Fusion positioning method, device and electronic equipment for autonomous driving vehicle

Abstract

The present application discloses a fusion positioning method, device, and electronic device for an autonomous driving vehicle. The method includes: obtaining the laser lateral correction information of the autonomous driving vehicle at the previous moment; when the laser lateral correction information at the previous moment meets a preset correction condition, determining the laser lateral correction information corresponding to the fusion positioning information at the current moment based on the laser lateral correction information at the previous moment; when the signal state of the high-precision positioning signal is unavailable, using the laser lateral correction information corresponding to the fusion positioning information at the current moment to correct the fusion positioning information at the current moment; using the corrected fusion positioning information as measurement information for fusion positioning to obtain a final fusion positioning result. The present application uses the laser lateral correction information to correct the fusion positioning information when the laser lateral correction information meets the preset correction condition and the signal state of the high-precision positioning signal is unavailable, thereby ensuring the positioning accuracy of the autonomous driving vehicle.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a fusion positioning method, device and electronic equipment for an autonomous driving vehicle. Background Art

[0002] In the autonomous driving scenario, it is necessary to achieve high-precision positioning of the autonomous driving vehicle. At present, a multi-sensor fusion positioning method is usually adopted, that is, the positioning information collected by multiple sensors is fused through the Kalman filter to achieve high-precision positioning of the vehicle. For example, one fusion positioning solution in the prior art is a fusion positioning solution based on IMU (Inertial Measurement Unit) and RTK (Real-time kinematic). However, when the autonomous driving vehicle encounters working conditions such as cities, canyons or tunnels, RTK will be interfered with or have no signal, resulting in it being unable to work. Especially in long tunnel conditions, high-precision positioning information cannot be obtained, and the autonomous driving vehicle will not be able to maintain lanes due to the above reasons.

[0003] Laser SLAM (Simultaneous Localization and Mapping)-based positioning solutions have good positioning effects in areas with more features. However, in open roads, the lack of features causes degradation, which in turn leads to positioning failure.

[0004] Therefore, simply using one of the above solutions during autonomous driving may not guarantee high-precision positioning of the autonomous driving vehicle. Summary of the Invention

[0005] The embodiments of the present application provide a fusion positioning method, device and electronic equipment for an autonomous driving vehicle to improve the positioning accuracy and stability of the autonomous driving vehicle.

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

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

[0008] Obtaining the laser lateral correction information of the autonomous driving vehicle at the previous moment;

[0009] When the laser lateral correction information at the previous moment meets the preset correction condition, determining the laser lateral correction information corresponding to the fused positioning information at the current moment according to the laser lateral correction information at the previous moment;

[0010] When the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, correcting the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment to obtain corrected fused positioning information;

[0011] The corrected fused positioning information is used as measurement information for fusion positioning to obtain the final fused positioning result of the autonomous driving vehicle.

[0012] Optionally, the laser lateral correction information at the previous moment includes a position offset and a timestamp corresponding to the position offset. After obtaining the laser lateral correction information of the autonomous driving vehicle at the previous moment, the method further includes:

[0013] Obtaining a fused positioning information queue of the autonomous driving vehicle, wherein the fused positioning information queue is used to cache fused positioning information in real time, and the fused positioning information queue includes multiple position coordinates and corresponding timestamps;

[0014] Traversing the timestamps corresponding to the respective position coordinates in the fused positioning information queue;

[0015] Determining whether there is a timestamp in the fused positioning information queue, wherein the absolute value of the difference between the timestamp corresponding to the position coordinate and the timestamp corresponding to the position offset is less than a preset difference threshold;

[0016] If so, it is determined that the laser transverse correction information at the previous moment meets the preset correction condition.

[0017] Optionally, determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment includes:

[0018] Converting the laser lateral correction information at the previous moment into a navigation coordinate system to obtain the laser lateral correction information in the navigation coordinate system;

[0019] The laser lateral correction information corresponding to the fused positioning information at the current moment is determined according to the laser lateral correction information in the navigation coordinate system.

[0020] Optionally, determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment includes:

[0021] Determining a current accumulated time, where the current accumulated time is calculated from when the laser lateral correction information at the previous moment is acquired;

[0022] If the current accumulated time is less than the first accumulated time threshold, directly using the laser lateral correction information at the previous moment as the laser lateral correction information corresponding to the fused positioning information at the current moment;

[0023] If the current accumulated time is not less than the first accumulated time threshold but less than the second accumulated time threshold, then attenuating the laser lateral correction information at the previous moment, and using the attenuated laser lateral correction information as the laser lateral correction information corresponding to the fused positioning information at the current moment;

[0024] If the current accumulated time is not less than the second accumulated time threshold, the attenuated laser lateral correction information is directly reset to zero as the laser lateral correction information corresponding to the fused positioning information at the current moment.

[0025] Optionally, attenuating the laser lateral correction information at the previous moment includes:

[0026] Determine the attenuation factor;

[0027] When the current accumulated time is not less than the first accumulated time threshold but less than the second accumulated time threshold, the laser lateral correction information at the previous moment is attenuated using the attenuation factor to obtain the attenuated laser lateral correction information.

[0028] Optionally, the correcting the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment to obtain the corrected fused positioning information includes:

[0029] Obtain laser lateral correction information corresponding to the fused positioning information of multiple historical moments;

[0030] Fitting the laser lateral correction information corresponding to the fused positioning information at the current moment and the laser lateral correction information corresponding to the fused positioning information at the multiple historical moments to obtain a fitting equation;

[0031] Determining the laser lateral correction information at the current moment according to the fitting equation;

[0032] The fused positioning information at the current moment is corrected using the laser lateral correction information at the current moment to obtain the corrected fused positioning information.

[0033] Optionally, after determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment, the method further includes:

[0034] Get the current number of satellites and the current RTK positioning signal;

[0035] When the number of satellites at the current moment reaches a preset number threshold and the RTK positioning signal at the current moment is a fixed solution, determining that the signal state of the high-precision positioning signal is an available state;

[0036] Otherwise, it is determined that the signal state of the high-precision positioning signal is an unavailable state.

[0037] In a second aspect, an embodiment of the present application further provides a fusion positioning device for an autonomous driving vehicle, wherein the device includes:

[0038] A first acquisition unit is used to acquire laser lateral correction information of the autonomous driving vehicle at a previous moment;

[0039] a first determining unit, configured to determine, if the laser lateral correction information at the previous moment satisfies a preset correction condition, the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment;

[0040] a correction unit, configured to, when the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, correct the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment, to obtain corrected fused positioning information;

[0041] The fusion positioning unit is used to perform fusion positioning using the corrected fusion positioning information as measurement information to obtain a final fusion positioning result of the autonomous driving vehicle.

[0042] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0043] processor; and

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

[0045] 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 applications, the electronic device executes any of the aforementioned methods.

[0046] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the fusion positioning method for an autonomous driving vehicle in the embodiments of the present application first obtains the laser lateral correction information of the autonomous driving vehicle at the previous moment; then, when the laser lateral correction information at the previous moment meets the preset correction condition, the laser lateral correction information corresponding to the fusion positioning information at the current moment is determined based on the laser lateral correction information at the previous moment; then, when the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, the laser lateral correction information corresponding to the fusion positioning information at the current moment is used to correct the fusion positioning information at the current moment to obtain the corrected fusion positioning information; finally, the corrected fusion positioning information is used as measurement information for fusion positioning to obtain the final fusion positioning result of the autonomous driving vehicle. The fusion positioning method for an autonomous driving vehicle in the embodiments of the present application uses the laser lateral correction information to correct the fusion positioning information when the laser lateral correction information meets the preset correction condition and the signal state of the high-precision positioning signal is unavailable, thereby ensuring the positioning accuracy and stability of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] 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:

[0048] Figure 1 This is a flow chart of a fusion positioning method for an autonomous driving vehicle in an embodiment of the present application;

[0049] Figure 2 This is a schematic diagram of the structure of a fusion positioning device for an autonomous driving vehicle in an embodiment of the present application;

[0050] Figure 3 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0051] 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.

[0052] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0053] The embodiment of the present application provides a fusion positioning method for an autonomous driving vehicle, such as Figure 1As shown, a flow chart of a fusion positioning method for an autonomous driving vehicle in an embodiment of the present application is provided, wherein the method includes at least the following steps S110 to S140:

[0054] Step S110: Acquire the laser lateral correction information of the automatic driving vehicle at the previous moment.

[0055] The fusion positioning method of the autonomous driving vehicle in the embodiment of the present application can be executed by the fusion positioning subsystem of the autonomous driving vehicle. The fusion positioning subsystem is mainly used to fuse data from multiple sensors, thereby outputting a fusion positioning result to achieve high-precision positioning.

[0056] When performing fusion positioning of an autonomous vehicle, embodiments of the present application require obtaining the laser lateral correction information of the autonomous vehicle at the previous moment. This laser lateral correction information is generated by the LiDAR subsystem in the autonomous driving system. Because the frequency at which the LiDAR subsystem outputs laser lateral correction information differs from the frequency at which the fusion positioning subsystem outputs fusion positioning information, the laser lateral correction information is delayed relative to the fusion positioning information, for example, by 70ms-100ms. Therefore, the "previous moment" can be understood as the moment corresponding to the most recently acquired laser lateral correction information, but not the laser lateral correction information actually corresponding to the current fusion positioning information.

[0057] Step S120 , when the laser lateral correction information at the previous moment meets a preset correction condition, determining the laser lateral correction information corresponding to the fused positioning information at the current moment according to the laser lateral correction information at the previous moment.

[0058] As mentioned above, the laser lateral correction information at the previous moment is not the laser lateral correction information actually corresponding to the fused positioning information at the current moment. Therefore, when it is impossible to directly obtain the laser lateral correction information actually corresponding to the fused positioning information at the current moment, it is necessary to determine whether the laser lateral correction information at the previous moment can be used to correct the fused positioning information at the current moment, that is, whether the preset correction conditions are met. If the preset correction conditions are met, the laser lateral correction information corresponding to the fused positioning information at the current moment can be determined based on the laser lateral correction information at the previous moment, so as to be used for subsequent correction.

[0059] In step S130, when the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, the fused positioning information at the current moment is corrected using the laser lateral correction information corresponding to the fused positioning information at the current moment to obtain the corrected fused positioning information.

[0060] After obtaining the laser lateral correction information corresponding to the fused positioning information at the current moment, it is also necessary to judge the signal status of the high-precision positioning signal of the current autonomous driving vehicle. Because if the signal status of the current high-precision positioning signal is good and sufficient to ensure the positioning accuracy requirements of the autonomous driving vehicle, then the correction link of the laser lateral correction information can be omitted at this time. If the signal status of the current high-precision positioning signal is poor and cannot meet the positioning accuracy requirements of the autonomous driving vehicle, then the above-mentioned laser lateral correction information needs to be used to compensate for the positioning deviation caused by the poor high-precision positioning signal.

[0061] Step S140: Using the corrected fused positioning information as measurement information for fusion positioning, to obtain a final fused positioning result of the autonomous driving vehicle.

[0062] After obtaining the corrected fused positioning information, in order to further improve the positioning accuracy, the corrected fused positioning information can be used as an observation value for measurement update. Here, EKF (Extended Kalman Filter) or Kalman filter can be used for fusion positioning to obtain the final fusion positioning result.

[0063] In one embodiment of the present application, the laser lateral correction information at the previous moment includes a position offset and a timestamp corresponding to the position offset. After obtaining the laser lateral correction information of the autonomous driving vehicle at the previous moment, the method further includes: obtaining a fused positioning information queue of the autonomous driving vehicle, the fused positioning information queue being used to cache fused positioning information in real time, the fused positioning information queue including multiple position coordinates and corresponding timestamps; traversing the timestamps corresponding to each position coordinate in the fused positioning information queue; determining whether there is a timestamp in the fused positioning information queue whose absolute value of the difference between the timestamp corresponding to the position coordinate and the timestamp corresponding to the position offset is less than a preset difference threshold; if so, determining that the laser lateral correction information at the previous moment meets the preset correction condition.

[0064] In determining whether the laser lateral correction information at the previous moment meets the preset correction conditions, the embodiment of the present application can first obtain the fused positioning information queue of the autonomous driving vehicle. The fused positioning information queue here is used to cache the fused positioning information output by the fused positioning subsystem in real time, that is, the fused positioning information in the fused positioning information queue is dynamically updated. The fused positioning information can be obtained by fusing the positioning information collected by multiple sensors such as IMU+RTK through an extended Kalman filter. Of course, those skilled in the art can also adopt other combined navigation modes, which are not specifically limited here.

[0065] The fused positioning information queue can be specifically implemented using a deque (double-ended queue). Deque is a data structure with the properties of a queue and a stack. Elements in the double-ended queue can be popped out from both ends. In an embodiment of the present application, the deque is used to cache the fused positioning information within a certain time length, such as 1 second, in real time. When new fused positioning information enters the queue, the earliest fused positioning information will be popped out from the queue, thereby ensuring that the queue always contains the latest fused positioning information within 1 second.

[0066] The laser lateral correction information of the embodiment of the present application may specifically include a position offset Δ and a timestamp time0 corresponding to the position offset. The fused positioning information cached in real time in the fused positioning information queue may specifically include position coordinates (Posx, Posy, Posz) and a timestamp time corresponding to the position coordinates. The position coordinates here can be obtained using UTM (Universal Transverse Mercator Grid System) or WGS84 (World Geodetic System-1984 Coordinate System). Of course, other forms may also be used, which are not specifically limited here.

[0067] The fusion positioning frequency of the embodiment of the present application is generally 100Hz, so if the fusion positioning information within 1s is cached, then there will be 100 data pairs consisting of position coordinates and timestamps in the fusion positioning information queue. Based on this, when judging whether the laser lateral correction information meets the first preset correction condition, you can first traverse the timestamp time corresponding to each position coordinate currently cached in the fusion positioning information queue, and compare the timestamp time corresponding to each position coordinate with the timestamp time0 corresponding to the laser lateral correction information. If the absolute value of the difference between the two is less than a certain difference threshold, it means that the delay error of the currently received laser lateral correction information is acceptable. Therefore, it can be determined that the laser lateral correction information meets the preset correction condition and can be used to correct the fusion positioning information at the current moment.

[0068] The size of the above-mentioned preset difference threshold mainly depends on the fusion positioning frequency. For example, if the fusion positioning frequency is 100Hz, then the preset difference threshold here can be set to 0.01s. Of course, in order to further improve the accuracy of the judgment, the preset difference threshold can also be set to a smaller value, such as 0.005s. If |time-time0|<0.005s, it means that the laser lateral correction information can be used to correct the fusion positioning information at the current moment, so the position information corresponding to the current time1 cached in the fusion positioning information queue can be recorded.

[0069] In one embodiment of the present application, determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment includes: converting the laser lateral correction information at the previous moment into a navigation coordinate system to obtain the laser lateral correction information in the navigation coordinate system; and determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information in the navigation coordinate system.

[0070] In the embodiment of the present application, when correcting the fused positioning information at the current moment using the laser lateral correction information at the previous moment, the position offset Δ(Lidar posx, Lidar posy, Lidar posz) in the laser lateral correction information can be first converted to a navigation coordinate system, such as the East-North-Up (ENU) coordinate system, based on the RTK positioning information at the current moment (RTK posx, RTK posy, RTK posz). This can thereby obtain the position offset (dx, dy, dz) in the navigation coordinate system. This can be specifically achieved in the following manner:

[0071] dx=timex Lidar posx-timex RTK posx

[0072] dy=timex Lidar posy-timex RTK posy

[0073] dz=timex Lidar posz-timex RTK posz

[0074] In one embodiment of the present application, determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment includes: determining the current cumulative time, and the current cumulative time is calculated from the time when the laser lateral correction information at the previous moment is acquired; if the current cumulative time is less than the first cumulative time threshold, then directly using the laser lateral correction information at the previous moment as the laser lateral correction information corresponding to the fused positioning information at the current moment; if the current cumulative time is not less than the first cumulative time threshold but less than the second cumulative time threshold, then attenuating the laser lateral correction information at the previous moment, and using the attenuated laser lateral correction information as the laser lateral correction information corresponding to the fused positioning information at the current moment; if the current cumulative time is not less than the second cumulative time threshold, then directly returning the attenuated laser lateral correction information to zero as the laser lateral correction information corresponding to the fused positioning information at the current moment.

[0075] As mentioned above, the laser lateral correction information of the previous moment obtained by the embodiment of the present application is not the correction information actually corresponding to the fused positioning information of the current moment. The laser lateral correction information still has a certain degree of availability in a short period of time, but when new laser lateral correction information cannot be obtained for a long time, the availability of the laser lateral correction information of the previous moment will be reduced or even no longer available. Therefore, after a large number of experiments, the embodiment of the present application has designed a logic for determining the availability of the laser lateral correction information of the previous moment under different cumulative times.

[0076] It should be noted here that the "current accumulated time" defined in the embodiment of the present application can be used to represent the length of time that has elapsed after the laser lateral correction information at the previous moment is obtained.

[0077] The first situation is that when the above-mentioned current cumulative time has not reached the first cumulative time threshold, it means that the time of the laser lateral correction information obtained at the previous moment is still close to the current moment, so the laser lateral correction information at the previous moment has a higher availability. At this time, the laser lateral correction information at the previous moment can be directly used to correct the fused positioning information at the current moment.

[0078] The second situation is that when the above-mentioned current cumulative time reaches the first cumulative time threshold but has not yet reached the second cumulative time threshold, it means that the time from the acquisition of the laser lateral correction information at the previous moment to the current moment has passed for a considerable period of time, and the availability of the laser lateral correction information at the previous moment has decreased due to the accumulation of time. However, in order to avoid the sudden change in the positioning trajectory caused by the direct abandonment of the correction link of the laser lateral correction information, the laser lateral correction information at the previous moment can be smoothed. For example, the laser lateral correction information at the previous moment can be gradually attenuated, and then the attenuated laser lateral correction information can be used to correct the fused positioning information at the current moment, thereby optimizing the entry and exit mechanism of the laser lateral correction information and ensuring the smoothness and stability of the fused positioning. Therefore, the above processing method takes into account the stability of the corrected fused positioning result and the fused positioning accuracy.

[0079] The third situation is that when the above-mentioned current cumulative time reaches the second cumulative time threshold, it means that the distance between the time when the laser lateral correction information of the previous moment was obtained and the current moment is already long. After this long period of time, the laser lateral correction information may have undergone relatively large changes. Therefore, the laser lateral correction information of the previous moment will no longer be available. At this time, the laser lateral correction information can be directly reset to zero, that is, lateral correction is no longer performed based on the laser lateral correction information.

[0080] The above-mentioned first cumulative time threshold and second cumulative time threshold are both empirical values ​​and can be flexibly adjusted according to actual scenarios and actual needs. In order to facilitate the understanding of the embodiments of the present application, further examples are given here. Assuming that the first cumulative time threshold is 1s and the second cumulative time threshold is 4s, when the current cumulative time is less than 1s, the laser lateral correction information of the previous moment can be directly used to correct the fused positioning information of the current moment. When the current cumulative time reaches 1s but does not reach 4s, the laser lateral correction information of the previous moment can be attenuated and then the fused positioning information of the current moment can be corrected. When the current cumulative time reaches 4s, the laser lateral correction information is directly reset to zero.

[0081] In addition, it should be noted that since the generation of laser lateral correction information is not affected by lane line obstruction, weather, or lighting, the output of laser lateral correction information is relatively more stable. However, the solution of visual lateral correction information based on visual recognition output relies on the recognition effect of lane lines, so the output of visual lateral correction information is relatively less stable. Therefore, in the embodiment of the present application, the judgment of the availability of the above-mentioned laser lateral correction information at different cumulative times is more stringent than the judgment of the visual lateral correction information. For example, the cumulative time for judging the visual lateral correction information can reach 6 seconds, while the cumulative time for judging the laser lateral correction information in the embodiment of the present application will be less than the cumulative time for judging the visual lateral correction information, for example, set to 4 seconds.

[0082] In one embodiment of the present application, the attenuation of the laser lateral correction information at the previous moment includes: determining an attenuation factor; when the current cumulative time is not less than a first cumulative time threshold but less than a second cumulative time threshold, using the attenuation factor to attenuate the laser lateral correction information at the previous moment to obtain the attenuated laser lateral correction information.

[0083] In this embodiment of the application, when performing attenuation processing on the laser lateral correction information of the previous moment, an attenuation factor lidar_k can be determined first. This attenuation factor can represent the degree of attenuation of the laser lateral correction information each time. The position offset in the navigation coordinate system is (dx, dy, dz), so the attenuation factor lidar_k can be determined as follows:

[0084] Lidar_k[0]=dx() / 100.0;

[0085] Lidar_k[1]=dy() / 100.0;

[0086] Lidar_k[2]=dz() / 100.0.

[0087] Assuming that the first cumulative time threshold is 1s and the second cumulative time threshold is 4s, the attenuated laser lateral correction information can be further calculated based on the above attenuation factor Lidar_k, which can be specifically expressed as:

[0088]

[0089]

[0090] In one embodiment of the present application, the laser lateral correction information corresponding to the fused positioning information at the current moment is used to correct the fused positioning information at the current moment to obtain the corrected fused positioning information, including: acquiring laser lateral correction information corresponding to the fused positioning information at multiple historical moments; fitting the laser lateral correction information corresponding to the fused positioning information at the current moment and the laser lateral correction information corresponding to the fused positioning information at the multiple historical moments to obtain a fitting equation; determining the laser lateral correction information at the current moment according to the fitting equation; and correcting the fused positioning information at the current moment using the laser lateral correction information at the current moment to obtain the corrected fused positioning information.

[0091] The above embodiment has a good positioning effect when the autonomous driving vehicle is traveling at a low speed or a normal speed. However, when the autonomous driving vehicle is traveling at a high speed, the position of the autonomous driving vehicle will change significantly in a short period of time. At this time, directly using the attenuated laser lateral correction information obtained by the above method for correction will produce a certain degree of error.

[0092] Based on this, in order to further improve the positioning effect of the autonomous driving vehicle when traveling at high speed, the embodiment of the present application can perform fitting processing on the multiple frames of laser lateral correction information obtained after continuous attenuation over a period of time when no new laser lateral correction information is received. For example, 5 consecutive frames of laser lateral correction information can be obtained, and then these 5 frames of laser lateral correction information can be fitted to obtain a fitting equation. Finally, the fitting equation is used to predict the laser lateral correction information at the current moment, thereby compensating for the error problem of the laser lateral correction information caused by the autonomous driving vehicle traveling at high speed.

[0093] When correcting the current fusion positioning information (Posx, Posy, Posz) using the current laser lateral correction information (dx, dy, dz), the following form can be used:

[0094] Posx'=Posx+dx

[0095] Posy'=Posy+dy

[0096] Posz'=Posy+dz

[0097] Among them, (Posx', Posy', Posz') is the corrected fusion positioning information.

[0098] In one embodiment of the present application, after determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment, the method further includes: obtaining the number of satellites at the current moment and the RTK positioning signal at the current moment; when the number of satellites at the current moment reaches a preset number threshold and the RTK positioning signal at the current moment is a fixed solution, determining that the signal state of the high-precision positioning signal is an available state; otherwise, determining that the signal state of the high-precision positioning signal is an unavailable state.

[0099] In the embodiment of the present application, determining the laser lateral correction information corresponding to the fused positioning information at the current moment can be an ongoing process, but the determined laser lateral correction information is mainly used to compensate for the positioning deviation when the quality of the high-precision positioning signal of the autonomous driving vehicle is poor. Once the signal state of the current high-precision positioning signal is restored to a usable state, there is no need to use the laser lateral correction information for correction.

[0100] That is, the calculation of the laser lateral correction information is ongoing, but whether the calculated laser lateral correction information will be used to correct the fused positioning information at the current moment depends on the signal state of the high-precision positioning signal at the current moment. Therefore, the embodiment of the present application can judge the signal state of the current high-precision positioning signal in real time. If the signal state of the current high-precision positioning signal is unavailable, the calculated laser lateral correction information can be used to correct the fused positioning information at the current moment. Once the signal state of the current high-precision positioning signal is restored to an available state, it can be switched to a strategy of fused positioning based on the high-precision positioning signal.

[0101] When determining the current high-precision positioning signal status, a comprehensive judgment can be made based on the current number of satellites and the current RTK positioning signal. If the current number of satellites is greater than a certain threshold, such as 20, and the current RTK positioning signal is a fixed solution of 42, then the high-precision positioning signal status is available. Otherwise, the high-precision positioning signal status is unavailable.

[0102] It should be noted that if the judgment is made solely based on whether the RTK positioning signal is a fixed solution, the extended Kalman filter may be "deceived". For example, the output RTK positioning signal is a fixed solution, but the number of satellites is small at this time, which still indicates that the quality of the RTK positioning signal is poor. Therefore, the embodiment of the present application uses the above two dimensions for comprehensive judgment, which can greatly improve the accuracy of the judgment of the signal status of the high-precision positioning signal.

[0103] In addition, in order to further improve the stability of judging whether the signal status is an available state, the embodiment of the present application can continuously judge whether the signal status of the high-precision positioning signal within a period of time is all in an available state. For example, the signal status of the high-precision positioning signal within 3 seconds can be continuously judged. Specifically, the timing can be performed by counting the laser radar data, namely lidar_num_cnt.

[0104] The fusion positioning method of the autonomous driving vehicle of the present application performs fusion positioning optimization based on the laser lateral correction information, and can automatically switch the measurement information used according to the number of satellites and the quality of the RTK positioning signal, thereby ensuring the positioning accuracy. At the same time, it optimizes the entry and exit mechanism of the laser lateral correction information, thereby ensuring the smoothness and stability of the fusion positioning.

[0105] The embodiment of the present application also provides a fusion positioning device 200 for an autonomous driving vehicle, such as Figure 2 As shown, a fusion positioning device for an autonomous driving vehicle in an embodiment of the present application is provided. The device 200 includes: a first acquisition unit 210, a first determination unit 220, a correction unit 230, and a fusion positioning unit 240, wherein:

[0106] A first acquisition unit 210 is configured to acquire laser lateral correction information of the autonomous driving vehicle at a previous moment;

[0107] A first determining unit 220 is configured to determine, if the laser lateral correction information at the previous moment satisfies a preset correction condition, the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment;

[0108] The correction unit 230 is configured to correct the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment, when the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, to obtain corrected fused positioning information;

[0109] The fusion positioning unit 240 is used to perform fusion positioning using the corrected fusion positioning information as measurement information to obtain a final fusion positioning result of the autonomous driving vehicle.

[0110] In one embodiment of the present application, the laser lateral correction information at the previous moment includes a position offset and a timestamp corresponding to the position offset, and the device also includes: a second acquisition unit, used to obtain the fused positioning information queue of the autonomous driving vehicle, the fused positioning information queue is used to cache fused positioning information in real time, and the fused positioning information queue includes multiple position coordinates and corresponding timestamps; a traversal unit, used to traverse the timestamps corresponding to each position coordinate in the fused positioning information queue; a second determination unit, used to determine whether there is a timestamp in the fused positioning information queue, the absolute value of the difference between the timestamp corresponding to the position coordinate and the timestamp corresponding to the position offset being less than a preset difference threshold; a third determination unit, used to determine that the laser lateral correction information at the previous moment meets the preset correction condition if it exists.

[0111] In one embodiment of the present application, the first determination unit 220 is specifically used to: convert the laser lateral correction information of the previous moment into the navigation coordinate system to obtain the laser lateral correction information in the navigation coordinate system; determine the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information in the navigation coordinate system.

[0112] In one embodiment of the present application, the first determination unit 220 is specifically used to: determine the current cumulative time, and the current cumulative time is calculated from the time when the laser lateral correction information of the previous moment is obtained; if the current cumulative time is less than the first cumulative time threshold, the laser lateral correction information of the previous moment is directly used as the laser lateral correction information corresponding to the fusion positioning information of the current moment; if the current cumulative time is not less than the first cumulative time threshold but less than the second cumulative time threshold, the laser lateral correction information of the previous moment is attenuated, and the attenuated laser lateral correction information is used as the laser lateral correction information corresponding to the fusion positioning information of the current moment; if the current cumulative time is not less than the second cumulative time threshold, the attenuated laser lateral correction information is directly reset to zero as the laser lateral correction information corresponding to the fusion positioning information of the current moment.

[0113] In one embodiment of the present application, the first determination unit 220 is specifically used to: determine an attenuation factor; and when the current cumulative time is not less than the first cumulative time threshold but less than the second cumulative time threshold, use the attenuation factor to attenuate the laser lateral correction information at the previous moment to obtain the attenuated laser lateral correction information.

[0114] In one embodiment of the present application, the correction unit 230 is specifically used to: obtain laser lateral correction information corresponding to the fused positioning information of multiple historical moments; fit the laser lateral correction information corresponding to the fused positioning information of the current moment and the laser lateral correction information corresponding to the fused positioning information of the multiple historical moments to obtain a fitting equation; determine the laser lateral correction information of the current moment according to the fitting equation; use the laser lateral correction information of the current moment to correct the fused positioning information of the current moment to obtain the corrected fused positioning information.

[0115] In one embodiment of the present application, the device also includes: a third acquisition unit, used to obtain the number of satellites at the current moment and the RTK positioning signal at the current moment; a fourth determination unit, used to determine that the signal state of the high-precision positioning signal is an available state when the number of satellites at the current moment reaches a preset number threshold and the RTK positioning signal at the current moment is a fixed solution; and a fifth determination unit, used to determine that the signal state of the high-precision positioning signal is an unavailable state otherwise.

[0116] It can be understood that the above-mentioned fusion positioning device of the autonomous driving vehicle can implement the various steps of the fusion positioning method of the autonomous driving vehicle provided in the aforementioned embodiments. The relevant explanations on the fusion positioning method of the autonomous driving vehicle are applicable to the fusion positioning device of the autonomous driving vehicle 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 3Only 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 the autonomous vehicle at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0121] Obtaining the laser lateral correction information of the autonomous driving vehicle at the previous moment;

[0122] When the laser lateral correction information at the previous moment meets the preset correction condition, determining the laser lateral correction information corresponding to the fused positioning information at the current moment according to the laser lateral correction information at the previous moment;

[0123] When the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, correcting the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment to obtain corrected fused positioning information;

[0124] The corrected fused positioning information is used as measurement information for fusion positioning to obtain the final fused positioning result of the autonomous driving vehicle.

[0125] The above application Figure 1The method performed by the fusion positioning device of an autonomous vehicle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by 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.

[0126] The electronic device may also perform Figure 1 A method for executing a fusion positioning device of an autonomous driving vehicle, and realizing a fusion positioning device of an autonomous driving vehicle in Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0127] 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 of the autonomous driving vehicle in the illustrated embodiment is specifically used to perform:

[0128] Obtaining the laser lateral correction information of the autonomous driving vehicle at the previous moment;

[0129] When the laser lateral correction information at the previous moment meets the preset correction condition, determining the laser lateral correction information corresponding to the fused positioning information at the current moment according to the laser lateral correction information at the previous moment;

[0130] When the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, correcting the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment to obtain corrected fused positioning information;

[0131] The corrected fused positioning information is used as measurement information for fusion positioning to obtain the final fused positioning result of the autonomous driving vehicle.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A fusion positioning method for an autonomous driving vehicle, wherein: The method comprises: Obtaining the laser lateral correction information of the autonomous driving vehicle at the previous moment; When the laser lateral correction information at the previous moment meets the preset correction condition, determining the laser lateral correction information corresponding to the fused positioning information at the current moment according to the laser lateral correction information at the previous moment; When the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, correcting the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment to obtain corrected fused positioning information; Using the corrected fused positioning information as measurement information for fusion positioning to obtain a final fused positioning result of the autonomous driving vehicle; The step of determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment includes: Determining a current accumulated time, where the current accumulated time is calculated from when the laser lateral correction information at the previous moment is acquired; If the current accumulated time is less than the first accumulated time threshold, the laser lateral correction information at the previous moment is directly used as the laser lateral correction information corresponding to the fused positioning information at the current moment; If the current accumulated time is not less than the first accumulated time threshold but less than the second accumulated time threshold, then attenuating the laser lateral correction information at the previous moment, and using the attenuated laser lateral correction information as the laser lateral correction information corresponding to the fused positioning information at the current moment; If the current accumulated time is not less than the second accumulated time threshold, the attenuated laser lateral correction information is directly reset to zero as the laser lateral correction information corresponding to the fused positioning information at the current moment.

2. The method according to claim 1, wherein: The laser lateral correction information at the previous moment includes a position offset and a timestamp corresponding to the position offset. After obtaining the laser lateral correction information at the previous moment of the autonomous driving vehicle, the method further includes: Obtaining a fused positioning information queue of the autonomous driving vehicle, wherein the fused positioning information queue is used to cache fused positioning information in real time, and the fused positioning information queue includes multiple position coordinates and corresponding timestamps; Traversing the timestamps corresponding to the respective position coordinates in the fused positioning information queue; Determining whether there is a timestamp in the fused positioning information queue, the absolute value of the difference between the timestamp corresponding to the position coordinate and the timestamp corresponding to the position offset being less than a preset difference threshold; If so, it is determined that the laser transverse correction information at the previous moment meets the preset correction condition.

3. The method according to claim 1, wherein: The step of determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment includes: Converting the laser lateral correction information at the previous moment into a navigation coordinate system to obtain the laser lateral correction information in the navigation coordinate system; The laser lateral correction information corresponding to the fused positioning information at the current moment is determined according to the laser lateral correction information in the navigation coordinate system.

4. The method according to claim 1, wherein: The attenuating the laser transverse correction information at the previous moment includes: Determine the attenuation factor; When the current accumulated time is not less than the first accumulated time threshold but less than the second accumulated time threshold, the laser lateral correction information at the previous moment is attenuated using the attenuation factor to obtain the attenuated laser lateral correction information.

5. The method of claim 1, wherein: The step of correcting the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment to obtain the corrected fused positioning information includes: Obtain laser lateral correction information corresponding to the fused positioning information of multiple historical moments; Fitting the laser lateral correction information corresponding to the fused positioning information at the current moment and the laser lateral correction information corresponding to the fused positioning information at the multiple historical moments to obtain a fitting equation; Determining the laser lateral correction information at the current moment according to the fitting equation; The fused positioning information at the current moment is corrected using the laser lateral correction information at the current moment to obtain the corrected fused positioning information.

6. The method of claim 1, wherein: After determining the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment, the method further includes: Get the current number of satellites and the current RTK positioning signal; When the number of satellites at the current moment reaches a preset number threshold and the RTK positioning signal at the current moment is a fixed solution, determining that the signal state of the high-precision positioning signal is an available state; Otherwise, it is determined that the signal state of the high-precision positioning signal is an unavailable state.

7. A fusion positioning device for an autonomous driving vehicle, wherein: The device comprises: A first acquisition unit is used to acquire laser lateral correction information of the autonomous driving vehicle at a previous moment; a first determining unit, configured to determine, if the laser lateral correction information at the previous moment satisfies a preset correction condition, the laser lateral correction information corresponding to the fused positioning information at the current moment based on the laser lateral correction information at the previous moment; a correction unit, configured to, when the signal state of the high-precision positioning signal of the autonomous driving vehicle is unavailable, correct the fused positioning information at the current moment by using the laser lateral correction information corresponding to the fused positioning information at the current moment, to obtain corrected fused positioning information; a fusion positioning unit, configured to perform fusion positioning using the corrected fusion positioning information as measurement information to obtain a final fusion positioning result of the autonomous driving vehicle; The first determining unit is specifically configured to: Determining a current accumulated time, where the current accumulated time is calculated from when the laser lateral correction information at the previous moment is acquired; If the current accumulated time is less than the first accumulated time threshold, the laser lateral correction information at the previous moment is directly used as the laser lateral correction information corresponding to the fused positioning information at the current moment; If the current accumulated time is not less than the first accumulated time threshold but less than the second accumulated time threshold, then attenuating the laser lateral correction information at the previous moment, and using the attenuated laser lateral correction information as the laser lateral correction information corresponding to the fused positioning information at the current moment; If the current accumulated time is not less than the second accumulated time threshold, the attenuated laser lateral correction information is directly reset to zero as the laser lateral correction information corresponding to the fused positioning information 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