Method, device and electronic equipment for optimizing pose of autonomous vehicle

Abstract

The application discloses a posture optimization method and device of an automatic driving vehicle and electronic equipment, and the method comprises the following steps: determining the current driving state of the automatic driving vehicle, wherein the current driving state comprises a motion state and a static state; determining the posture optimization strategy corresponding to the current driving state of the automatic driving vehicle according to the current driving state; determining the current posture observation data of the automatic driving vehicle according to the posture optimization strategy corresponding to the current driving state; and performing observation fusion on the current posture observation data of the automatic driving vehicle by using a preset fusion algorithm to obtain the current posture fusion result of the automatic driving vehicle. The application adopts different posture optimization strategies for different driving states of the automatic driving vehicle, so as to optimize the posture observation data output by the RTK positioning device and the like in different states, thereby obtaining more accurate posture observation data, and further improving the fusion accuracy and stability of the automatic driving vehicle.

Description

Technical Field

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

[0002] Multiple modules in an autonomous vehicle typically use the vehicle's attitude information, especially its heading angle, when performing their respective functions. A fusion positioning system composed of multiple sensors, such as GNSS (Global Navigation Satellite System) / RTK (Real-time kinematic) + IMU (Inertial Measurement Unit), can provide the vehicle's attitude information.

[0003] However, the heading angle output by RTK will drift when the vehicle is stationary. When the drift is large, it may result in a heading angle change of about 2 degrees. When the vehicle just transitions from a stationary state to a moving state, there will also be some angle deviation and jump problem, which will affect the fusion localization, perception and planning control effect of autonomous vehicles. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for optimizing the attitude of autonomous vehicles, so as to improve the accuracy and stability of attitude fusion of autonomous vehicles.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a method for attitude optimization of an autonomous vehicle, wherein the method includes:

[0007] Determine the current driving state of the autonomous vehicle, which includes both a moving state and a stationary state;

[0008] Based on the current driving state of the autonomous vehicle, determine the attitude optimization strategy corresponding to the current driving state;

[0009] The current attitude observation data of the autonomous vehicle is determined based on the attitude optimization strategy corresponding to the current driving state;

[0010] The current attitude observation data of the autonomous vehicle is fused using a preset fusion algorithm to obtain the current attitude fusion result of the autonomous vehicle.

[0011] Optionally, determining the current driving state of the autonomous vehicle includes:

[0012] Acquire the chassis speed and raw IMU data of autonomous vehicles;

[0013] The current driving state of the autonomous vehicle is determined based on the vehicle chassis speed and the raw IMU data.

[0014] Optionally, determining the attitude optimization strategy corresponding to the current driving state based on the current driving state of the autonomous vehicle includes:

[0015] When the current driving state of the autonomous vehicle is stationary, the attitude fusion result of the previous moment is obtained and the attitude optimization strategy corresponding to the stationary state is determined based on the attitude fusion result of the previous moment.

[0016] If the current driving state of the autonomous vehicle is in motion, then the attitude optimization strategy corresponding to the motion state is determined based on the attitude error determined when the autonomous vehicle switches from a stationary state to a motion state.

[0017] Optionally, the current driving state is the stationary state, and determining the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state includes:

[0018] The attitude fusion result from the previous moment is directly used as the current attitude observation data of the autonomous vehicle.

[0019] Optionally, the current driving state is the motion state, and determining the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state includes:

[0020] Acquire the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state;

[0021] Based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, the current attitude observation data of the autonomous vehicle is determined.

[0022] Optionally, determining the current attitude observation data of the autonomous vehicle based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state includes:

[0023] Determine the time when the autonomous vehicle transitions from a stationary state to a moving state;

[0024] If the time it takes for the autonomous vehicle to transition from a stationary state to a moving state is within a preset time threshold, then the current attitude observation data of the autonomous vehicle is determined directly based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state.

[0025] If the time it takes for the autonomous vehicle to transition from a stationary state to a moving state is not within the preset time threshold, a preset attenuation strategy is used to attenuate the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, and the current attitude observation data of the autonomous vehicle is determined based on the attenuated attitude error and the RTK attitude data at the current moment.

[0026] Optionally, after determining the current driving state of the autonomous vehicle, the method further includes:

[0027] When the current driving state of the autonomous vehicle is stationary, the IMU prediction data in the preset fusion algorithm is set as the true value in the stationary state, and the original IMU data in the stationary state is recorded.

[0028] IMU zero bias data are determined based on the raw IMU data in the static state;

[0029] When the current driving state of the autonomous vehicle is in motion, the raw IMU data in motion state is acquired, and the IMU zero-bias data is used to compensate for the raw IMU data in motion state.

[0030] Secondly, embodiments of this application also provide an attitude optimization device for an autonomous vehicle, wherein the device includes:

[0031] The first determining unit is used to determine the current driving state of the autonomous vehicle, the current driving state including a moving state and a stationary state;

[0032] The second determining unit is used to determine the attitude optimization strategy corresponding to the current driving state based on the current driving state of the autonomous vehicle.

[0033] The third determining unit is used to determine the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state.

[0034] The fusion unit is used to perform observation fusion on the current attitude observation data of the autonomous vehicle using a preset fusion algorithm to obtain the current attitude fusion result of the autonomous vehicle.

[0035] Thirdly, embodiments of this application also provide an electronic device, including:

[0036] Processor; and

[0037] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0038] 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.

[0039] The above-mentioned at least one technical solution adopted in the embodiments of this application can achieve the following beneficial effects: The attitude optimization method for autonomous vehicles in the embodiments of this application first determines the current driving state of the autonomous vehicle, which includes a moving state and a stationary state; based on the current driving state of the autonomous vehicle, it determines the attitude optimization strategy corresponding to the current driving state; based on the attitude optimization strategy corresponding to the current driving state, it determines the current attitude observation data of the autonomous vehicle; and it uses a preset fusion algorithm to perform observation fusion on the current attitude observation data of the autonomous vehicle to obtain the current attitude fusion result of the autonomous vehicle. The attitude optimization method for autonomous vehicles in the embodiments of this application adopts different attitude optimization strategies for different driving states of the autonomous vehicle, thereby optimizing the attitude observation data output by positioning devices such as RTK in different states, thereby obtaining more accurate attitude observation data, and thus improving the accuracy and stability of attitude fusion of autonomous vehicles. Attached Figure Description

[0040] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0041] Figure 1 This is a flowchart illustrating an attitude optimization method for an autonomous vehicle according to an embodiment of this application.

[0042] Figure 2 This is a schematic diagram of the posture optimization device for an autonomous vehicle according to an embodiment of this application;

[0043] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0044] 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.

[0045] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0046] This application provides a method for attitude optimization of autonomous vehicles, such as... Figure 1 The diagram shows a flowchart of an attitude optimization method for an autonomous vehicle according to an embodiment of this application. The method includes at least the following steps S110 to S140:

[0047] Step S110: Determine the current driving state of the autonomous vehicle, which includes both a moving state and a stationary state.

[0048] In this embodiment of the application, when optimizing the attitude of an autonomous vehicle, it is necessary to first determine the current driving state of the autonomous vehicle, such as whether it is in motion or stationary. Since there is a clear difference in the speed of an autonomous vehicle in motion and stationary states, the speed and other information can be combined to make the judgment.

[0049] Step S120: Determine the attitude optimization strategy corresponding to the current driving state based on the current driving state of the autonomous vehicle.

[0050] The attitude optimization method for autonomous vehicles in this application is mainly used to optimize the heading angle data originally output by the RTK positioning device on the autonomous vehicle. Since different driving states cause different deviations in the original heading angle data output by the RTK, different attitude optimization strategies need to be adopted for different driving states.

[0051] Step S130: Determine the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state.

[0052] Once the attitude optimization strategy corresponding to the current driving state is determined, the heading angle data output by the RTK can be optimized using the attitude optimization strategy corresponding to the current driving state to obtain the optimized heading angle data, which serves as the current heading angle observation data for the autonomous vehicle. This ensures the accuracy of the attitude observation data under different driving states, especially in the stationary state and the state just after switching from a stationary state to a moving state.

[0053] Step S140: Use a preset fusion algorithm to perform observation fusion on the current attitude observation data of the autonomous vehicle to obtain the current attitude fusion result of the autonomous vehicle.

[0054] After obtaining the optimized current attitude observation data, fusion algorithms such as Kalman filtering or extended Kalman filtering can be used to fuse the optimized current attitude observation data with other sensor data such as IMU data to obtain fused positioning results, which may include fused position and attitude data.

[0055] The attitude optimization method for autonomous vehicles in this application adopts different attitude optimization strategies for different driving states of autonomous vehicles, thereby optimizing the attitude observation data output by positioning devices such as RTK under different states, so as to obtain more accurate attitude observation data and improve the accuracy and stability of attitude fusion of autonomous vehicles.

[0056] In some embodiments of this application, determining the current driving state of the autonomous vehicle includes: acquiring the chassis speed and raw IMU data of the autonomous vehicle; and determining the current driving state of the autonomous vehicle based on the chassis speed and the raw IMU data.

[0057] Determining the current driving state of an autonomous vehicle can be based on two main factors: the vehicle's current chassis speed and the raw data from its IMU (Integrated Measurement Unit), primarily the angular velocity output by the gyroscope. If the vehicle's chassis speed remains below a certain threshold or is zero for a continuous period, and the variance of the gyroscope's output angular velocity is also below a certain variance threshold, then the vehicle can be judged to be stationary or parked. Conversely, if the speed is above a certain threshold, it can be judged to be in motion.

[0058] The reason for comprehensively judging the driving status of autonomous vehicles from the above two dimensions is that a judgment based on a single dimension is difficult to guarantee the accuracy of the driving status judgment. For example, if the vehicle is moving at high speed, the angular velocity variance may be less than a certain variance threshold. Therefore, the above judgment method can improve the accuracy of the driving status judgment, thereby providing a reliable basis for subsequent attitude optimization logic for different driving states.

[0059] In some embodiments of this application, determining the attitude optimization strategy corresponding to the current driving state based on the current driving state of the autonomous vehicle includes: when the current driving state of the autonomous vehicle is stationary, obtaining the attitude fusion result of the previous moment and determining the attitude optimization strategy corresponding to the stationary state based on the attitude fusion result of the previous moment; when the current driving state of the autonomous vehicle is in motion, determining the attitude optimization strategy corresponding to the motion state based on the attitude error determined when the autonomous vehicle switches from stationary to motion.

[0060] If the current driving state of the autonomous vehicle is determined to be stationary, then a corresponding attitude optimization strategy for the stationary state needs to be determined. Since the attitude of the autonomous vehicle does not change when stationary, the attitude optimization strategy corresponding to the stationary state can be determined based on the attitude fusion result of the previous moment.

[0061] If the current driving state is a moving state, then a corresponding attitude optimization strategy for the moving state needs to be determined. The moving state here mainly refers to the state of the autonomous vehicle during the short period immediately following its transition from a stationary state to a moving state. Therefore, in this embodiment, the heading angle error when the autonomous vehicle first switches from a stationary state to a moving state can be determined first. Specifically, the difference between the original RTK output heading angle yaw_RTK and the fused heading angle yaw_last from the previous moment can be used as the heading angle error dyaw. This heading angle error dyaw can be used to characterize the magnitude of the error in the original RTK output heading angle during the brief period immediately following the transition from a stationary state to a moving state. Based on this, the attitude optimization strategy for the period immediately following the transition from a stationary state to a moving state can be further determined.

[0062] In some embodiments of this application, the current driving state is the stationary state, and determining the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state includes: directly using the attitude fusion result of the previous moment as the current attitude observation data of the autonomous vehicle.

[0063] Since the heading angle of an autonomous vehicle does not change when stationary, if the current driving state of the autonomous vehicle is stationary, the fused heading angle information yaw_last output by the fusion algorithm at the previous moment can be directly obtained. Then, yaw_last can be used as the heading angle observation information in Kalman filtering or extended Kalman filtering. At the same time, the speed of 0 can also be used as the speed observation information for subsequent fusion, thereby improving the fusion positioning accuracy when stationary.

[0064] In some embodiments of this application, the current driving state is the motion state, and determining the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state includes: acquiring the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a motion state; and determining the current attitude observation data of the autonomous vehicle according to the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a motion state.

[0065] If the current driving state of the autonomous vehicle is in motion, the heading angle error determined when the autonomous vehicle switches from a stationary state to a moving state can be used to compensate and optimize the heading angle data of the original RTK output when it just enters the moving state, so as to obtain the corresponding attitude observation data.

[0066] Once the autonomous vehicle has entered a relatively stable state of motion, the heading angle error determined when switching from a stationary state to a moving state will have a reduced impact on the heading angle data output by the RTK. However, considering the smoothness of heading angle data processing during the switching between static and dynamic states, the heading angle error determined when switching from a stationary state to a moving state can still be used to compensate for the current heading angle data output by the RTK, but to a different degree than when it first entered the moving state. This is to ensure the stability of the heading angle fusion of the autonomous vehicle after the switching between static and dynamic states and to avoid abrupt changes.

[0067] In some embodiments of this application, determining the current attitude observation data of the autonomous vehicle based on the current RTK attitude data and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state includes: determining the time when the autonomous vehicle transitions from a stationary state to a moving state; if the time when the autonomous vehicle transitions from a stationary state to a moving state is within a preset time threshold, then the current attitude observation data of the autonomous vehicle is directly determined based on the current RTK attitude data and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state; if the time when the autonomous vehicle transitions from a stationary state to a moving state is not within the preset time threshold, then a preset attenuation strategy is used to attenuate the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, and the current attitude observation data of the autonomous vehicle is determined based on the attenuated attitude error and the current RTK attitude data.

[0068] As mentioned above, this application's embodiments divide the motion state into two cases: one is when the autonomous vehicle has just switched from a stationary state to a moving state, and the other is when it has entered a relatively stable motion state. These two cases can be distinguished by a pre-set time threshold. For example, the first case, i.e., the case where the autonomous vehicle has just switched from a stationary state to a moving state, can be considered as 3 seconds after the autonomous vehicle switches from a stationary state to a moving state, and the second case, i.e., the case where it has entered a relatively stable motion state, can be considered as 3 seconds after the autonomous vehicle switches from a stationary state to a moving state. Of course, the specific setting of the time threshold can be flexibly adjusted by those skilled in the art according to actual needs, and is not specifically limited here.

[0069] Based on this, timing begins when the autonomous vehicle is detected to be moving from a stationary state. If the preset time threshold has not yet been reached, it means that the autonomous vehicle has just entered a moving state. In this case, the heading angle currently output by the RTK can be obtained first, and then the heading angle observation data in this case can be obtained by using the heading angle ± heading angle error dyaw.

[0070] If the time it takes for the autonomous vehicle to enter a moving state has reached a preset time threshold, it indicates that the vehicle has entered a relatively stable moving state, and the RTK can stably output the corresponding heading angle data. In this case, the impact of the previously determined heading angle error (dyaw) on the heading angle data output by the RTK will be greatly reduced. However, if the heading angle currently output by the RTK is directly used as the observation value for subsequent fusion, large jumps may occur. Therefore, this embodiment can adopt a certain attenuation strategy to attenuate the heading angle error (dyaw), thereby enabling the autonomous vehicle to output relatively stable heading angle data after switching from a stationary state to a moving state, avoiding jumps.

[0071] The aforementioned attenuation strategy can, for example, set an attenuation coefficient α, such as 0.5 degrees / s, thus obtaining the current heading angle observation data = current RTK output heading angle ± α * heading angle error dyaw. Furthermore, the limits of dyaw can be constrained. For example, when dyaw < 0.05 degrees or greater than 2.5 degrees, it indicates that the influence of the heading angle error is very small, so dyaw can be directly set to 0.

[0072] In some embodiments of this application, after determining the current driving state of the autonomous vehicle, the method further includes: when the current driving state of the autonomous vehicle is stationary, setting the IMU prediction data in the preset fusion algorithm to the true value in the stationary state, and recording the original IMU data in the stationary state; determining IMU zero-bias data based on the original IMU data in the stationary state; and when the current driving state of the autonomous vehicle is in motion, acquiring the original IMU data in the motion state, and using the IMU zero-bias data to compensate for the original IMU data in the motion state.

[0073] Since the gyroscope will still represent the equivalent input angular rate as the average value of the output measured within a specified time when the autonomous vehicle is stationary, i.e., there is zero bias of the gyroscope, the accelerometer will also output a corresponding value, i.e., there is zero bias of the accelerometer. Therefore, the embodiments of this application can calculate the zero bias value of the IMU in a stationary state to improve the accuracy and stability of subsequent fusion positioning.

[0074] In a stationary state, the true values ​​in the IMU data used for filter prediction should be (0, 0, 0) for the gyroscope and (0, 0, g) for the accelerometer. Therefore, the IMU information in the filter can be directly set using these true values. At this time, the raw output of the IMU represents the magnitude of the zero bias of the gyroscope and the zero bias of the accelerometer.

[0075] After obtaining the zero-bias data from the IMU, when the autonomous vehicle enters a moving state, the zero-bias data from the IMU can be used to compensate for the raw output of the IMU, thereby improving the accuracy of the IMU data and thus improving the fusion positioning accuracy.

[0076] This application also provides an attitude optimization device 200 for an autonomous vehicle, such as... Figure 2 The diagram shows a schematic representation of an attitude optimization device for an autonomous vehicle according to an embodiment of this application. The device 200 includes: a first determining unit 210, a second determining unit 220, a third determining unit 230, and a fusion unit 240, wherein:

[0077] The first determining unit 210 is used to determine the current driving state of the autonomous vehicle, the current driving state including a moving state and a stationary state;

[0078] The second determining unit 220 is used to determine the attitude optimization strategy corresponding to the current driving state based on the current driving state of the autonomous vehicle.

[0079] The third determining unit 230 is used to determine the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state.

[0080] The fusion unit 240 is used to perform observation fusion on the current attitude observation data of the autonomous vehicle using a preset fusion algorithm to obtain the current attitude fusion result of the autonomous vehicle.

[0081] In some embodiments of this application, the first determining unit 210 is specifically configured to: acquire the chassis speed and IMU raw data of the autonomous vehicle; and determine the current driving state of the autonomous vehicle based on the chassis speed and the IMU raw data.

[0082] In some embodiments of this application, the second determining unit 220 is specifically used to: when the current driving state of the autonomous vehicle is stationary, obtain the attitude fusion result of the previous moment and determine the attitude optimization strategy corresponding to the stationary state based on the attitude fusion result of the previous moment; when the current driving state of the autonomous vehicle is in motion, determine the attitude optimization strategy corresponding to the motion state based on the attitude error determined when the autonomous vehicle switches from stationary state to motion state.

[0083] In some embodiments of this application, the current driving state is the stationary state, and the third determining unit 230 is specifically used to: directly use the attitude fusion result of the previous moment as the current attitude observation data of the autonomous vehicle.

[0084] In some embodiments of this application, the current driving state is the motion state, and the third determining unit 230 is specifically used to: acquire the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a motion state; and determine the current attitude observation data of the autonomous vehicle based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a motion state.

[0085] In some embodiments of this application, the third determining unit 230 is specifically used to: determine the time when the autonomous vehicle transitions from a stationary state to a moving state; if the time when the autonomous vehicle transitions from a stationary state to a moving state is within a preset time threshold, then directly determine the current attitude observation data of the autonomous vehicle based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state; if the time when the autonomous vehicle transitions from a stationary state to a moving state is not within the preset time threshold, then use a preset attenuation strategy to attenuate the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, and determine the current attitude observation data of the autonomous vehicle based on the attenuated attitude error and the RTK attitude data at the current moment.

[0086] In some embodiments of this application, the apparatus further includes: a setting unit, configured to set the IMU prediction data in the preset fusion algorithm to the true value in the static state when the current driving state of the autonomous vehicle is stationary, and record the original IMU data in the static state; a fourth determining unit, configured to determine IMU zero-bias data based on the original IMU data in the static state; and a compensation unit, configured to acquire the original IMU data in the moving state when the current driving state of the autonomous vehicle is in motion, and compensate the original IMU data in the moving state using the IMU zero-bias data.

[0087] It is understood that the above-mentioned attitude optimization device for autonomous vehicles can implement each step of the attitude optimization method for autonomous vehicles provided in the foregoing embodiments. The relevant explanations of the attitude optimization method for autonomous vehicles are applicable to the attitude optimization device for autonomous vehicles, and will not be repeated here.

[0088] 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 3 At 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.

[0089] 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.

[0090] 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.

[0091] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming the attitude optimization device for the autonomous vehicle at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0092] Determine the current driving state of the autonomous vehicle, which includes both a moving state and a stationary state;

[0093] Based on the current driving state of the autonomous vehicle, determine the attitude optimization strategy corresponding to the current driving state;

[0094] The current attitude observation data of the autonomous vehicle is determined based on the attitude optimization strategy corresponding to the current driving state;

[0095] The current attitude observation data of the autonomous vehicle is fused using a preset fusion algorithm to obtain the current attitude fusion result of the autonomous vehicle.

[0096] The above is as stated in this application. Figure 1 The method for optimizing the attitude of an autonomous vehicle disclosed in the illustrated embodiments 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 in the execution of 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.

[0097] The electronic device can also perform Figure 1 A method for implementing the attitude optimization device in an autonomous vehicle, and how to realize the attitude optimization device in an autonomous vehicle. Figure 1 The functions of the embodiments shown are not described in detail here.

[0098] 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 attitude optimization device of the autonomous vehicle in the illustrated embodiment is specifically used to perform:

[0099] Determine the current driving state of the autonomous vehicle, which includes both a moving state and a stationary state;

[0100] Based on the current driving state of the autonomous vehicle, determine the attitude optimization strategy corresponding to the current driving state;

[0101] The current attitude observation data of the autonomous vehicle is determined based on the attitude optimization strategy corresponding to the current driving state;

[0102] The current attitude observation data of the autonomous vehicle is fused using a preset fusion algorithm to obtain the current attitude fusion result of the autonomous vehicle.

[0103] 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.

[0104] 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 1A device that provides the functions specified in one or more boxes.

[0105] 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.

[0106] 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.

[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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 posture optimization method for an autonomous vehicle, wherein, The method includes: Determine the current driving state of the autonomous vehicle, which includes both a moving state and a stationary state; Based on the current driving state of the autonomous vehicle, determine the attitude optimization strategy corresponding to the current driving state; The current attitude observation data of the autonomous vehicle is determined based on the attitude optimization strategy corresponding to the current driving state; The current attitude observation data of the autonomous vehicle is fused using a preset fusion algorithm to obtain the current attitude fusion result of the autonomous vehicle. The current driving state is the motion state, and determining the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state includes: Acquire the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state; Based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, the current attitude observation data of the autonomous vehicle is determined. The step of determining the current attitude observation data of the autonomous vehicle based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state includes: Determine the time when the autonomous vehicle transitions from a stationary state to a moving state; If the time it takes for the autonomous vehicle to transition from a stationary state to a moving state is within a preset time threshold, then the current attitude observation data of the autonomous vehicle is determined directly based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state. If the time it takes for the autonomous vehicle to transition from a stationary state to a moving state is not within the preset time threshold, a preset attenuation strategy is used to attenuate the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, and the current attitude observation data of the autonomous vehicle is determined based on the attenuated attitude error and the RTK attitude data at the current moment.

2. The method as described in claim 1, wherein, Determining the current driving status of the autonomous vehicle includes: Acquire the chassis speed and raw IMU data of autonomous vehicles; The current driving state of the autonomous vehicle is determined based on the vehicle chassis speed and the raw IMU data.

3. The method as described in claim 1, wherein, The step of determining the attitude optimization strategy corresponding to the current driving state based on the current driving state of the autonomous vehicle includes: When the current driving state of the autonomous vehicle is stationary, the attitude fusion result of the previous moment is obtained and the attitude optimization strategy corresponding to the stationary state is determined based on the attitude fusion result of the previous moment. If the current driving state of the autonomous vehicle is in motion, then the attitude optimization strategy corresponding to the motion state is determined based on the attitude error determined when the autonomous vehicle switches from a stationary state to a motion state.

4. The method as described in claim 1, wherein, The current driving state is the stationary state, and the step of determining the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state includes: The attitude fusion result from the previous moment is directly used as the current attitude observation data of the autonomous vehicle.

5. The method as described in claim 1, wherein, After determining the current driving state of the autonomous vehicle, the method further includes: When the current driving state of the autonomous vehicle is stationary, the IMU prediction data in the preset fusion algorithm is set as the true value in the stationary state, and the original IMU data in the stationary state is recorded. IMU zero bias data are determined based on the raw IMU data in the static state; When the current driving state of the autonomous vehicle is in motion, the raw IMU data in motion state is acquired, and the IMU zero-bias data is used to compensate for the raw IMU data in motion state.

6. An attitude optimization device for an autonomous vehicle, wherein, The device includes: The first determining unit is used to determine the current driving state of the autonomous vehicle, the current driving state including a moving state and a stationary state; The second determining unit is used to determine the attitude optimization strategy corresponding to the current driving state based on the current driving state of the autonomous vehicle. The third determining unit is used to determine the current attitude observation data of the autonomous vehicle according to the attitude optimization strategy corresponding to the current driving state. The fusion unit is used to perform observation fusion on the current attitude observation data of the autonomous vehicle using a preset fusion algorithm to obtain the current attitude fusion result of the autonomous vehicle. The current driving state is the motion state, and the third determining unit is specifically used for: Acquire the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state; Based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, the current attitude observation data of the autonomous vehicle is determined. The third determining unit is specifically used for: Determine the time when the autonomous vehicle transitions from a stationary state to a moving state; If the time it takes for the autonomous vehicle to transition from a stationary state to a moving state is within a preset time threshold, then the current attitude observation data of the autonomous vehicle is determined directly based on the RTK attitude data at the current moment and the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state. If the time it takes for the autonomous vehicle to transition from a stationary state to a moving state is not within the preset time threshold, a preset attenuation strategy is used to attenuate the attitude error determined when the autonomous vehicle switches from a stationary state to a moving state, and the current attitude observation data of the autonomous vehicle is determined based on the attenuated attitude error and the RTK attitude data at the current moment.

7. 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 5.

8. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 5.

Images