Autonomous driving vehicle fusion positioning method and related device for tunnels

Abstract

This application discloses a fusion positioning method and related devices for autonomous driving vehicles in tunnels, wherein the method includes obtaining SLAM map data in the tunnel before entering the tunnel; after entering the tunnel, obtaining laser SLAM positioning information and visual SLAM positioning information based on the SLAM map data in the tunnel; determining the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information; determining the fusion positioning result at the current moment based on the combined positioning information of IMU and RTK at the previous moment, the visual longitudinal correction information offset parameter, and the laser lateral correction information offset parameter; and calculating the vehicle's current position information based on the fusion positioning result at the current moment. This application achieves high-precision positioning in tunnel scenarios.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method for fusion positioning of autonomous driving vehicles in tunnels and related devices. Background Art

[0002] The positioning technology of autonomous vehicles is mainly based on combined navigation. Through a Kalman filter, low-frequency GNSS / RTK signals and high-frequency IMU information are integrated to output high-frequency, high-precision positioning information.

[0003] In related technologies, autonomous driving fusion positioning solutions typically rely on inertial navigation (IMU) and real-time tracking (RTK). However, in tunnels and other working conditions, RTK can be disrupted or lose signal, rendering it inoperable. MEMS IMU and RTK systems are unable to provide high-precision positioning information. Laser SLAM (Laser SLAM) provides good positioning in areas with a large number of feature points. However, due to the lack of features on open roads, positioning degrades and fails, especially in tunnels. Using any of these features alone during autonomous driving cannot achieve high-precision positioning. Summary of the Invention

[0004] The embodiments of the present application provide a fusion positioning method and related devices for autonomous driving vehicles in tunnels to provide high-precision positioning in tunnel scenarios.

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

[0006] In the first aspect, an embodiment of the present application provides a fusion positioning method for an autonomous driving vehicle in a tunnel, wherein the method includes: before entering the tunnel, obtaining SLAM map data in the tunnel; after entering the tunnel, obtaining laser SLAM positioning information and visual SLAM positioning information based on the SLAM map data in the tunnel; determining the laser lateral correction information offset parameters corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameters corresponding to the visual SLAM positioning information; determining the fusion positioning result at the current moment based on the combined positioning information of IMU and RTK at the previous moment, the visual longitudinal correction information offset parameters and the laser lateral correction information offset parameters; and calculating the current position information of the vehicle based on the fusion positioning result at the current moment.

[0007] In the second aspect, an embodiment of the present application also provides a fusion positioning device for an autonomous driving vehicle in a tunnel, wherein the device is used for an autonomous driving vehicle and includes: a map acquisition module for acquiring SLAM map data in the tunnel before entering the tunnel; a positioning information acquisition module for acquiring laser SLAM positioning information and visual SLAM positioning information according to the SLAM map data in the tunnel after entering the tunnel; an offset determination module for determining the laser lateral correction information offset parameters corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameters corresponding to the visual SLAM positioning information; a fusion positioning module for determining the fusion positioning result at the current moment based on the combined positioning information of IMU and RTK at the previous moment, the visual longitudinal correction information offset parameters and the laser lateral correction information offset parameters; a position determination module for calculating the current position information of the vehicle based on the fusion positioning result at the current moment.

[0008] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein the executable instructions, when executed, enable the processor to perform the above method.

[0009] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.

[0010] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0011] After entering a tunnel, the system acquires laser SLAM positioning information and visual SLAM positioning information based on the SLAM map data within the tunnel. It then determines the laser lateral correction information offset parameters corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameters corresponding to the visual SLAM positioning information. Finally, the current fused positioning result is determined based on the combined IMU and RTK positioning information from the previous moment, the visual longitudinal correction information offset parameters, and the laser lateral correction information offset parameters. This allows for fused positioning optimization in tunnel scenarios by combining relevant SLAM positioning information. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0013] Figure 1Schematic diagram of the flow of the fusion positioning method for an autonomous driving vehicle in a tunnel according to an embodiment of the present application;

[0014] Figure 2 This is a schematic diagram of the structure of a fusion positioning device for an autonomous driving vehicle used in a tunnel in an embodiment of the present application;

[0015] Figure 3 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0016] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] The fusion positioning method for autonomous vehicles in tunnels, described in this application, is based on fusion positioning optimization based on laser and visual SLAM correction information, and can be used for fusion positioning in tunnel conditions. Furthermore, based on the attributes of map SLAM data, inaccurate longitudinal positioning information from laser SLAM is eliminated and new observation information is constructed in combination with the visual longitudinal positioning information.

[0018] In addition, the entry and exit mechanism (tunnel state 2) is optimized in this application to ensure the smoothness and stability of fusion positioning.

[0019] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0020] The embodiment of the present application provides a fusion positioning method for an autonomous driving vehicle in a tunnel, such as Figure 1 As shown, a flow chart of a method for fusion positioning of an autonomous driving vehicle in a tunnel according to an embodiment of the present application is provided. The method includes at least the following steps S110 to S140:

[0021] Step S110: Before entering the tunnel, obtain SLAM map data in the tunnel.

[0022] Before entering a tunnel, an autonomous vehicle acquires the tunnel's SLAM map data. Understandably, this data is often large, making it impossible to load and cache it in real time or in its entirety within the autonomous vehicle. This SLAM map data is typically stored in the cloud.

[0023] Furthermore, before entering the tunnel, the vehicle's position needs to be determined based on the combined positioning information of IMU and RTK, and the timing of sending a request to the cloud is determined based on the vehicle's position.

[0024] Step S120: After entering the tunnel, laser SLAM positioning information and visual SLAM positioning information are obtained according to the SLAM map data in the tunnel.

[0025] After the autonomous driving vehicle enters the tunnel, the laser SLAM positioning information and the visual SLAM positioning information are obtained based on the SLAM map data (high-precision map data) in the tunnel obtained from the cloud.

[0026] It should be noted that each point cloud data in the laser SLAM positioning information has an offset and a corresponding timestamp. Due to the data refresh frequency, there is usually a 70 to 100ms delay.

[0027] Each feature point in the visual SLAM positioning information has an offset and a corresponding timestamp. Due to the data refresh rate, there is usually a 70 to 100ms delay.

[0028] Furthermore, due to the presence of delay, it is necessary to find corresponding timestamps in two dimensions (laser and visual). Those skilled in the art can achieve alignment of timestamps using relevant technical means and obtain the location information of the cache corresponding to the target timestamp.

[0029] Step S130 , determining the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information.

[0030] Determine the offset parameters of the laser lateral correction information corresponding to the laser SLAM positioning information. Considering that the laser longitudinal information in the tunnel scene is degraded due to the lack of features (the tunnel scene lacks features and degrades). Therefore, the offset parameters of the laser lateral correction information corresponding to the laser SLAM positioning information are obtained.

[0031] Determine the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information. Considering that the visual horizontal direction is fixed in the tunnel scene, the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information is obtained.

[0032] It should be noted that the offset parameter for the laser lateral correction information is the offset in the navigation coordinate system (usually the northeast celestial coordinate). Similarly, the offset parameter for the visual longitudinal correction information is the offset in the navigation coordinate system (usually the northeast celestial coordinate).

[0033] In addition, the attenuation factor needs to be considered to ensure smooth offset calculation.

[0034] Step S140 , determining the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameter of the visual longitudinal correction information, and the offset parameter of the laser lateral correction information.

[0035] In order to achieve fused positioning in a tunnel, it is necessary to determine the current fused positioning result based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameters of the visual longitudinal correction information, and the offset parameters of the laser lateral correction information. In other words, fused positioning is performed based on the optimized laser SLAM method lateral correction information and the SLAM visual longitudinal correction information.

[0036] Furthermore, it is also necessary to judge the combined positioning information of the IMU and RTK in real time to determine whether the autonomous driving vehicle has exited the tunnel.

[0037] Get the fused inertial navigation RTK positioning information posx1, posy1, posz1 corresponding to the current time1

[0038] Posx1=Posx+dx+dx1

[0039] Posy1=Posy+dy+dy1

[0040] Posz1=Posy+dz+dz1

[0041] Posx, Posy, Posy are the current position information

[0042] Step S150: Calculate the current position information of the vehicle based on the fused positioning result at the current moment.

[0043] The fused positioning result at the current moment is used as a new measurement value to update the measurement value of the Kalman filter to obtain high-precision fused positioning information.

[0044] In one embodiment of the present application, the determination of the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information also includes: if the laser SLAM positioning information is not received within the first preset time period, the laser lateral correction information offset parameter is set to zero; if the laser SLAM positioning information is received within the second preset time period, the attenuated laser lateral correction information offset parameter is calculated according to the first attenuation factor, wherein the first preset time period is greater than the duration of the second preset time period; and the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information also includes: if the visual SLAM positioning information is not received within the third preset time period, the visual longitudinal correction information offset parameter is set to zero; if the visual SLAM positioning information is received within the fourth preset time period, the attenuated visual longitudinal correction information offset parameter is calculated according to the second attenuation factor, wherein the third preset time period is greater than the duration of the fourth preset time period.

[0045] In a specific implementation, determining the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information also includes the following steps:

[0046] If laser SLAM positioning information is received within a second preset time period, the offset parameters of the attenuated laser lateral correction information are calculated based on the first attenuation factor, where the second preset time period is longer than the first preset time period. If laser SLAM correction information is still not obtained within a certain period of time, the offset after attenuation is calculated. For example, if laser correction information is not obtained within 1 second, the offsets dx, dy, and dz after attenuation are calculated.

[0047] For example, calculate the offset dx, dy, dz of the radar lateral correction information in the navigation coordinate system (usually northeast sky),

[0048] dx=timex lidar posx-timex rtk posx

[0049] dy=timex lidar posy-timex rtk posy

[0050] dz=timex lidar posz-timex rtk posz

[0051] For example, calculate the attenuation factor lidar_k

[0052] For example, if no laser calibration information is obtained within 1 second, the offset dx, dy, dz after attenuation is calculated:

[0053]

[0054]

[0055] Similarly, calculate dx1, dy1, and dz1. If no laser calibration information is obtained within 3 seconds, calculate the offsets dx, dy, and dz after attenuation.

[0056] If no laser SLAM positioning information is received within the first preset time period, the laser lateral correction information offset parameters are set to zero. For another example, if no laser SLAM correction information is obtained for more than 4 seconds, the offsets dx, dy, and dz are set to 0. Similarly, for the visual SLAM correction information dx1, dy1, and dz1. If no visual correction information is obtained within 6 seconds, the offsets dx1, dy1, and dz1 are set to 0:

[0057] It should be noted that the first preset time period, the second preset time period, and the third preset time period are only used as descriptions of the time itself and are not used to limit their order or the order in which they are executed. Specifically, determining the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information also includes:

[0058] If laser SLAM positioning information is received within a second preset time period, the offset parameter of the attenuated laser lateral correction information is calculated according to the first attenuation factor, wherein the first preset time period is longer than the second preset time period, for example, no laser SLAM correction information is obtained within 1 second.

[0059] If no laser SLAM positioning information is received within the first preset time period, the laser lateral correction information offset parameter is set to zero. For example, if no laser SLAM correction information is obtained within 4 seconds.

[0060] If no laser SLAM positioning information is received within the first preset time period, the laser lateral correction information offset parameters are reset to zero. That is, when determining the laser lateral correction information offset parameters, if no laser SLAM correction information is received after a certain period of time, the offset is set to 0. For example, if no laser SLAM correction information is received for more than 4 seconds, the offsets dx, dy, and dz are set to 0. Similarly, dx1, dy1, and dz1 are calculated.

[0061] If laser SLAM positioning information is received within a second preset time period, the offset parameters of the attenuated laser lateral correction information are calculated based on the first attenuation factor, where the second preset time period is longer than the first preset time period. If laser SLAM correction information is still not obtained within a certain period of time, the offset after attenuation is calculated. For example, if laser correction information is not obtained within 1 second, the offsets dx, dy, and dz after attenuation are calculated. Similarly, dx1, dy1, and dz1 are calculated.

[0062] For example, calculate the offset dx, dy, dz of the radar lateral correction information in the navigation coordinate system (usually northeast sky),

[0063] dx=timex lidar posx-timex rtk posx

[0064] dy=timex lidar posy-timex rtk posy

[0065] dz=timex lidar posz-timex rtk posz

[0066] For example, calculate the attenuation factor lidar_k

[0067] lidar_k[0]=dx() / 100.0;

[0068] lidar_k[1]=dy() / 100.0;

[0069] lidar_k[2] = dy() / 100.0;

[0070] If no visual SLAM positioning information is received within a third preset time period, the visual longitudinal correction information offset parameter is set to zero. If visual SLAM positioning information is received within a fourth preset time period, the attenuated visual longitudinal correction information offset parameter is calculated based on the second attenuation factor, where the third preset time period is longer than the fourth preset time period. The laser lateral correction information offset parameter for the laser SLAM lateral correction information is calculated similarly.

[0071] It should be noted that the above calculation process is performed in real time and in parallel.

[0072] In one embodiment of the present application, before determining the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the visual longitudinal correction information offset parameter, and the laser lateral correction information offset parameter, it also includes: based on the SLAM map data in the tunnel, obtaining the lateral offset information in the laser SLAM positioning information and the timestamp information corresponding to each lateral offset; based on the SLAM map data in the tunnel, obtaining the longitudinal offset information in the visual SLAM positioning information and the timestamp information corresponding to each longitudinal offset; traversing the timestamps of the vehicle position information cached within a preset time period, and when the error between the timestamp of the vehicle position information and the timestamp information corresponding to the longitudinal or lateral offset meets the preset conditions, determining the cached vehicle position information corresponding to the target timestamp at the current moment, wherein the vehicle position is obtained based on the combined positioning information of the IMU and RTK.

[0073] In specific implementations, the timestamps of the vehicle location information cached within a preset time period are traversed. When the error between the timestamp of the vehicle location information and the timestamp corresponding to the longitudinal or lateral offset meets a preset condition, the cached vehicle location information corresponding to the current target timestamp is determined. To determine the target timestamp, the timestamp time and SLAM timestamp time0 cached within 1s can be traversed. When the absolute value |time-time0| is less than 0.005s, the cached location information corresponding to the current timex is recorded.

[0074] In one embodiment of the present application, the calculation of the vehicle's current position information based on the fused positioning result at the current moment also includes: judging whether the autonomous driving vehicle uses the combined positioning information of IMU and RTK based on the number of GPS satellites and the differential information positioning status in the fused positioning result at the current moment.

[0075] During specific implementation, in order to determine whether it is still in the tunnel, it is also necessary to determine whether the current autonomous driving vehicle can use the combined positioning information of IMU and RTK for high-precision positioning based on the number of GPS satellites and the differential information positioning status in the fused positioning result at the current moment.

[0076] That is, by judging whether the number of GPS satellites is greater than 20 and the differential state is 42 (that is, the differential signal is good and can be used for high-precision positioning), the sensor count lidar_num_cnt is started.

[0077] If the sensor count lidar_num_cnt is greater than 300, the laser lateral offset dx, dy, dz is set to 0, and the visual longitudinal offset dx1, dy1, dz1 is set to 0. Otherwise, no SLAM offset correction is performed, and the original normal SLAM positioning information is used.

[0078] In one embodiment of the present application, it also includes: before entering the tunnel, obtaining SLAM map data in the tunnel through the cloud; and after entering the tunnel, obtaining laser SLAM positioning information based on the SLAM map data in the tunnel and the point cloud data collected in real time; and obtaining the visual SLAM positioning information based on the SLAM map data in the tunnel and the real-time identification of road sign information.

[0079] In a specific implementation, after entering the tunnel, the high-precision positioning information of the autonomous vehicle obtained by the combined positioning of IMU and RTK for a preset duration is cached in real time through a double-ended queue. It is understood that the preset duration can be positioning information within 1 second. At this time, since the data refresh frequency is 100 Hz, 100 positioning point information is obtained. That is, the positioning information of the autonomous vehicle (UTM / WGS84 coordinates and corresponding timestamp) for 1 second is cached in real time through the deque double-ended queue.

[0080] It should be noted that the positioning information here is the combined positioning information of IMU and RTK.

[0081] In one embodiment of the present application, after entering the tunnel, laser SLAM positioning information and visual SLAM positioning information are obtained based on the SLAM map data in the tunnel, including: after entering the tunnel, high-precision positioning information of the autonomous driving vehicle obtained by combined positioning of IMU and RTK within a preset time period is cached in real time through a double-ended queue; based on the SLAM map data in the tunnel, the laser SLAM positioning information and visual SLAM positioning information are obtained, wherein the laser SLAM positioning information has a preset delay time relative to the preset time period, and the visual SLAM positioning information has a preset delay time within the preset time period; the laser SLAM positioning information is converted into a northeast celestial rectangular coordinate system according to the current tunnel working condition information, wherein the initial value of the laser SLAM on the vehicle body lateral information is 0.

[0082] In specific implementation, after entering the tunnel, the high-precision positioning information of the autonomous driving vehicle obtained by the combined positioning of IMU and RTK within a preset time period is cached in real time through a double-ended queue. Then, based on the SLAM map data in the tunnel, the laser SLAM positioning information and the visual SLAM positioning information are obtained. Thereafter, the laser SLAM positioning information is converted into the northeast celestial rectangular coordinate system according to the current tunnel working condition information.

[0083] Obtain the laser positioning status. If it is "2 (Tunnel)", set the laser SLAM vehicle lateral information to 0. For example, in the vehicle coordinate system xyz (front upper left), set y = 0. Based on the conversion relationship, convert the laser xyz information to the Northeast Celestial coordinate system. Similarly, the visual positioning status can be obtained.

[0084] In one embodiment of the present application, before entering the tunnel, SLAM map data in the tunnel is obtained, which also includes: pre-establishing SLAM map data in the tunnel for the tunnel and uploading it to the cloud, wherein the SLAM map data in the tunnel is marked as a tunnel state; according to the combined positioning information of IMU and RTK, a map acquisition request is sent to the cloud before entering the tunnel, wherein the map acquisition request carries the tunnel state; the autonomous driving vehicle is positioned according to the received SLAM map data in the tunnel sent from the cloud, and the tunnel state is synchronized to the cloud.

[0085] In a specific implementation, in order to reduce the memory usage of the autonomous vehicle, SLAM map data of the tunnel is created in advance and uploaded to the cloud. Then, based on the combined positioning information of IMU and RTK, a map acquisition request is sent to the cloud before entering the tunnel. Finally, the autonomous vehicle is positioned based on the received SLAM map data of the tunnel sent from the cloud, and the tunnel status is synchronized to the cloud.

[0086] It should be noted that the state of the SLAM map data in the tunnel is marked as the tunnel state, and the map acquisition request carries the tunnel state.

[0087] Using IMU and RTK positioning information as prior factors, combined with laser SLAM factors, we optimize the factor graph to build SLAM tunnel maps. At the same time, we need to mark the map with the attribute "2 (tunnel)".

[0088] Before entering the tunnel, when the differential status is 42 (RTK differential status is good), positioning information is obtained and sent to the cloud. The cloud then sends the corresponding tunnel SLAM map to the vehicle (only part of the tunnel SLAM map data).

[0089] When entering the tunnel, the vehicle performs SLAM positioning, sends the positioning information in the vehicle coordinate system to the fusion positioning node in real time, and sends the status "2 (tunnel)".

[0090] In one embodiment of the present application, preferably, for the current scenario where the autonomous driving vehicle is traveling at high speed, in order to further improve the positioning effect of the autonomous driving vehicle when traveling at high speed, a plurality of frames of laser / visual correction information obtained within a period of time can be fitted, and at least 5 consecutive frames of laser / visual correction information can be obtained. Then, these at least 5 frames of laser / visual correction information are fitted to obtain a fitting equation, and finally, the fitting equation is used to predict the laser / visual correction information at the current moment, thereby compensating for the error problem of the laser / visual correction information caused by the autonomous driving vehicle traveling at high speed.

[0091] The embodiment of the present application also provides a fusion positioning device 200 for an autonomous driving vehicle in a tunnel, such as Figure 2 As shown, a schematic diagram of the structure of a fusion positioning device for an autonomous driving vehicle in a tunnel according to an embodiment of the present application is provided. The fusion positioning device 200 for an autonomous driving vehicle in a tunnel includes at least: a map acquisition module 210, a positioning information acquisition module 220, an offset determination module 230, a fusion positioning module 240, and a position determination module 250, wherein:

[0092] The map acquisition module 210 is used to obtain SLAM map data in the tunnel before entering the tunnel;

[0093] A positioning information acquisition module 220 is used to acquire laser SLAM positioning information and visual SLAM positioning information according to the SLAM map data in the tunnel after entering the tunnel;

[0094] An offset determination module 230 is configured to determine an offset parameter of the laser lateral correction information corresponding to the laser SLAM positioning information and an offset parameter of the visual longitudinal correction information corresponding to the visual SLAM positioning information;

[0095] The fusion positioning module 240 is used to determine the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameter of the visual longitudinal correction information, and the offset parameter of the laser lateral correction information;

[0096] The position determination module 250 is used to calculate the current position information of the vehicle based on the fused positioning result at the current moment.

[0097] In one embodiment of the present application, the map acquisition module 210 is specifically configured to:

[0098] In one embodiment of the present application, the map acquisition module 210 is specifically configured to acquire SLAM map data for the tunnel before the autonomous vehicle enters it. It is understood that SLAM map data is typically large and cannot be loaded in real time or in its entirety into the autonomous vehicle. This SLAM map data is typically stored in the cloud.

[0099] Furthermore, before entering the tunnel, the vehicle's position needs to be determined based on the combined positioning information of IMU and RTK, and the timing of sending a request to the cloud is determined based on the vehicle's position.

[0100] In one embodiment of the present application, the positioning information acquisition module 220 is specifically used to: after the autonomous driving vehicle enters the tunnel, obtain the laser SLAM positioning information and the visual SLAM positioning information based on the SLAM map data (high-precision map data) in the tunnel obtained from the cloud.

[0101] It should be noted that each point cloud data in the laser SLAM positioning information has an offset and a corresponding timestamp. Due to the data refresh frequency, there is usually a 70 to 100ms delay.

[0102] Each feature point in the visual SLAM positioning information has an offset and a corresponding timestamp. Due to the data refresh rate, there is usually a 70 to 100ms delay.

[0103] Furthermore, due to the presence of delay, it is necessary to find corresponding timestamps in two dimensions (laser and visual). Those skilled in the art can achieve alignment of timestamps using relevant technical means and obtain the location information of the cache corresponding to the target timestamp.

[0104] In one embodiment of the present application, the offset determination module 230 is specifically configured to determine an offset parameter of the laser lateral correction information corresponding to the laser SLAM positioning information. Considering that the laser longitudinal information in a tunnel scenario is degraded due to missing features, the offset parameter of the laser lateral correction information corresponding to the laser SLAM positioning information is obtained.

[0105] Determine the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information. Considering that the visual horizontal direction is fixed in the tunnel scene, the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information is obtained.

[0106] It should be noted that the offset parameter for the laser lateral correction information is the offset in the navigation coordinate system (usually the northeast celestial coordinate). Similarly, the offset parameter for the visual longitudinal correction information is the offset in the navigation coordinate system (usually the northeast celestial coordinate).

[0107] In addition, the attenuation factor needs to be considered to ensure smooth offset calculation.

[0108] In one embodiment of the present application, the fusion positioning module 240 is specifically configured to: In order to achieve fusion positioning in a tunnel, it is necessary to determine the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameters of the visual longitudinal correction information, and the offset parameters of the laser lateral correction information. In other words, fusion positioning is performed based on the optimized laser SLAM method lateral correction information and the SLAM visual longitudinal correction information.

[0109] Furthermore, it is also necessary to judge the combined positioning information of the IMU and RTK in real time to determine whether the autonomous driving vehicle has exited the tunnel.

[0110] Get the fused inertial navigation RTK positioning information posx1, posy1, posz1 corresponding to the current time1.

[0111] Posx1=Posx+dx+dx1

[0112] Posy1=Posy+dy+dy1

[0113] Posz1=Posy+dz+dz1

[0114] Posx, Posy, Posy are the current position information

[0115] In one embodiment of the present application, the position determination module 250 is specifically configured to update the measurement value of the Kalman filter based on the fusion positioning result at the current moment as a new measurement value to obtain high-precision fusion positioning information.

[0116] It can be understood that the above-mentioned autonomous driving vehicle fusion positioning device for tunnels can implement the various steps of the autonomous driving vehicle fusion positioning method for tunnels provided in the aforementioned embodiments. The relevant explanations on the autonomous driving vehicle fusion positioning method for tunnels are applicable to the autonomous driving vehicle fusion positioning device for tunnels and will not be repeated here.

[0117] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal 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 its services.

[0118] 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. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0119] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0120] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a fusion positioning device for autonomous driving vehicles in tunnels at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0121] Before entering the tunnel, obtain the SLAM map data inside the tunnel;

[0122] After entering the tunnel, the laser SLAM positioning information and the visual SLAM positioning information are obtained according to the SLAM map data in the tunnel;

[0123] Determine the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information;

[0124] Determine the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameter of the visual longitudinal correction information, and the offset parameter of the laser lateral correction information;

[0125] The current position information of the vehicle is calculated based on the fused positioning result at the current moment.

[0126] The above application Figure 1The method disclosed in the illustrated embodiment for a fusion positioning device for an autonomous vehicle in a tunnel can be applied to 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 hardware integrated logic circuits in the processor or by software instructions. The above 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 various 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 conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0127] The electronic device may also perform Figure 1 A method for implementing a fusion positioning device for an autonomous driving vehicle in a tunnel, and realizing a fusion positioning device for an autonomous driving vehicle in a tunnel Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0128] The embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, can enable the electronic device to execute Figure 1 The method performed by the fusion positioning device for an autonomous driving vehicle in a tunnel in the embodiment shown is specifically used to perform:

[0129] Before entering the tunnel, obtain the SLAM map data inside the tunnel;

[0130] After entering the tunnel, the laser SLAM positioning information and the visual SLAM positioning information are obtained according to the SLAM map data in the tunnel;

[0131] Determine the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information;

[0132] Determine the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameter of the visual longitudinal correction information, and the offset parameter of the laser lateral correction information;

[0133] The current position information of the vehicle is calculated based on the fused positioning result at the current moment.

[0134] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0136] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0137] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0138] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0139] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0140] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0141] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0142] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included within the scope of the claims of the present application.

Claims

1. A fusion positioning method for autonomous driving vehicles in tunnels, wherein: The method comprises: Before entering the tunnel, obtain the SLAM map data inside the tunnel; After entering the tunnel, the laser SLAM positioning information and the visual SLAM positioning information are obtained according to the SLAM map data in the tunnel; Determine the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information and the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information; Determine the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameter of the visual longitudinal correction information, and the offset parameter of the laser lateral correction information; Before determining the fused positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the visual longitudinal correction information offset parameter, and the laser lateral correction information offset parameter, the method further includes: Based on the SLAM map data in the tunnel, obtaining lateral offset information in the laser SLAM positioning information and timestamp information corresponding to each lateral offset; Based on the SLAM map data in the tunnel, obtaining longitudinal offset information in the visual SLAM positioning information and timestamp information corresponding to each longitudinal offset; Traversing the timestamps of vehicle position information cached within a preset time period, and determining the cached vehicle position information corresponding to the target timestamp at the current moment when an error between the timestamp of the vehicle position information and the timestamp information corresponding to the longitudinal or lateral offset satisfies a preset condition, wherein the vehicle position is obtained based on the combined positioning information of the IMU and RTK; The current position information of the vehicle is calculated based on the fused positioning result at the current moment.

2. The method according to claim 1, wherein: Determining the laser lateral correction information offset parameter corresponding to the laser SLAM positioning information also includes: If no laser SLAM positioning information is received within the first preset time period, the laser lateral correction information offset parameter is set to zero; If the laser SLAM positioning information is received within a second preset time period, calculating the offset parameter of the attenuated laser lateral correction information according to the first attenuation factor, wherein the first preset time period is longer than the second preset time period; And, the visual longitudinal correction information offset parameter corresponding to the visual SLAM positioning information also includes: If no visual SLAM positioning information is received within the third preset time period, the visual longitudinal correction information offset parameter is set to zero; If the visual SLAM positioning information is received within a fourth preset time period, the attenuated visual longitudinal correction information offset parameter is calculated according to the second attenuation factor, wherein the third preset time period is longer than the fourth preset time period.

3. The method according to claim 1, wherein: The calculating the current position information of the vehicle according to the fused positioning result at the current moment also includes: Based on the number of GPS satellites and the differential information positioning status in the fused positioning result at the current moment, it is determined whether the autonomous driving vehicle uses the combined positioning information of IMU and RTK.

4. The method according to claim 1, wherein: Also includes: Before entering the tunnel, obtain the SLAM map data in the tunnel through the cloud; After entering the tunnel, laser SLAM positioning information is obtained based on the SLAM map data in the tunnel and the point cloud data collected in real time; and the visual SLAM positioning information is obtained based on the SLAM map data in the tunnel and the real-time recognition of road sign information.

5. The method of claim 1, wherein: After entering the tunnel, obtaining laser SLAM positioning information and visual SLAM positioning information according to the SLAM map data in the tunnel includes: After entering the tunnel, high-precision positioning information of the autonomous driving vehicle obtained by combined positioning of IMU and RTK for a preset time period is cached in real time through a double-ended queue; Based on the SLAM map data in the tunnel, the laser SLAM positioning information and the visual SLAM positioning information are obtained, wherein the laser SLAM positioning information has a preset delay time relative to the preset time length, and the visual SLAM positioning information has a preset delay time within the preset time length; The laser SLAM positioning information is converted into a northeastern rectangular coordinate system according to the current tunnel working condition information, wherein the initial value of the laser SLAM on the vehicle body lateral information is 0.

6. The method of claim 1, wherein: Before entering the tunnel, the SLAM map data in the tunnel is obtained, which also includes: Pre-establishing SLAM map data for the tunnel and uploading it to the cloud, wherein the SLAM map data for the tunnel is marked as a tunnel state; Based on the combined positioning information of IMU and RTK, a map acquisition request is sent to the cloud before entering the tunnel, wherein the map acquisition request carries the tunnel status; The autonomous driving vehicle is positioned according to the received SLAM map data in the tunnel sent from the cloud, and the tunnel status is synchronized to the cloud.

7. A fusion positioning device for an autonomous driving vehicle in a tunnel, wherein: For use in an autonomous driving vehicle, the device comprises: Map acquisition module, used to obtain SLAM map data in the tunnel before entering the tunnel; A positioning information acquisition module is used to obtain laser SLAM positioning information and visual SLAM positioning information according to the SLAM map data in the tunnel after entering the tunnel; An offset determination module is used to determine an offset parameter of the laser lateral correction information corresponding to the laser SLAM positioning information and an offset parameter of the visual longitudinal correction information corresponding to the visual SLAM positioning information; A fusion positioning module is used to determine the fusion positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the offset parameter of the visual longitudinal correction information, and the offset parameter of the laser lateral correction information; Before determining the fused positioning result at the current moment based on the combined positioning information of the IMU and RTK at the previous moment, the visual longitudinal correction information offset parameter, and the laser lateral correction information offset parameter, the method further includes: Based on the SLAM map data in the tunnel, obtaining lateral offset information in the laser SLAM positioning information and timestamp information corresponding to each lateral offset; Based on the SLAM map data in the tunnel, obtaining longitudinal offset information in the visual SLAM positioning information and timestamp information corresponding to each longitudinal offset; Traversing the timestamps of vehicle position information cached within a preset time period, and determining the cached vehicle position information corresponding to the target timestamp at the current moment when an error between the timestamp of the vehicle position information and the timestamp information corresponding to the longitudinal or lateral offset satisfies a preset condition, wherein the vehicle position is obtained based on the combined positioning information of the IMU and RTK; The position determination module is used to calculate the current position information of the vehicle based on the fused positioning result at the current moment.

8. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute the method according to any one of claims 1 to 6.

Images