Automatic driving positioning evaluation method and device, electronic equipment and storage medium

Abstract

The invention discloses an automatic driving positioning evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a positioning signal of a vehicle and a positioning truth value signal of the vehicle in response to an automatic driving mode of the vehicle; determining a positioning evaluation result of the vehicle in the target scene according to the positioning truth value signal of the vehicle and the positioning signal of the vehicle; wherein the positioning signal of the vehicle is used as a corresponding positioning signal in a target scene, and the target scene comprises a simulation scene. According to the invention, simulation of positioning scenes of various tunnels is realized, and an off-line automatic evaluation process is established. According to the invention, the data acquisition and evaluation cost in a special scene can be reduced, and the overall evaluation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of autonomous driving testing, and particularly to a method and device for evaluating autonomous driving positioning, an electronic device, and a storage medium. Background Art

[0002] With the rapid development of autonomous driving technology, the scenarios it can adapt to are increasing, such as common scenarios like highways and urban streets. However, for some special scenarios, such as tunnels, heavy rain and fog, strong backlighting, etc., the autonomous driving ability is still relatively weak. Although the probability of these special scenarios occurring in real life is relatively low, their importance cannot be ignored.

[0003] If we want to solve the problems brought by these special scenarios, we need to rely on data collection and construction of the above scenarios. However, the above special scenarios are few and difficult to encounter, causing great difficulties in data collection and construction. For example, taking the tunnel scenario as an example, tunnel scenarios mostly exist in mountainous sections, while most urban areas are in plain areas, and there are no tunnel scenarios within the urban area. Moreover, the lengths and curvatures of different tunnels vary greatly, which causes great difficulties in data collection and construction of tunnel scenarios. Summary of the Invention

[0004] Embodiments of the present application provide a method and device for evaluating autonomous driving positioning, an electronic device, and a storage medium, which can simulate the positioning scenarios of various tunnels and establish an offline automated evaluation process. Thereby reducing the data collection and evaluation costs for special scenarios and improving the overall evaluation efficiency.

[0005] Embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, embodiments of the present application provide a method for evaluating autonomous driving positioning, wherein the positioning evaluation method includes:

[0007] In response to the autonomous driving mode of the vehicle itself, obtain the positioning signal and the positioning true value signal of the vehicle itself;

[0008] Determine the positioning evaluation result of the vehicle itself in the target scenario according to the positioning true value signal and the positioning signal of the vehicle itself;

[0009] Wherein, the positioning signal of the vehicle itself serves as the corresponding positioning signal in the target scenario, and the target scenario includes a simulated scenario.

[0010] In some embodiments, the vehicle itself includes a signal shielding device and a true value positioning device, and the vehicle itself includes a positioning module. The step of obtaining the positioning signal and the positioning true value signal of the vehicle itself in response to the autonomous driving mode of the vehicle itself includes:

[0011] In response to the autonomous driving mode of the host vehicle, start a signal shielding device to obtain a simulated scenario;

[0012] Based on the simulated scenario, obtain the positioning signal of the host vehicle, where the positioning signal of the host vehicle includes at least one of the following: positioning data output by the positioning module, and original data required by the positioning module;

[0013] Based on the true value positioning device, synchronously obtain the positioning true value signal of the host vehicle.

[0014] In some embodiments, the positioning data output by the positioning module includes any one or more of: laser SLAM data, visual SLAM data, high-precision map data, GPS data, RTK data, and the original data required by the positioning module includes any one or more of: original point cloud data, original camera image data, road surface identification data in the original high-precision map, and original GNSS data.

[0015] In some embodiments, determining the positioning evaluation result of the host vehicle in the target scenario according to the positioning true value signal and the positioning signal of the host vehicle includes:

[0016] When the simulated scenario is a tunnel scenario, according to the positioning true value signal of the host vehicle and the positioning signals of the host vehicle when entering and exiting the tunnel scenario simulation stage, determine the positioning evaluation results of the host vehicle when entering and exiting the tunnel scenario;

[0017] and / or,

[0018] When the simulated scenario is a non-tunnel scenario, according to the positioning true value signal of the host vehicle and the positioning signal of the host vehicle on the normal road, determine the positioning evaluation result of the host vehicle on the normal road.

[0019] In some embodiments, determining the positioning evaluation result of the host vehicle in the target scenario according to the positioning true value signal and the positioning signal of the host vehicle includes:

[0020] Input the positioning true value signal and the positioning signal of the host vehicle into a pre-established positioning evaluation system, and the configuration file corresponding to each vehicle model can be updated in the positioning evaluation system;

[0021] Based on the configuration file corresponding to each vehicle model, perform data analysis on the positioning signal and the positioning true value signal of the host vehicle according to the positioning evaluation system, and output the positioning evaluation result.

[0022] In some embodiments, it further includes:

[0023] By controlling the signal shielding device, adjust the space blocking the RTK antenna of the host vehicle to change the satellite signal strength received by the RTK antenna;

[0024] The degrees of satellite signal reception by the RTK antenna include: a first reception state, a weakening state, a weakening-to-zero state, a state where signal reception is always zero, a strengthening state, and a second reception state. The first reception state and the second reception state are the RTK signal reception states when the satellite signal strength is normal;

[0025] The simulated scenarios in response to the degrees of satellite signal reception by the RTK antenna include: the host vehicle has not entered the simulated scenario, the host vehicle is entering the simulated scenario, the host vehicle has entered the simulated scenario, the host vehicle is continuously driving in the simulated scenario, the host vehicle is exiting the simulated scenario, and the host vehicle has exited the simulated scenario.

[0026] In some embodiments, the positioning evaluation result includes a positioning algorithm evaluation result, and the method further includes:

[0027] When there is a new positioning algorithm to be evaluated, based on the positioning signal of the host vehicle and the new positioning algorithm, output a new positioning evaluation result;

[0028] Visualize and display according to the new positioning evaluation result through any one or more of instant messaging software, emails, and data platforms.

[0029] In a second aspect, an embodiment of the present application further provides an autonomous driving positioning evaluation device, where the device includes:

[0030] A response module, configured to obtain the positioning signal of the host vehicle and the positioning true value signal of the host vehicle in response to the autonomous driving mode of the host vehicle;

[0031] A determination module, configured to determine the positioning evaluation result of the host vehicle in the target scenario according to the positioning true value signal of the host vehicle and the positioning signal of the host vehicle;

[0032] Wherein, the positioning signal of the host vehicle serves as the corresponding positioning signal in the target scenario, and the target scenario includes a simulated scenario.

[0033] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to execute the above method.

[0034] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the above method.

[0035] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects: in response to the autonomous driving mode of the vehicle, the positioning signal of the vehicle and the positioning true value signal of the vehicle are acquired. Then, according to the positioning true value signal of the vehicle and the positioning signal of the vehicle, the positioning evaluation result of the vehicle in the target scenario is determined. Since the positioning signal of the vehicle is used as the corresponding positioning signal in the target scenario, various types of positioning data to be evaluated can be obtained. Since the target scenario includes a simulation scenario, most common or less common scenarios can be simulated, and positioning evaluation can be performed on these scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] 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 of the present application. In the drawings:

[0037] Figure 1 is a timing diagram of the autonomous driving positioning evaluation method in the embodiments of the present application;

[0038] Figure 2 is a schematic flowchart of the autonomous driving positioning evaluation method in the embodiments of the present application;

[0039] Figure 3 is a schematic structural diagram of the autonomous driving positioning evaluation device in the embodiments of the present application;

[0040] Figure 4 is a schematic working flowchart of the positioning evaluation system in the autonomous driving positioning evaluation method in the embodiments of the present application;

[0041] Figure 5 is a schematic structural diagram of an electronic device in the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0043] The following will describe in detail the technical solutions provided in each embodiment of the present application in conjunction with the drawings.

[0044] As Figure 1As shown in the figure, the timing interaction in the embodiments of the present application includes the host vehicle, the simulated scenario, and the positioning evaluation. The host vehicle refers to a vehicle with an autonomous driving mode, and the positioning evaluation refers to evaluating the positioning accuracy of the host vehicle. The simulated scenario includes, but is not limited to, scenarios with signal loss or occlusion such as simulated tunnels, simulated viaducts, and simulated basements. The simulated scenario simulates instructions for different scenarios, the host vehicle responds to the instructions for different scenarios, and the host vehicle enters the autonomous driving mode. Based on the simulated scenario, the positioning true value signal of the host vehicle is collected and the positioning signal of the host vehicle is used for positioning evaluation. The positioning evaluation result of the host vehicle in the target scenario is sent to the simulated scenario, and the host vehicle determines whether to continue the test according to the scenario. It can be understood that the simulated scenario can send the target scenario to the host vehicle and perform positioning evaluation after implementing the corresponding operations on the host vehicle.

[0045] The embodiments of the present application provide an autonomous driving positioning evaluation method, as Figure 2 shown, provides a schematic flowchart of the autonomous driving positioning evaluation method in the embodiments of the present application. The method at least includes the following steps S210 to step S220:

[0046] Step S210, in response to the autonomous driving mode of the host vehicle, obtain the positioning signal of the host vehicle and the positioning true value signal of the host vehicle.

[0047] The host vehicle serves as a collection carrier for autonomous driving positioning evaluation. By responding to the autonomous driving mode of the host vehicle, the positioning signal of the host vehicle is obtained. It can be understood that the positioning signal of the host vehicle includes, but is not limited to, the positioning data output by the positioning module of the host vehicle in the autonomous driving mode and the positioning raw data required by the positioning module when outputting the positioning data, or the node positioning data respectively output by each node in the positioning module.

[0048] At the same time, it is also necessary to obtain the positioning true value signal of the host vehicle. It can be understood that the positioning true value signal of the host vehicle can be collected by a true value device installed on the host vehicle.

[0049] It should be noted that the positioning signal of the host vehicle and the positioning true value signal of the host vehicle are obtained simultaneously through the host vehicle, so as to ensure timestamp synchronization.

[0050] Step S220, according to the positioning true value signal of the host vehicle and the positioning signal of the host vehicle, determine the positioning evaluation result of the host vehicle in the target scenario, where the positioning signal of the host vehicle serves as the corresponding positioning signal in the target scenario, and the target scenario includes a simulated scenario.

[0051] Based on the positioning true value signal of the host vehicle and the positioning signal of the host vehicle, the positioning evaluation result of the host vehicle in the target scenario can be determined. For example, by comparing the difference between the positioning true value signal of the host vehicle and the positioning signal of the host vehicle, the error result can be determined. Another example is that by comparing the difference between the positioning true value signal of the host vehicle and the output result of the positioning algorithm after the positioning signal of the host vehicle is fed back for testing, the error result can be determined.

[0052] It can be understood that the positioning signal of the host vehicle, as the corresponding positioning signal in the target scenario, includes but is not limited to the original positioning data (host vehicle sensor perception data), the host vehicle positioning result output by the positioning module (the positioning result output by the positioning algorithm), and the positioning results respectively output by each node (laser node, vision node) in the positioning module at this time.

[0053] Through the above method, in response to the autonomous driving mode of the host vehicle, the positioning signal and the positioning true value signal of the host vehicle are obtained; based on the positioning true value signal of the host vehicle and the positioning signal of the host vehicle, the positioning evaluation result of the host vehicle in the target scenario is determined. This solves the problem of the small amount of data in the special positioning scenario of autonomous driving. For example, tunnel scenarios mostly exist in mountainous sections, most urban areas are in plain areas, and there are no tunnel scenarios inside the urban area, making it difficult to collect data. And it solves the problem of the single type of data in the special positioning scenario of autonomous driving. For example, due to the small amount of data, the types of tunnel data collected are relatively single, and only the tunnel data near the city where it is located can be collected, resulting in a single type.

[0054] Through the above method, when determining the positioning evaluation result of the host vehicle in the target scenario, an offline automated evaluation process is established. This solves the problems of difficult data collection, high human and time costs, and safety in the special positioning scenario of autonomous driving. For example, in special scenarios such as tunnels, data collection is difficult and the risk factor is relatively high, making it not easy to collect. At the same time, it solves the problem of low evaluation efficiency. For example, when evaluating the collected positioning data, manual comparison is required, the process is cumbersome, the efficiency is low, and the probability of errors in the results is high.

[0055] Different from the related technology that requires collecting the host vehicle positioning data in the actual scenario, which causes great difficulties in the collection and construction of scenario data. Through the above method, various tunnel positioning scenarios are simulated, and an offline automated evaluation process is established. Especially for the simulated tunnel positioning data, the positioning accuracy of the host vehicle is evaluated offline, greatly reducing the time and labor costs spent on data collection and evaluation for special scenarios such as tunnels, and improving the overall efficiency.

[0056] In one embodiment of the present application, the host vehicle includes a signal shielding device and a true value positioning device. The host vehicle includes a positioning module. Responding to the autonomous driving mode of the host vehicle to obtain the positioning signal and the positioning true value signal of the host vehicle includes: responding to the autonomous driving mode of the host vehicle, starting the signal shielding device to obtain a simulated scenario; based on the simulated scenario, obtaining the positioning signal of the host vehicle, and the positioning signal of the host vehicle includes at least one of the following: the positioning data output by the positioning module, the original data required by the positioning module; based on the true value positioning device, synchronously obtaining the positioning true value signal of the host vehicle.

[0057] Taking the tunnel scenario as an example, a detailed description will be given.

[0058] The true value positioning device can adopt a device common in related technologies. After being installed on the host vehicle, the positioning true value (data / signal) can be obtained through the true value positioning device. The shielding device can be a signal shielding device. For example, a device similar to a dome shape, such as a metal cap, can be used to cover the antenna to shield the signal. It is covered above the GNSS antenna. By controlling the opening and closing degree of this metal cap, the GNSS signal reception intensity can be affected. It can be understood that those skilled in the art can design the specific structure of the shielding device according to actual needs, and no specific limitation is made in the embodiments of the present application.

[0059] Based on the simulated scenario again, obtaining the positioning signal of the host vehicle, and the positioning signal of the host vehicle includes but is not limited to: the positioning data output by the positioning module as the positioning result output by the positioning algorithm of the host vehicle, the original data required by the positioning module as the positioning data sensed by the host vehicle sensor.

[0060] In one embodiment of the present application, the positioning data output by the positioning module includes any one or more of: laser SLAM data, visual SLAM data, high-precision map data, GPS data, RTK data, and the original data required by the positioning module includes any one or more of: original point cloud data, original camera image data, road surface marking data in the original high-precision map, original GNSS data.

[0061] Taking the tunnel scenario as an example, a detailed description will be given.

[0062] The positioning data output by the positioning module includes but is not limited to laser SLAM, which mainly includes the lateral laser SLAM positioning result. Visual SLAM, which mainly includes the longitudinal visual SLAM positioning result. The positioning results of lane lines, road surface markings, road edge positioning results, etc. in the high-precision map. GPS and RTK are used as GNSS positioning results. The accuracy of GPS is relatively low, and the accuracy of RTK is relatively high and can reach the millimeter level.

[0063] The original data required by the positioning module mainly includes the original data collected by the vehicle's own sensors, namely, the original point cloud data, the original camera image data, the road marking data in the original high-precision map, the original GNSS data, etc.

[0064] In an embodiment of the present application, determining the positioning evaluation result of the vehicle in the target scenario according to the positioning true value signal of the vehicle and the positioning signal of the vehicle includes: when the simulated scenario is a tunnel scenario, determining the positioning evaluation results of the vehicle entering and exiting the tunnel scenario according to the positioning true value signal of the vehicle and the positioning signals of the vehicle in the simulated stage of entering the tunnel scenario and the simulated stage of exiting the tunnel scenario; and / or, when the simulated scenario is a non-tunnel scenario, determining the positioning evaluation result of the vehicle on the normal road according to the positioning true value signal of the vehicle and the positioning signal of the vehicle on the normal road.

[0065] Taking the tunnel scenario as an example, a detailed description is given.

[0066] When the simulated scenario is a tunnel scenario, according to the positioning true value signal of the vehicle and the positioning signals of the vehicle in the simulated stage of entering the tunnel scenario and the simulated stage of exiting the tunnel scenario, the positioning evaluation results of the vehicle entering and exiting the tunnel scenario within the entire tunnel scenario are obtained.

[0067] Taking the non-tunnel scenario as an example, a detailed description is given.

[0068] According to the positioning true value signal of the vehicle and the positioning signal of the vehicle on the normal road, the positioning evaluation result of the vehicle on the normal road is obtained, that is, the error between the positioning result of the positioning algorithm in the positioning module of the vehicle and the positioning true value signal of the vehicle is evaluated.

[0069] In an embodiment of the present application, determining the positioning evaluation result of the vehicle in the target scenario according to the positioning true value signal of the vehicle and the positioning signal of the vehicle includes: inputting the positioning true value signal of the vehicle and the positioning signal of the vehicle into a pre-established positioning evaluation system, and the configuration file corresponding to each vehicle model can be updated in the positioning evaluation system; based on the configuration file corresponding to each vehicle model, the positioning evaluation system performs data analysis on the positioning signal of the vehicle and the positioning true value signal of the vehicle, and outputs the positioning evaluation result.

[0070] Equip the positioning true value device on the vehicle to collect the true value data for evaluation. This not only ensures synchronous real-time collection and time stamp synchronization, but also guarantees the accuracy of the positioning data.

[0071] The vehicle starts the autonomous driving mode to collect positioning data, and during this period, the shielding device is turned on to collect positioning data in a simulated tunnel scene. The collected positioning data includes not only the output data of the positioning module, but also the original data required by the positioning module, so as to facilitate the iterative update and verification of the positioning algorithm. For example, the positioning algorithm needs to be verified when the algorithm from version V1 is iterated to version V2. By re-injecting the positioning data, the positioning result of the process node or the final output can be obtained.

[0072] Furthermore, the collected true value data is analyzed and processed, and the true value data and the positioning collected data are then imported into the database of the automated evaluation pipeline.

[0073] like Figure 4 As shown, an automated positioning evaluation pipeline is established.

[0074] The establishment of an automated pipeline can achieve one-click evaluation of positioning data and display the results to emails and platform systems. The specific process is as follows:

[0075] First, build the Jenkins service on the domain controller, pull the positioning evaluation code, and pull the corresponding image running environment.

[0076] Then, update the relevant configuration files, and each model corresponds to different calibration parameters. For example, considering that the vehicles to be tested (calibration results can be bound based on the license plate number) may be distributed in different regions (different cities or the same different regions), the internal and external calibration parameters of different models (for example, robobus, robotaxi) are different. Therefore, in order to make the data volume of positioning evaluation more objective, it is necessary to cover cities and models, and adjust the calibration parameters. In addition, due to different cities or the same different regions, the corresponding high-precision map data needs to be imported. At the same time, SLAM also needs to be matched and changed.

[0077] Finally, start each submodule process in the positioning module (such as laser, vision), start the packet recording process, obtain relevant data and logs, start the packet broadcasting process, perform data re-injection operation (injection of original data), and conduct evaluation after the packet broadcasting is completed. Perform data analysis on the positioning output value and the true value, and output the results. It can be understood that the log includes but is not limited to the breakpoints of the data when an error is reported or the buried point data during the test, the field display data for easy visualization, and the longitude and latitude information of the positioning.

[0078] Based on the above positioning evaluation automated pipeline, it is possible to achieve one-key automated evaluation for the evaluation work that previously involved a lot of manual participation. The evaluation steps are simple, and there are multiple evaluation modes to choose from. Through time comparison, the establishment of the positioning evaluation automated pipeline has improved the evaluation efficiency from 8 hours before to 0.5 hours now. It is also possible to achieve offline simulation evaluation. Based on the collected positioning data + new algorithm processes, the accuracy of the new positioning algorithm can be iteratively evaluated, eliminating the need for real vehicle testing, and significantly optimizing the development efficiency and verification cost of the positioning algorithm.

[0079] In an embodiment of the present application, it further includes: by controlling the signal shielding device, adjusting the space that blocks the RTK antenna of the host vehicle to change the satellite signal strength received by the RTK antenna; the degrees of satellite signal received by the RTK antenna include: the first receiving state, the weakening state, the weakening to zero state, the signal reception always being zero state, the strengthening state, and the second receiving state. The first receiving state and the second receiving state are the receiving states of the RTK signal when the satellite signal strength is normal; the simulated scenarios in response to the degrees of satellite signal received by the RTK antenna include: the host vehicle has not entered the simulated scenario, the host vehicle is entering the simulated scenario, the host vehicle has entered the simulated scenario, the host vehicle is continuously driving in the simulated scenario, the host vehicle is exiting the simulated scenario, and the host vehicle has exited the simulated scenario.

[0080] It can be understood that the simulated scenarios include but are not limited to simulated tunnels, simulated elevated roads, simulated basements and other scenarios.

[0081] Taking the tunnel scenario as an example, the GNSS antenna is taken as an example of the RTK signal for detailed description.

[0082] In the tunnel scenario, the number of satellites that the in-vehicle RTK can receive is 0, resulting in the failure of the RTK. Therefore, a signal shielding device is installed above the vehicle RTK antenna to simulate the situation of RTK failure. When the signal shielding device is turned on, the RTK function fails, and the tunnel scenario simulation stage is carried out. When the signal shielding device is turned off, the RTK function is restored, and the tunnel scenario simulation stage is exited. Therefore, based on this signal shielding device, tunnel positioning scenarios can be simulated on any urban / high-speed road, and there are great improvements in terms of quantity, diversity, safety, and acquisition efficiency.

[0083] During the process of the signal shielding device changing from fully open → slowly closing → fully closed → maintaining the closed state → slowly opening → fully open, the degree of satellite signal received by the RTK antenna is: fully received → slowly weakening → weakening to zero → signal reception always being zero → slowly strengthening → fully received. The tunnel scenario simulated thereby is: not entering the tunnel → entering the tunnel process → fully entering the tunnel → continuously driving in the tunnel → exiting the tunnel process → fully exiting the tunnel.

[0084] Further, the starting point, ending point, and duration of the road section to be tested can be pre-calibrated, and the opening speed of the signal shielding device can be adjusted. Thus, when the vehicle passes through the target road section, it is opened or closed according to the opening speed of the signal shielding device and the calibrated starting and ending points and duration.

[0085] By adopting the above method, the data and diversity of the automatic driving tunnel positioning scenario can be increased. The data simulating the tunnel positioning scenario can be collected on urban streets, which greatly reduces the collection difficulty and greatly improves the collection efficiency. Moreover, there are various types of urban streets, including streets with various lengths and curvatures, which increases the diversity of the simulated tunnel positioning scenario.

[0086] In an embodiment of the present application, the positioning evaluation result includes a positioning algorithm evaluation result, and the method further includes: when a new positioning algorithm needs to be evaluated, output a new positioning evaluation result according to the positioning signal of the vehicle and the new positioning algorithm; perform visual display through any one or more of instant messaging software, emails, and data platforms according to the new positioning evaluation result.

[0087] After the positioning algorithm is updated again, the operation is re-executed to evaluate the latest positioning algorithm. The generated results are automatically edited into an email and sent to relevant personnel, and the result data is sent to the data display platform for display.

[0088] By starting an automated pipeline, new positioning data can be output based on the collected positioning data and the new positioning algorithm. The new positioning algorithm is evaluated and the results are output. The results are automatically sorted out and displayed through three ways including but not limited to enterprise communication software, emails, and data platforms.

[0089] The embodiment of the present application also provides an automatic driving positioning evaluation device 300, as Figure 3 shown, which provides a structural schematic diagram of the automatic driving positioning evaluation device in the embodiment of the present application. The automatic driving positioning evaluation device 300 at least includes: a response module 310 and a determination module 320, where:

[0090] In an embodiment of the present application, the response module 310 is specifically configured to: in response to the automatic driving mode of the vehicle, obtain the positioning signal and the positioning true value signal of the vehicle.

[0091] The host vehicle serves as a data acquisition carrier for autonomous driving positioning evaluation. By responding to the autonomous driving mode of the host vehicle, the positioning signal of the host vehicle is obtained. It can be understood that the positioning signal of the host vehicle includes, but is not limited to, the positioning data output by the positioning module of the host vehicle in the autonomous driving mode, the original positioning data required by the positioning module when outputting the positioning data, or the node positioning data respectively output by each node in the positioning module.

[0092] Meanwhile, it is also necessary to obtain the true positioning signal of the host vehicle. It can be understood that the true positioning signal of the host vehicle can be collected by a true value device installed on the host vehicle.

[0093] It should be noted that the positioning signal of the host vehicle and the true positioning signal of the host vehicle are obtained simultaneously through the host vehicle, which can ensure timestamp synchronization.

[0094] In an embodiment of the present application, the determination module 320 is specifically configured to: determine the positioning evaluation result of the host vehicle in the target scenario according to the true positioning signal of the host vehicle and the positioning signal of the host vehicle, where the positioning signal of the host vehicle is used as the corresponding positioning signal in the target scenario, and the target scenario includes a simulated scenario.

[0095] According to the true positioning signal of the host vehicle and the positioning signal of the host vehicle, the positioning evaluation result of the host vehicle in the target scenario can be determined. For example, by comparing the difference between the true positioning signal of the host vehicle and the positioning signal of the host vehicle, the error result can be determined. Another example is that by comparing the difference between the true positioning signal of the host vehicle and the output result of the positioning algorithm after the positioning signal of the host vehicle is looped back for testing, the error result can be determined.

[0096] It can be understood that the positioning signal of the host vehicle is used as the corresponding positioning signal in the target scenario. At this time, it includes, but is not limited to, the original positioning data (the data sensed by the host vehicle sensor), the positioning result of the host vehicle output by the positioning module (the positioning result output by the positioning algorithm), and the positioning results respectively output by each node (laser node, vision node) in the positioning module.

[0097] In an embodiment of the present application, the host vehicle includes a signal shielding device and a true value positioning device. The host vehicle includes a positioning module, and the response module 310 is further configured to

[0098] Respond to the autonomous driving mode of the host vehicle, activate the signal shielding device to obtain a simulated scenario;

[0099] Based on the simulated scenario, obtain the positioning signal of the host vehicle. The positioning signal of the host vehicle includes at least one of the following: the positioning data output by the positioning module, the original data required by the positioning module;

[0100] Based on the true value positioning device, synchronously obtain the positioning true value signal of the host vehicle.

[0101] In an embodiment of the present application, the positioning data output by the positioning module includes any one or more of laser SLAM data, visual SLAM data, high-precision map data, GPS data, and RTK data. The original data required by the positioning module includes any one or more of original point cloud data, original camera image data, road surface marking data in the original high-precision map, and original GNSS data.

[0102] In an embodiment of the present application, the determination module 320 is further configured to

[0103] When the simulated scenario is a tunnel scenario, according to the positioning true value signal of the host vehicle and the positioning signals of the host vehicle when entering and exiting the tunnel scenario simulation stage, determine the positioning evaluation results of the host vehicle entering and exiting the tunnel scenario;

[0104] And / or,

[0105] When the simulated scenario is a non-tunnel scenario, according to the positioning true value signal of the host vehicle and the positioning signal of the host vehicle on the normal road, determine the positioning evaluation result of the host vehicle on the normal road.

[0106] In an embodiment of the present application, the determination module 320 is further configured to

[0107] Input the positioning true value signal of the host vehicle and the positioning signal of the host vehicle into a pre-established positioning evaluation system, and the configuration file corresponding to each vehicle model can be updated in the positioning evaluation system;

[0108] Based on the configuration file corresponding to each vehicle model, perform data analysis on the positioning signal of the host vehicle and the positioning true value signal of the host vehicle according to the positioning evaluation system, and output the positioning evaluation result.

[0109] In an embodiment of the present application, it further includes a control module for

[0110] By controlling the signal shielding device, adjust the space blocking the RTK antenna of the host vehicle to change the satellite signal reception intensity of the RTK antenna;

[0111] The satellite signal reception degree of the RTK antenna includes: the first reception state, the weakening state, the weakening to zero state, the signal reception always being zero state, the strengthening state, and the second reception state. The first reception state and the second reception state are the RTK signal reception states when the satellite signal intensity is normal.

[0112] The tunnel scenarios in response to the satellite signal reception level simulation by the RTK antenna include: the vehicle not entering the tunnel, the vehicle entering the tunnel, the vehicle entering the tunnel, the vehicle continuously driving in the tunnel, the vehicle exiting the tunnel, and the vehicle exiting the tunnel.

[0113] In an embodiment of the present application, the determining module is further configured to,

[0114] When a new positioning algorithm needs to be evaluated, output a new positioning evaluation result according to the positioning signal of the vehicle and the new positioning algorithm;

[0115] Visualize and display according to the new positioning evaluation result through any one or more of instant messaging software, emails, and data platforms.

[0116] It can be understood that the above-mentioned automatic driving positioning evaluation device can implement each step of the automatic driving positioning evaluation method provided in the foregoing embodiment. The relevant explanations regarding the automatic driving positioning evaluation method are applicable to the automatic driving positioning evaluation device and will not be elaborated here.

[0117] Figure 5 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 5 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0118] The processor, network interface, and memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 5 only a bidirectional arrow is used in

[0119] A memory for storing programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

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

[0121] In response to the automatic driving mode of the host vehicle, obtain the positioning signal and the positioning true value signal of the host vehicle;

[0122] Determine the positioning evaluation result of the host vehicle in the target scenario according to the positioning true value signal and the positioning signal of the host vehicle;

[0123] Wherein, the positioning signal of the host vehicle is used as the corresponding positioning signal in the target scenario, and the target scenario includes a simulation scenario.

[0124] The above as in this application Figure 2The method executed by the automatic driving positioning evaluation device disclosed in the illustrated embodiment can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method can be completed by the integrated logic circuit in the hardware of the processor or instructions in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may 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, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0125] The electronic device can also execute Figure 2 the method executed by the automatic driving positioning evaluation device in Figure 2 the illustrated embodiment and implement the functions of the automatic driving positioning evaluation device in

[0126] Embodiments of the present application also propose a computer-readable storage medium that stores one or more programs. The one or more programs include instructions that, when executed by an electronic device including multiple application programs, can enable the electronic device to execute Figure 2 the method executed by the automatic driving positioning evaluation device in the illustrated embodiment and specifically used to execute:

[0127] In response to the automatic driving mode of the vehicle itself, obtain the positioning signal and the positioning true value signal of the vehicle itself;

[0128] Determine the positioning evaluation result of the vehicle itself in the target scenario according to the positioning true value signal and the positioning signal of the vehicle itself;

[0129] Among them, the positioning signal of the host vehicle is used as the corresponding positioning signal in the target scenario, and the target scenario includes a simulation scenario.

[0130] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0132] These computer program instructions can 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, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0134] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0135] The 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. The memory is an example of a computer-readable medium.

[0136] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 disk read-only memory (CD-ROM), digital versatile disk (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 temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0137] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0138] 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 adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0139] The above is only 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 principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for evaluating positioning of an autonomous driving system, wherein: The positioning evaluation method comprises: In response to the automatic driving mode of the vehicle, obtaining a positioning signal of the vehicle and a true positioning signal of the vehicle; Determining a positioning evaluation result of the ego vehicle in the target scene according to the ego vehicle positioning true value signal and the ego vehicle positioning signal; The positioning signal of the vehicle is used as a corresponding positioning signal in a target scene, and the target scene includes a simulation scene.

2. The method of claim 1, wherein: The self-vehicle includes a signal shielding device and a true value positioning device, and the self-vehicle includes a positioning module. The self-vehicle positioning signal and the self-vehicle positioning true value signal are obtained in response to the automatic driving mode of the self-vehicle, including: In response to the autonomous driving mode of the vehicle, a signal shielding device is activated to obtain a simulated scenario; Based on the simulation scenario, obtaining a positioning signal of the vehicle, wherein the positioning signal of the vehicle includes at least one of the following: positioning data output by the positioning module and raw data required by the positioning module; Based on the true value positioning device, the positioning true value signal of the vehicle is synchronously acquired.

3. The method of claim 2, wherein: The positioning data output by the positioning module includes: any one or more of laser SLAM data, visual SLAM data, high-precision map data, GPS data, and RTK data; the original data required by the positioning module includes: any one or more of original point cloud data, original camera image data, original road marking data in high-precision maps, and original GNSS data.

4. The method of claim 1, wherein: The determining, according to the positioning true value signal of the ego vehicle and the positioning signal of the ego vehicle, a positioning evaluation result of the ego vehicle in the target scene includes: When the simulation scene is a tunnel scene, determining the positioning evaluation results of the ego vehicle entering and exiting the tunnel scene according to the positioning true value signal of the ego vehicle and the positioning signals of the ego vehicle in the simulation stage of entering the tunnel scene and the simulation stage of exiting the tunnel scene; and / or, When the simulation scene is a non-tunnel scene, the positioning evaluation result of the ego vehicle on the normal road is determined according to the true positioning signal of the ego vehicle and the positioning signal of the ego vehicle on the normal road.

5. The method of claim 4, wherein: The determining, according to the positioning true value signal of the ego vehicle and the positioning signal of the ego vehicle, a positioning evaluation result of the ego vehicle in the target scene includes: Inputting the positioning true value signal of the vehicle and the positioning signal of the vehicle into a pre-established positioning evaluation system, wherein the configuration file corresponding to each vehicle type can be updated in the positioning evaluation system; Based on the configuration files corresponding to each vehicle type, the positioning evaluation system performs data analysis on the positioning signal of the vehicle and the true value signal of the positioning of the vehicle, and outputs a positioning evaluation result.

6. The method of claim 2, wherein: Also includes: By controlling the signal shielding device, the space shielding the RTK antenna of the vehicle is adjusted to change the strength of the satellite signal received by the RTK antenna; The degree of receiving satellite signals by the RTK antenna includes: a first receiving state, a weakened state, a weakened zero state, a signal receiving zero state, a strengthened state, and a second receiving state. The first receiving state and the second receiving state are the receiving states of the RTK signal when the satellite signal strength is normal. The simulation scenarios simulated in response to the degree of satellite signal reception by the RTK antenna include: the vehicle does not enter the simulation scenario, the vehicle enters the simulation scenario, the vehicle enters the simulation scenario, the vehicle continues to drive in the simulation scenario, the vehicle exits the simulation scenario, and the vehicle exits the simulation scenario.

7. The method of claim 1, wherein: The positioning evaluation result includes a positioning algorithm evaluation result, and the method further includes: When a new positioning algorithm needs to be evaluated, a new positioning evaluation result is output according to the positioning signal of the vehicle and the new positioning algorithm; The new positioning evaluation result is visualized through any one or more of instant messaging software, email, and data platform.

8. An automatic driving positioning evaluation device, wherein: The device comprises: A response module, configured to obtain a positioning signal of the vehicle and a true positioning signal of the vehicle in response to the automatic driving mode of the vehicle; A determination module, used to determine a positioning evaluation result of the ego vehicle in a target scene according to the positioning true value signal of the ego vehicle and the positioning signal of the ego vehicle; The positioning signal of the vehicle is used as a corresponding positioning signal in a target scene, and the target scene includes a simulation scene.

9. 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 7.

10. 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 any one of the methods of claims 1 to 7.

Images