurement data to obtain the speed measurement noise fitting results for different driving states includes:

[0028] Based on the measurement data of the first sensor of the target and the second wheel speed measurement data of multiple consecutive frames in the straight-moving state within the first preset time period, the speed measurement noise in the straight-moving state is fitted using a preset fitting algorithm to obtain the speed measurement noise fitting result in the straight-moving state.

[0029] Based on the measurement data of the first sensor and the second wheel speed measurement data of the target under the turning state in multiple consecutive frames within the second preset time period, the speed measurement noise under the turning state is fitted using a preset fitting algorithm to obtain the speed measurement noise fitting result under the turning state.

[0030] Optionally, the autonomous vehicle is equipped with at least two IMUs, and the IMU measurement data is valid IMU measurement data. Acquiring the measurement data from the second sensor includes:

[0031] The status of each IMU is determined based on the measurement data and IMU measurement thresholds.

[0032] The valid IMU measurement data are determined based on the status of each IMU.

[0033] Optionally, after determining the location of the autonomous vehicle based on the measurement data from the second sensor and the speed measurement noise, the method further includes:

[0034] The positioning accuracy of the autonomous vehicle's positioning results is determined based on the positioning results of the autonomous vehicle.

[0035] The location accuracy of the autonomous vehicle's location results determines whether the autonomous vehicle has triggered an alarm condition.

[0036] If the alarm conditions are triggered, an alarm will be issued and the location of the autonomous vehicle will be downgraded.

[0037] Secondly, embodiments of this application also provide a positioning device for an autonomous vehicle, wherein the device includes:

[0038] The acquisition unit is used to acquire measurement data from a second sensor when the positioning status of multiple first sensors of an autonomous vehicle is in a failed state. The measurement data from the second sensor includes IMU measurement data and first wheel speed measurement data.

[0039] The first determining unit is used to determine the driving state of the autonomous vehicle based on the IMU measurement data;

[0040] The second determining unit is used to determine the current speed measurement noise based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and when the positioning state of at least one first sensor is in an effective state.

[0041] The positioning unit is used to perform positioning based on the measurement data of the second sensor and the speed measurement noise to obtain the positioning result of the autonomous vehicle.

[0042] Thirdly, embodiments of this application also provide an electronic device, including:

[0043] Processor; and

[0044] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0045] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform any of the methods described above.

[0046] The above-mentioned at least one technical solution adopted in the embodiments of this application can achieve the following beneficial effects: The autonomous vehicle positioning method of this application, when the positioning states of multiple first sensors of the autonomous vehicle are all in a failed state, acquires measurement data from a second sensor, including IMU measurement data and first wheel speed measurement data; then, determines the driving state of the autonomous vehicle based on the IMU measurement data; subsequently, determines the current speed measurement noise based on the driving state of the autonomous vehicle and the speed measurement noise fitting result, where the speed measurement noise fitting result is obtained for different driving states and under the condition that the positioning state of at least one first sensor is valid; finally, positioning is performed based on the measurement data of the second sensor and the speed measurement noise to obtain the positioning result of the autonomous vehicle. The autonomous vehicle positioning method of this application, when multiple sensor positioning fails, performs assisted positioning for a certain period based on the IMU and wheel speed meter, and uses pre-fitted speed measurement noise fitting results for different driving states to determine the speed measurement noise under the current driving state, thereby performing positioning estimation, improving the positioning accuracy and positioning stability in multi-sensor positioning failure scenarios. Attached Figure Description

[0047] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0048] Figure 1 This is a flowchart illustrating a positioning method for an autonomous vehicle according to an embodiment of this application.

[0049] Figure 2 This is a schematic diagram of the structure of a positioning device for an autonomous vehicle according to an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0053] This application provides a method for locating an autonomous vehicle, such as... Figure 1 The diagram shows a flowchart of a positioning method for an autonomous vehicle according to an embodiment of this application. The method includes at least the following steps S110 to S140:

[0054] Step S110: When the positioning status of multiple first sensors of the autonomous vehicle is in a failed state, the measurement data of the second sensor is acquired. The measurement data of the second sensor includes IMU measurement data and first wheel speed measurement data.

[0055] The positioning scheme for autonomous vehicles in this application is mainly an auxiliary positioning scheme adopted when the positioning status of multiple first sensors of the autonomous vehicle fails. The first sensors may include, for example, lidar, vision camera and GNSS / RTK. In extreme cases, when the positioning status of these sensors is all in a failed state, the autonomous vehicle needs to rely on the measurement data output by second sensors such as IMU and wheel speed meter for positioning. The measurement data output by IMU may include, for example, angular velocity and acceleration, and the measurement data output by wheel speed meter may include, for example, velocity.

[0056] Step S120: Determine the driving status of the autonomous vehicle based on the IMU measurement data.

[0057] When locating an autonomous vehicle based on a second sensor, speed is one of the key observation parameters. However, speed measurements can be noisy in the event of multi-sensor positioning failure. Furthermore, the magnitude of this noise varies depending on the vehicle's driving state (e.g., straight-ahead or turning). Relying on a fixed noise value for filtering would reduce the positioning accuracy, especially during turns where the positioning divergence is significant. Therefore, this embodiment of the application requires further determination of the autonomous vehicle's current driving state (e.g., whether it is straight-ahead or turning) based on IMU measurement data.

[0058] Step S130: Determine the current speed measurement noise based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and under the condition that the positioning state of at least one first sensor is in an effective state.

[0059] Since the speed measurement noise varies depending on the driving state, the embodiments of this application first fit the speed measurement noise for different driving states while at least one first sensor is in an active state, thereby obtaining the speed measurement noise fitting results for different driving states.

[0060] Based on the speed measurement noise fitting results corresponding to the different driving states, and combined with the current driving state, the speed measurement noise corresponding to the current speed measurement information can be determined.

[0061] Step S140: Based on the measurement data of the second sensor and the speed measurement noise, the vehicle is located to obtain the positioning result of the autonomous vehicle.

[0062] After obtaining the speed measurement noise corresponding to the current driving state, the speed measurement noise can be used as the basis for correcting the speed observation information. Together with the measurement data of the second sensor, it is input into the Kalman filter for filtering processing, thereby obtaining the current positioning result, including the position and attitude information of the autonomous vehicle.

[0063] The autonomous vehicle positioning method of this application embodiment performs assisted positioning for a certain period of time based on IMU and wheel speedometer when multiple sensor positioning fails. It also uses the pre-fitted speed measurement noise fitting results of different driving states to determine the speed measurement noise in the current driving state, thereby performing positioning estimation and improving the positioning accuracy and positioning stability in multi-sensor positioning failure scenarios.

[0064] In some embodiments of this application, the positioning status of the plurality of first sensors includes the positioning status of laser SLAM, the positioning status of visual SLAM, and the positioning status of GNSS / RTK. When the positioning status of the plurality of first sensors of the autonomous vehicle is in a failed state, acquiring the measurement data of the second sensor includes: acquiring the confidence level of laser SLAM positioning information, the confidence level of visual SLAM positioning information, and the differential status of GNSS / RTK positioning information; when the confidence level of laser SLAM positioning information is lower than a first preset confidence threshold, the confidence level of visual SLAM positioning information is lower than a second preset confidence threshold, and the differential status of GNSS / RTK positioning information is a non-fixed solution state, it is determined that the positioning status of the plurality of first sensors of the autonomous vehicle is in a failed state.

[0065] When implementing the positioning scheme of this application embodiment, it is possible to determine in real time whether the positioning status of each first sensor is in a failed state. Specifically, it can be determined based on the confidence level of the positioning information provided by laser SLAM, the confidence level of the positioning information provided by visual SLAM, and the differential state of the positioning information provided by GNSS / RTK. If the confidence level of the laser SLAM positioning information is lower than the corresponding confidence threshold requirement, it indicates that the laser SLAM positioning is in a failed state. If the confidence level of the visual SLAM positioning information is lower than the corresponding confidence threshold requirement, it indicates that the visual SLAM positioning is also in a failed state. If the positioning result of GNSS / RTK is a non-fixed solution, it indicates that the GNSS / RTK positioning is also in a failed state.

[0066] When the aforementioned laser SLAM, visual SLAM, and GNSS / RTK positioning are all ineffective, dead reckoning must be performed using the IMU and wheel speedometer of the autonomous vehicle.

[0067] In some embodiments of this application, determining the driving state of the autonomous vehicle based on the IMU measurement data includes: determining the angular velocity change information of the autonomous vehicle based on the angular velocity, and determining the lateral velocity of the autonomous vehicle based on the acceleration; if the angular velocity change information of the autonomous vehicle is greater than a preset angular velocity change threshold, and the lateral velocity of the autonomous vehicle is greater than a preset lateral velocity threshold, then the driving state of the autonomous vehicle is determined to be a turning state; otherwise, the driving state of the autonomous vehicle is determined to be a straight-going state.

[0068] In this embodiment of the application, when determining the current driving state of an autonomous vehicle, the first IMU measurement data can be used to determine the driving state of the autonomous vehicle, which may specifically include angular velocity and acceleration. The angular velocity and acceleration information are used to comprehensively judge the driving state of the autonomous vehicle to ensure the accuracy of the driving state judgment.

[0069] On one hand, the angular velocity changes of autonomous vehicles can be calculated using angular velocity information. For example, the angular velocity variance can be used as a measure, because the angular velocity change is usually small when the vehicle is traveling straight, but changes significantly when turning. On the other hand, the current velocity can be calculated from the acceleration and the velocity at the previous moment. By decomposing this, the lateral velocity of the autonomous vehicle can be obtained. Because the lateral velocity should be equal to or close to 0 when the vehicle is traveling straight, without considering sideslip, while it will be significantly greater than 0 when turning. Based on this, if the angular velocity variance is greater than a pre-set variance threshold, and the lateral velocity is also greater than the corresponding lateral velocity threshold, then the autonomous vehicle can be considered to be currently turning; otherwise, it is considered to be traveling straight.

[0070] In some embodiments of this application, the first wheel speed measurement data includes the speed output by the wheel speed meter. The step of locating the autonomous vehicle based on the measurement data of the second sensor and the speed measurement noise to obtain the positioning result of the autonomous vehicle includes: constructing a first observed speed of the autonomous vehicle based on the speed output by the wheel speed meter and non-integrity constraints; and locating the autonomous vehicle based on the IMU measurement data, the first observed speed of the autonomous vehicle, and the speed measurement noise to obtain the positioning result of the autonomous vehicle.

[0071] In this embodiment, when locating the vehicle based on the measurement data from the second sensor and the velocity measurement noise, the first observed velocity of the autonomous vehicle can be constructed based on the velocity output by the wheel speedometer, using a fusion of vehicle kinematic constraints, i.e., non-holonomic constraints (NHC). Non-holonomic constraints assume that the vehicle does not experience sideslip, drift, or bouncing during its operation, and that its lateral and vertical velocities are zero. This process constructs virtual observations and applies motion constraints. The effectiveness of this process is closely related to the setting of the variance of the virtual observations.

[0072] Based on the filtering equation of the Kalman filter, the first IMU measurement data, the first observed speed of the autonomous vehicle, and the speed measurement noise are input into the Kalman filter for filtering processing, thereby obtaining the localization result of the autonomous vehicle.

[0073] In some embodiments of this application, constructing the first observed speed of the autonomous vehicle based on the speed output by the wheel speed meter and non-integrity constraints includes: using the speed output by the wheel speed meter as the forward speed of the autonomous vehicle; constraining the lateral and vertical speeds of the autonomous vehicle according to non-integrity constraints to obtain the non-integrity-constrained lateral and vertical speeds; and constructing the first observed speed of the autonomous vehicle based on the forward speed of the autonomous vehicle and the non-integrity-constrained lateral and vertical speeds.

[0074] In this embodiment of the application, when constructing the first observed speed of an autonomous vehicle based on the speed and incompleteness constraints output by the wheel speed meter, the constraint that the speed of the vehicle's X-axis and Z-axis (X, Y, Z correspond to the right, front, and up directions of the vehicle, respectively) is zero during normal driving can be used to determine the speed measurement noise. The speed of the Y-axis is speed_vehicle output by the wheel speed meter, and the observed speed (0, speed_vehicle, 0) is constructed in this way, thereby improving the accuracy of dead reckoning.

[0075] The Kalman filter equation can be expressed as Z = HX + V, where Z is the observed velocity (0, speed_vehicle, 0), H is the measurement matrix, X is the state variable to be estimated (velocity, position, attitude), and V is the velocity measurement noise.

[0076] In some embodiments of this application, the speed measurement noise fitting result is obtained as follows: determining the positioning state of multiple first sensors and the driving state of the autonomous vehicle; when the positioning state of the target first sensor is valid, acquiring the measurement data of the target first sensor and the second wheel speed measurement data under different driving states according to the driving state of the autonomous vehicle, wherein the target first sensor is at least one of multiple first sensors; and fitting the speed measurement noise corresponding to different driving states using a preset fitting algorithm based on the measurement data of the target first sensor and the second wheel speed measurement data to obtain the speed measurement noise fitting result for different driving states.

[0077] In this embodiment of the application, when fitting the speed measurement noise, the positioning status of each first sensor and the driving status of the autonomous vehicle can be determined first. When the positioning status of at least one first sensor is in an effective state, the current driving status of the vehicle is further determined. Then, based on the current driving status, the measurement data of the corresponding target first sensor and the second wheel speed measurement data are obtained. The speed measurement noise is obtained by subtracting the speed measured by the target first sensor and the speed measured by the wheel speed measurement. By continuously calculating multiple speed measurement noises, a reliable correspondence between the speed measurement noise, wheel speed measurement data, and driving status is fitted using a certain fitting algorithm such as the least squares fitting algorithm. This serves as the basis for real-time determination of speed measurement noise in subsequent multi-sensor failure scenarios.

[0078] In some embodiments of this application, the step of acquiring the target first sensor measurement data and second wheel speed measurement data under different driving states according to the driving state of the autonomous vehicle includes: if the autonomous vehicle is driving straight, acquiring the target first sensor measurement data and second wheel speed measurement data for multiple consecutive frames in the straight-driving state within a first preset time period; if the autonomous vehicle is driving turning, acquiring the target first sensor measurement data and second wheel speed measurement data for multiple consecutive frames in the turning state within a second preset time period.

[0079] Since there are significant differences in speed measurement noise under different driving conditions, when using a fitting algorithm, it is necessary to fit the speed measurement noise data under different driving conditions separately. Therefore, during the data acquisition phase, it is necessary to collect measurement data under different driving conditions separately.

[0080] Specifically, when at least one first sensor is in an active state, the current driving state of the autonomous vehicle is further determined. If it is in a straight-ahead state, the measurement data of the first sensor and the corresponding wheel speed measurement data of multiple consecutive frames in the straight-ahead state within a certain period of time are obtained. If it is in a turning state, the measurement data of the first sensor and the wheel speed measurement data of multiple consecutive frames in the turning state within a certain period of time are obtained.

[0081] The reason why data needs to be collected continuously during the constraint fitting stage is that the continuity of data can improve the accuracy of the fitting algorithm, and reduces the requirement for the amount of data compared to training the model.

[0082] In some embodiments of this application, the step of fitting the speed measurement noise corresponding to different driving states using a preset fitting algorithm based on the measurement data of the first target sensor and the second wheel speed measurement data to obtain speed measurement noise fitting results for different driving states includes: fitting the speed measurement noise in the straight-ahead state using a preset fitting algorithm based on the measurement data of the first target sensor and the second wheel speed measurement data of multiple consecutive frames in the straight-ahead state within a first preset time period to obtain speed measurement noise fitting results in the straight-ahead state; and fitting the speed measurement noise in the turning state using a preset fitting algorithm based on the measurement data of the first target sensor and the second wheel speed measurement data of multiple consecutive frames in the turning state within a second preset time period to obtain speed measurement noise fitting results in the turning state.

[0083] Based on the measurement data obtained in the straight-ahead state and the turning state obtained in the aforementioned embodiments, multiple consecutive speed measurement noises in the straight-ahead state and the turning state can be calculated respectively. Then, the correspondence between the speed measurement noise and the measurement data can be fitted by least squares fitting algorithms, and an association can be established with the corresponding driving state. When used in the subsequent positioning stage, the fitting relationship of the corresponding speed measurement noise can be obtained according to the driving state, and the current measurement data can be input into the fitting relationship to obtain the current speed measurement noise.

[0084] In some embodiments of this application, the autonomous vehicle is equipped with at least two IMUs, and the IMU measurement data is valid IMU measurement data. The acquisition of measurement data from the second sensor includes: determining the state of each IMU based on the measurement data of each IMU and the IMU measurement threshold; and determining the valid IMU measurement data based on the state of each IMU.

[0085] Current autonomous vehicles typically only have one IMU (Integrated Measurement Unit). However, if multiple sensor positioning fails, and a single IMU also malfunctions, the entire positioning system will fail. Therefore, the autonomous vehicle in this embodiment is equipped with at least two IMUs. When both IMUs are active, the measurement data from either IMU can be used for subsequent processing. Alternatively, the measurement data from the two IMUs can be weighted and fused before being used for further processing.

[0086] The status of each IMU can be determined based on IMU measurement thresholds. If the measurement data of one IMU does not meet the IMU measurement threshold requirements, the IMU can be considered to be in a failed state, and the measurement data of another IMU can be used for subsequent processing. This embodiment further ensures the positioning accuracy and stability of autonomous vehicles in the event of multi-sensor positioning failure through redundant IMU configuration.

[0087] In some embodiments of this application, after obtaining the positioning result of the autonomous vehicle by positioning based on the measurement data of the second sensor and the speed measurement noise, the method further includes: determining the positioning accuracy of the autonomous vehicle positioning result based on the positioning result of the autonomous vehicle; determining whether the autonomous vehicle has triggered an alarm condition based on the positioning accuracy of the positioning result of the autonomous vehicle; and, if the alarm condition is triggered, issuing an alarm and performing positioning downgrade processing on the autonomous vehicle.

[0088] Based on the aforementioned embodiments, the positioning accuracy of autonomous vehicles can be maintained for a short period of time in the event of multi-sensor positioning failure. However, if effective sensor observation information cannot be obtained for a long time, the positioning accuracy of autonomous vehicles will decrease. Therefore, the embodiments of this application can determine the positioning accuracy in real time based on the positioning results of autonomous vehicles. If the positioning accuracy meets the positioning accuracy requirements of autonomous vehicles, they can continue to drive normally. If it does not meet the requirements, an alarm is triggered, and the autonomous vehicle needs to be downgraded, i.e., lane keeping is required. If effective sensor observation information cannot be obtained for a certain period of time, remote intervention or manual takeover is required to ensure the safety of autonomous vehicles.

[0089] This application also provides a positioning device 200 for an autonomous vehicle, such as... Figure 2 The diagram shows a schematic representation of a positioning device for an autonomous vehicle according to an embodiment of this application. The device 200 includes at least: an acquisition unit 210, a first determination unit 220, a second determination unit 230, and a positioning unit 240, wherein:

[0090] The acquisition unit 210 is used to acquire measurement data of a second sensor when the positioning status of multiple first sensors of an autonomous vehicle is in a failed state. The measurement data of the second sensor includes IMU measurement data and first wheel speed measurement data.

[0091] The first determining unit 220 is used to determine the driving state of the autonomous vehicle based on the IMU measurement data;

[0092] The second determining unit 230 is used to determine the current speed measurement noise based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and when the positioning state of at least one first sensor is in an effective state.

[0093] The positioning unit 240 is used to perform positioning based on the measurement data of the second sensor and the speed measurement noise to obtain the positioning result of the autonomous vehicle.

[0094] In some embodiments of this application, the first wheel speed measurement data includes the speed output by the wheel speed meter, and the positioning unit 240 is specifically used to: construct a first observed speed of the autonomous vehicle based on the speed output by the wheel speed meter and non-integrity constraints; perform positioning based on the IMU measurement data, the first observed speed of the autonomous vehicle, and the speed measurement noise to obtain the positioning result of the autonomous vehicle.

[0095] In some embodiments of this application, the positioning unit 240 is specifically used to: use the speed output by the wheel speed meter as the forward speed of the autonomous vehicle; constrain the lateral speed and vertical speed of the autonomous vehicle according to non-integrity constraints to obtain the non-integrity-constrained lateral speed and vertical speed; and construct the first observed speed of the autonomous vehicle based on the forward speed of the autonomous vehicle and the non-integrity-constrained lateral speed and vertical speed.

[0096] In some embodiments of this application, the speed measurement noise fitting result is obtained as follows: determining the positioning state of multiple first sensors and the driving state of the autonomous vehicle; when the positioning state of the target first sensor is valid, acquiring the measurement data of the target first sensor and the second wheel speed measurement data under different driving states according to the driving state of the autonomous vehicle, wherein the target first sensor is at least one of multiple first sensors; and fitting the speed measurement noise corresponding to different driving states using a preset fitting algorithm based on the measurement data of the target first sensor and the second wheel speed measurement data to obtain the speed measurement noise fitting result for different driving states.

[0097] In some embodiments of this application, the speed measurement noise fitting result is obtained in the following manner: if the autonomous vehicle is driving in a straight-line state, then the measurement data of the first sensor of the target and the second wheel speed measurement data of the target in a straight-line state are obtained in a continuous multi-frame period within a first preset time period; if the autonomous vehicle is driving in a turning state, then the measurement data of the first sensor of the target and the second wheel speed measurement data of the target in a turning state of a continuous multi-frame period within a second preset time period are obtained.

[0098] In some embodiments of this application, the speed measurement noise fitting result is obtained as follows: based on the measurement data of the first sensor of the target and the second wheel speed measurement data of multiple consecutive frames in the straight-ahead state within a first preset time period, the speed measurement noise in the straight-ahead state is fitted using a preset fitting algorithm to obtain the speed measurement noise fitting result in the straight-ahead state; based on the measurement data of the first sensor of the target and the second wheel speed measurement data of multiple consecutive frames in the turning state within a second preset time period, the speed measurement noise in the turning state is fitted using a preset fitting algorithm to obtain the speed measurement noise fitting result in the turning state.

[0099] In some embodiments of this application, the autonomous vehicle is equipped with at least two IMUs, and the IMU measurement data is valid IMU measurement data. The acquisition unit 210 is specifically used to: determine the state of each IMU based on the measurement data of each IMU and the IMU measurement threshold; and determine the valid IMU measurement data based on the state of each IMU.

[0100] In some embodiments of this application, the device further includes: a third determining unit, configured to determine the positioning accuracy of the autonomous vehicle's positioning result based on the positioning result of the autonomous vehicle after obtaining the positioning result of the autonomous vehicle by performing positioning based on the measurement data of the second sensor and the speed measurement noise; a fourth determining unit, configured to determine whether the autonomous vehicle has triggered an alarm condition based on the positioning accuracy of the autonomous vehicle's positioning result; and an alarm and downgrade unit, configured to issue an alarm and perform positioning downgrade processing on the autonomous vehicle when the alarm condition is triggered.

[0101] It is understood that the above-mentioned positioning device for autonomous vehicles can realize each step of the positioning method for autonomous vehicles provided in the foregoing embodiments. The relevant explanations of the positioning method for autonomous vehicles are applicable to the positioning device for autonomous vehicles, and will not be repeated here.

[0102] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 3At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0103] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0104] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0105] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming the positioning device for the autonomous vehicle at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0106] When the positioning status of multiple first sensors of an autonomous vehicle is in a failed state, the measurement data of the second sensor is acquired. The measurement data of the second sensor includes IMU measurement data and first wheel speed measurement data.

[0107] The driving status of the autonomous vehicle is determined based on the IMU measurement data;

[0108] The current speed measurement noise is determined based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and under the condition that the positioning state of at least one first sensor is in an effective state.

[0109] The location of the autonomous vehicle is obtained by performing localization based on the measurement data from the second sensor and the speed measurement noise.

[0110] The above is as stated in this application. Figure 1 The method executed by the positioning device of the autonomous vehicle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0111] The electronic device can also perform Figure 1 The method for implementing the positioning device of an autonomous vehicle, and realizing the positioning device of the autonomous vehicle in Figure 1 The functions of the embodiments shown are not described in detail here.

[0112] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the positioning device of the autonomous vehicle in the illustrated embodiment is specifically used to perform:

[0113] When the positioning status of multiple first sensors of an autonomous vehicle is in a failed state, the measurement data of the second sensor is acquired. The measurement data of the second sensor includes IMU measurement data and first wheel speed measurement data.

[0114] The driving status of the autonomous vehicle is determined based on the IMU measurement data;

[0115] The current speed measurement noise is determined based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and under the condition that the positioning state of at least one first sensor is in an effective state.

[0116] The location of the autonomous vehicle is obtained by performing localization based on the measurement data from the second sensor and the speed measurement noise.

[0117] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0119] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0121] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0122] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0123] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0124] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0125] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for locating an autonomous vehicle, wherein, The method includes: When the positioning status of multiple first sensors of an autonomous vehicle is in a failed state, the measurement data of the second sensor is acquired. The measurement data of the second sensor includes IMU measurement data and first wheel speed measurement data. The driving status of the autonomous vehicle is determined based on the IMU measurement data; The current speed measurement noise is determined based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and under the condition that the positioning state of at least one first sensor is in an effective state. The location of the autonomous vehicle is obtained by performing positioning based on the measurement data of the second sensor and the speed measurement noise. The driving state includes straight driving and turning, and the speed measurement noise is different for different driving states. The velocity measurement noise fitting result is obtained in the following way: Determine the positioning status of multiple primary sensors and the driving status of the autonomous vehicle; When the positioning status of the target first sensor is in an effective state, the measurement data of the target first sensor and the second wheel speed measurement data under different driving states are obtained according to the driving state of the autonomous vehicle. The target first sensor is at least one of a plurality of first sensors. Based on the measurement data from the first sensor and the second wheel speed measurement data, a preset fitting algorithm is used to fit the speed measurement noise corresponding to different driving states, thereby obtaining the speed measurement noise fitting results for different driving states.

2. The method as described in claim 1, wherein, The first wheel speed measurement data includes the speed output by the wheel speed meter. The step of locating the autonomous vehicle based on the measurement data from the second sensor and the speed measurement noise includes: The first observed speed of the autonomous vehicle is constructed based on the speed and non-integrity constraints output by the wheel speedometer. The location of the autonomous vehicle is obtained by performing localization based on the IMU measurement data, the first observed speed of the autonomous vehicle, and the speed measurement noise.

3. The method as described in claim 2, wherein, The process of constructing the first observed speed of the autonomous vehicle based on the speed and non-integrity constraints output by the wheel speedometer includes: The speed output by the wheel speed meter is used as the forward speed of the autonomous vehicle. The lateral and vertical velocities of the autonomous vehicle are constrained by non-holonomic constraints to obtain the non-holonomically constrained lateral and vertical velocities. The first observed velocity of the autonomous vehicle is constructed based on its forward velocity and its lateral and vertical velocities after non-integrity constraints.

4. The method as described in claim 1, wherein, The step of acquiring the target first sensor measurement data and second wheel speed measurement data under different driving states according to the driving state of the autonomous vehicle includes: If the autonomous vehicle is in a straight-line driving state, then acquire the target first sensor measurement data and second wheel speed measurement data in a continuous multi-frame straight-line driving state within a first preset time period. If the autonomous vehicle is in a turning state, then the measurement data of the first sensor and the second wheel speed measurement data of the target in the turning state are acquired in multiple consecutive frames within a second preset time period.

5. The method as described in claim 4, wherein, The step of fitting the speed measurement noise corresponding to different driving states using a preset fitting algorithm based on the measurement data of the first sensor and the second wheel speed measurement data to obtain the speed measurement noise fitting results for different driving states includes: Based on the measurement data of the first sensor of the target and the second wheel speed measurement data of multiple consecutive frames in the straight-moving state within the first preset time period, the speed measurement noise in the straight-moving state is fitted using a preset fitting algorithm to obtain the speed measurement noise fitting result in the straight-moving state. Based on the measurement data of the first sensor and the second wheel speed measurement data of the target under the turning state in multiple consecutive frames within the second preset time period, the speed measurement noise under the turning state is fitted using a preset fitting algorithm to obtain the speed measurement noise fitting result under the turning state.

6. The method of claim 1, wherein, The autonomous vehicle is equipped with at least two IMUs, and the IMU measurement data is valid IMU measurement data. Acquiring the measurement data from the second sensor includes: The status of each IMU is determined based on the measurement data and IMU measurement thresholds. The valid IMU measurement data are determined based on the status of each IMU.

7. The method of claim 1, wherein, After obtaining the positioning result of the autonomous vehicle by performing positioning based on the measurement data of the second sensor and the speed measurement noise, the method further includes: The positioning accuracy of the autonomous vehicle's positioning results is determined based on the positioning results of the autonomous vehicle. The location accuracy of the autonomous vehicle's location results determines whether the autonomous vehicle has triggered an alarm condition. If the alarm conditions are triggered, an alarm will be issued and the location of the autonomous vehicle will be downgraded.

8. A positioning device for an autonomous vehicle, wherein, The device includes: The acquisition unit is used to acquire measurement data from a second sensor when the positioning status of multiple first sensors of an autonomous vehicle is in a failed state. The measurement data from the second sensor includes IMU measurement data and first wheel speed measurement data. The first determining unit is used to determine the driving state of the autonomous vehicle based on the IMU measurement data; The second determining unit is used to determine the current speed measurement noise based on the driving state of the autonomous vehicle and the speed measurement noise fitting result. The speed measurement noise fitting result is obtained for different driving states and when the positioning state of at least one first sensor is in an effective state. The positioning unit is used to perform positioning based on the measurement data of the second sensor and the speed measurement noise to obtain the positioning result of the autonomous vehicle. The driving state includes straight driving and turning, and the speed measurement noise is different for different driving states. The velocity measurement noise fitting result is obtained in the following way: Determine the positioning status of multiple primary sensors and the driving status of the autonomous vehicle; When the positioning status of the target first sensor is in an effective state, the measurement data of the target first sensor and the second wheel speed measurement data under different driving states are obtained according to the driving state of the autonomous vehicle. The target first sensor is at least one of a plurality of first sensors. Based on the measurement data from the first sensor and the second wheel speed measurement data, a preset fitting algorithm is used to fit the speed measurement noise corresponding to different driving states, thereby obtaining the speed measurement noise fitting results for different driving states.

9. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 7.

Images