阅读说明：本技术 路侧系统的定位性能评估方法、存储介质及车路协同系统 (Positioning performance evaluation method of road side system, storage medium and vehicle-road cooperative system ) 是由 李波 刘续博 姜乐 高瑞金 吴璇琪 于 2021-07-27 设计创作，主要内容包括：本发明涉及一种路侧系统的定位性能评估方法、存储介质及车路协同系统,所述方法包括以下步骤：分别实时获取带有时间戳数据的数据标准车的自车定位信息和路侧系统得到的目标定位信息；对所述自车定位信息和目标定位信息进行对齐处理,获得对齐后的定位数据；基于所述对齐后的定位数据实时计算获得路侧系统的单一准确度评估结果；基于设定时间内获得的所述对齐后的定位数据来统计评估路侧系统的定位准确度。与现有技术相比,本发明利用车端系统较成熟的优势,以简便的方式对路侧系统性能进行评估,可以获得可靠的评估结果,并辅助路侧系统提高性能,对车路协同技术的发展具有重要意义。(The invention relates to a positioning performance evaluation method of a road side system, a storage medium and a vehicle-road cooperation system, wherein the method comprises the following steps: respectively acquiring the self-vehicle positioning information of the data standard vehicle with the timestamp data and the target positioning information acquired by the road side system in real time; aligning the self-vehicle positioning information and the target positioning information to obtain aligned positioning data; calculating in real time to obtain a single accuracy evaluation result of the road side system based on the aligned positioning data; and statistically evaluating the positioning accuracy of the road side system based on the aligned positioning data obtained in a set time. Compared with the prior art, the method and the system have the advantages that the mature advantages of the vehicle end system are utilized, the performance of the roadside system is evaluated in a simple and convenient mode, a reliable evaluation result can be obtained, the roadside system is assisted to improve the performance, and the method and the system have important significance for the development of the vehicle-road cooperation technology.)

1. A positioning performance evaluation method of a road side system is characterized by comprising the following steps:

respectively acquiring the self-vehicle positioning information of the data standard vehicle and the target positioning information acquired by the road side system in real time;

aligning the self-vehicle positioning information and the target positioning information to obtain aligned positioning data;

obtaining a single accuracy evaluation result of the road side system based on the aligned positioning data through real-time online calculation;

and obtaining a positioning accuracy evaluation result of the road side system based on the aligned positioning data obtained in the set time.

2. The method of claim 1, wherein the self-vehicle positioning information comprises position, orientation, speed and time stamp of a data standard vehicle, and the target positioning information comprises position, orientation and speed of each target and a uniform time stamp.

3. The positioning performance evaluation method of the roadside system according to claim 1, wherein the alignment process includes a time alignment operation and a space alignment operation.

4. The method for evaluating the positioning performance of the roadside system according to claim 3, wherein the time alignment operation is specifically:

taking the moment of currently received target positioning information of the road side system as reference time, and adjusting the latest acquired self-vehicle positioning information to the self-vehicle positioning information at the reference time;

the spatial alignment operation is specifically:

screening out one target information with the minimum absolute distance to the data standard workshop at the same time from the target positioning information as matching target information;

and forming aligned positioning data by the self-vehicle positioning information and the matched target information at the reference time.

5. The method for evaluating the positioning performance of the roadside system according to claim 4, wherein the adjusting the latest acquired own vehicle positioning information to the own vehicle positioning information at the reference time:

and calculating and obtaining the self-vehicle positioning information at the reference time according to the recently obtained self-vehicle positioning information by a Kalman filtering method.

6. The positioning performance evaluation method of a roadside system according to claim 1, characterized in that a degree of coincidence between the own vehicle positioning information and the matching target information at the first time is taken as the single accuracy evaluation result;

the degree of coincidence is determined based on one or more of a position error, an orientation error, and a speed error of the own vehicle and the matching target.

7. The positioning performance evaluation method of the roadside system according to claim 1, wherein the positioning accuracy evaluation result includes a relative pose error and an absolute track error within m time instants.

8. The method for evaluating the positioning performance of the roadside system according to claim 1, further comprising:

visualizing the single accuracy assessment result and the positioning accuracy assessment result.

9. A computer-readable storage medium comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing the method for location performance evaluation of a roadside system as recited in any one of claims 1-8.

10. A vehicle road coordination system, characterized in that a computer readable storage medium according to claim 9 is deployed.

Technical Field

The invention belongs to the technical field of vehicle-road cooperation, and particularly relates to a positioning performance evaluation method of a road side system, a storage medium and a vehicle-road cooperation system.

Background

With the continuous development of the current intelligent technology, information technology and the like, the key points of the automobile industry have been shifted to the intelligent transportation field from the traditional automobile manufacturing industry. At present, systems such as sensing, positioning, planning and control based on a bicycle system are developed more mature, but due to the limitation of limited scope of bicycle sensing and high cost of sensors, the wide-area general application is difficult to realize.

With the development of communication technology in recent years, the vehicle-road cooperation technology has gained wide attention. The vehicle-road cooperation technology can use the road side equipment and the vehicle end equipment to jointly sense the environmental information, overcomes the defect of limited sensing range of a single vehicle, greatly enlarges the sensing visual field of the single vehicle, enables the vehicle to understand the global environment, and makes a decision and controls better. In addition, by installing the sensor at the roadside, the cost of the sensor can be considered to be equally divided by each vehicle user in the system, and the cost is greatly reduced. In conclusion, the vehicle-road cooperation technology has wide application prospect.

At present, the vehicle-road cooperation technology is still immature, and a large amount of research results are still needed. How to evaluate the vehicle-road cooperative system is a crucial issue, and one of the very important aspects is the evaluation of the performance of the road-side system. A good evaluation method has guiding significance for research and development and improvement of the technology in the future. However, at present, the direct performance evaluation of the roadside system is difficult, and the performance evaluation of the roadside system is difficult to accurately carry out.

Disclosure of Invention

The present invention aims to overcome the defects of the prior art and provide an accurate and effective road side system positioning performance evaluation method, storage medium and vehicle and road cooperation system.

The purpose of the invention can be realized by the following technical scheme:

in a first aspect, the present invention provides a method for evaluating positioning performance of a roadside system, including the following steps:

respectively acquiring the self-vehicle positioning information of the data standard vehicle and the target positioning information acquired by the road side system in real time;

aligning the self-vehicle positioning information and the target positioning information to obtain aligned positioning data;

obtaining a single accuracy evaluation result of the road side system based on the aligned positioning data through real-time online calculation;

and obtaining a positioning accuracy evaluation result of the road side system based on the aligned positioning data obtained in the set time.

Further, the self-vehicle positioning information comprises the position, the orientation, the speed and the time stamp of the data standard vehicle, and the target positioning information comprises the position, the orientation and the speed of each target and a uniform time stamp.

Further, the alignment process includes a temporal alignment operation and a spatial alignment operation.

Further, the time alignment operation specifically includes:

taking the moment of currently received target positioning information of the road side system as reference time, and adjusting the latest acquired self-vehicle positioning information to the self-vehicle positioning information at the reference time;

the spatial alignment operation is specifically:

screening out one target information with the minimum absolute distance to the data standard workshop at the same time from the target positioning information as matching target information;

and forming aligned positioning data by the self-vehicle positioning information and the matched target information at the reference time.

Further, the latest acquired own vehicle positioning information is adjusted to the own vehicle positioning information at the reference time:

and calculating and obtaining the self-vehicle positioning information at the reference time according to the recently obtained self-vehicle positioning information by a Kalman filtering method.

Further, the consistency degree of the self-vehicle positioning information and the matching target information at the first time is used as the single accuracy evaluation result;

the degree of coincidence is determined based on one or more of a position error, an orientation error, and a speed error of the own vehicle and the matching target.

Further, the positioning accuracy evaluation result includes relative pose errors and absolute track errors within m time instants.

Further, the method further comprises:

visualizing the single accuracy assessment result and the positioning accuracy assessment result.

In a second aspect, the invention provides a computer readable storage medium comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing the method for location performance evaluation of a roadside system as described above.

In a third aspect, the present invention provides a vehicle-road coordination system, which is disposed with the computer-readable storage medium as described above.

Compared with the prior art, the invention has the following beneficial effects:

1. the invention evaluates the positioning performance of the road side system through the set data standard vehicle, and is accurate and effective.

2. The method and the device perform alignment processing on the acquired positioning information, perform positioning performance evaluation on the road side system by using the aligned positioning data, and effectively improve the reliability of performance evaluation.

3. The alignment processing comprises time alignment operation and space alignment operation, and can comprehensively preprocess roadside data acquired in real time and ensure the accuracy of an evaluation result.

4. The invention can be deployed in the existing vehicle-road cooperative systems, and provides effective guidance for the technical development of the future road-side positioning system by effectively evaluating the positioning performance of the road-side system and assisting the road-side system to improve the performance.

Drawings

FIG. 1 is a schematic view of a usage scenario of the present invention;

FIG. 2 is a schematic diagram of an embodiment of the present invention;

FIG. 3 is a schematic diagram of the time alignment operation of the present invention;

FIG. 4 is a schematic diagram of evaluation result acquisition;

FIG. 5 is a schematic diagram of an implementation framework of the invention.

Detailed Description

The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.

Aiming at the problem that the performance evaluation of a roadside system in a vehicle-road cooperative system is difficult, the invention provides a positioning performance evaluation method of the roadside system, which comprises the following steps: respectively acquiring the self-vehicle positioning information of the data standard vehicle and the target positioning information acquired by the road side system in real time; aligning the self-vehicle positioning information and the target positioning information to obtain aligned positioning data; calculating to obtain a single accuracy evaluation result of the road side system based on the aligned positioning data; and calculating to obtain a statistical accuracy evaluation result of the road side system based on the aligned positioning data obtained in the set time. The method uses a data standard vehicle capable of realizing accurate self-positioning as a true value to evaluate the road side system, and has high accuracy and reliability.

The positioning performance evaluation method of this embodiment may be applied to a usage scenario as shown in fig. 1, where in the usage scenario, the vehicle positioning information is acquired by an on-board unit OBU installed on a data standard vehicle with accurate positioning performance, the OBU may upload the vehicle positioning information in real time, the target positioning information is acquired by a road side unit RSU of a road side system, and the RSU may upload the acquired target positioning information of all targets in real time, in the scenario, the OBU and the RSU upload data to a computing device, and the computing device performs positioning performance evaluation of the road side system.

As shown in fig. 2, the method for evaluating the positioning performance of the roadside system in the use scenario includes the following steps:

s1: and the vehicle-mounted unit and the road side unit respectively collect positioning information in real time, and stamp the obtained information with a time stamp and upload the information to the computing equipment for further evaluation.

In this embodiment, the computing device may be a cloud computing platform, or may be any computing device such as a locally deployed computer and an embedded platform.

And S1a, acquiring and uploading the positioning information of the vehicle-mounted unit. The vehicle-mounted unit of the data standard vehicle at each moment can obtain an accurate self-vehicle positioning result, the positioning result at each moment is stamped with a time stamp, and the positioning result can be packaged and uploaded to the computing equipment in a wired network or wireless network mode.

The vehicle positioning information uploaded to the computing device each time comprises the position, the orientation, the speed and the timestamp obtained by the vehicle positioning module:

(x,y,yaw,v,t)

wherein (x, y) is the position of the obtained self-vehicle positioning, yaw is the yaw angle, namely the orientation information of the self-vehicle, v is the speed of the self-vehicle, and t is the time stamp, namely the time of the positioning information.

And S1b, collecting and uploading positioning information of the road side unit. Different from the vehicle-mounted system, the vehicle-mounted system can only obtain one piece of positioning information at each moment, namely the self-vehicle positioning information of the data standard vehicle; and the roadside system may obtain location information for all targets within a sensing range in the traffic environment. In this embodiment, the positioning information of all targets obtained by the roadside system at each moment is packaged into a group, a timestamp is stamped for the group of data, and the group of data is packaged and uploaded to the computing device.

The target positioning information uploaded to the computing device each time comprises the position, the orientation and the speed of each target obtained by the road side system and a uniform timestamp:

{(x₁,y₁,yaw₁,v₁),…,(x_n,y_n,yaw_n,v_n),t}

n is the number of targets obtained by the roadside system at the same time, (x)_i,y_i) Is the position of the ith target therein, yaw_iYaw orientation information, v, for the ith target_iAnd t is a uniform time stamp, namely the time for obtaining the set of positioning information, which is the speed of the ith target.

S2: the obtained data of the on-board unit and the roadside unit are aligned and the accuracy of the roadside unit is evaluated in real time as shown in fig. 4.

The data of the on-board unit and the data of the road side unit need to be preprocessed before subsequent evaluation. According to the method, the alignment process comprises a time alignment operation and a space alignment operation. The timestamps of the on-board unit data and the road side unit data obtained by the computing equipment are different, so that the time alignment operation is needed; in addition, each set of data of the road side unit contains a plurality of targets in the sensing range, so that it is necessary to judge that the target information is information of the data standard vehicle, namely, the spatial alignment operation.

Step S2a, time alignment operation. And taking the time of the road side data as reference time, and aligning the latest data uploaded by the vehicle-mounted unit to the time of the road side data according to time when data transmitted from a group of road side systems are obtained every time.

Namely, the time stamp of the current group of road side data is set as t_rThe last data received by the on-board unit is (x)_on,y_on,yaw_on,v_on,t_on) Applying Kalman filtering method to calculate the t-th_rInformation on the on-board unit's own vehicle location, speed, etc. at the time, i.e. (x)_or,y_or,yaw_or,v_or,t_r) Thus, the time alignment of the vehicle-mounted unit data and the road side unit data is completed, and a schematic diagram is shown in fig. 3.

And S2b, performing space alignment operation. The data obtained by the road side unit are all targets in the sensing range, and the target information needs to be judged to be the information of the data standard vehicle. In the embodiment of the invention, the minimum absolute distance between the target position in the multiple target data of the road side and the positioning position information of the vehicle is selected as the matched same target information, namely the positioning information of the standard vehicle.

And forming aligned positioning data by the self-vehicle positioning information and the matched target information at the reference time, so as to complete the space alignment operation of the vehicle-mounted unit data and the road side unit data.

S2c, formally performing online evaluation of the computing device, as shown in the left half of FIG. 4. This step is a real-time assessment of the accuracy of the roadside units. After the data alignment, the accuracy of the road side unit is evaluated by taking the self-vehicle positioning information of the data standard vehicle as a true value. And each time data information of the road side unit is received, once evaluation is carried out, and an evaluation result is output.

The embodiment designs a series of online evaluation indexes which measure the consistency degree of the positioning from the road side unit and the self-positioning of the data standard vehicle, including the position error e_pOrientation error e_dAnd a speed error e_vAs a single accuracy assessment result.

The positioning information of the data standard vehicle is expressed as (x)_o,y_o,yaw_o,v_o) The positioning information obtained by the roadside is represented as (x)_r,y_r,yaw_r,v_r)；

Position error e_p：

Orientation error e_d：

e_d＝yaw_r-yaw_o

Error in velocity e_v：

e_v＝v_r-v_o

S3: statistical evaluation of the accuracy of the roadside unit over a period of time is performed based on the stored aligned data of the on-board unit and the roadside unit, as shown in fig. 4.

And S3a, storing the positioning information obtained by the vehicle-mounted unit and the road side unit for use when statistical evaluation is required.

The statistical evaluation in this embodiment refers to the statistical evaluation of the accuracy of the roadside unit over a period of time. After the data are aligned, the positioning information obtained by the vehicle-mounted unit and the road side unit is stored, when the estimation is needed, the accuracy of the road side unit in a period of time is estimated by using the data stored in the period of time, and the estimation time period is determined by a system user.

An S3b step of performing statistical evaluation of the computing device according to the user-specified time period using the data stored in the S3a step. In the time range specified by the user, the statistical evaluation and evaluation is the performance of the positioning system of the road side unit in a period of time, and the statistical evaluation and evaluation index of the embodiment includes:

the position error at the ith time is recorded as e_piCalculating the average value e of the statistical position error of the bicycle_paStandard deviation e_psMaximum value e_pm：

The orientation error at the ith time is recorded as e_diCalculating the mean value e of the statistical orientation error of the bicycle_daStandard deviation e_dsMaximum value e_dm：

The speed error at the ith time is recorded as e_viCalculating the average value e of the statistical speed error of the bicycle_vaStandard deviation e_vsMaximum value e_vm：

Marking the pose obtained by the road side system at the ith moment as P_iAnd the pose obtained by the vehicle-mounted unit at the ith moment is recorded as Q_iAnd calculating relative pose errors RTE within m moments, wherein the time interval of each time is delta:

calculating the absolute track error ATE in n moments:

where S is a rigid transformation matrix.

S4: and generating an evaluation result and a related image, and generating the related image to visualize the evaluation result.

And drawing the positioning result of the road side system and the data standard vehicle in the image in real time, drawing a corresponding measurement diagram after calculating RTE and ATE within specified time, and also visually displaying the result on an interface.

In one embodiment, a software system as shown in fig. 5 may be constructed to realize user interaction, embed software in the evaluation method, deploy on a Personal Computer (PC), and write a graphical operation interface, where the graphical interface displays real-time evaluation results in real time, and a user may customize a time period in which statistical evaluation is required to generate statistical evaluation results and visually display the results on the interface.

The method for evaluating the positioning performance of the roadside system has good universality and can be simply transplanted into all existing vehicle-road cooperative systems.

The method has the significance that the positioning performance of the roadside system can be well evaluated, so that the advantages and disadvantages of different roadside system positioning technologies are compared, and reliable guidance is provided for improvement of the roadside system positioning technology in the future; meanwhile, the method for evaluating the performance of the roadside system by using the data standard vehicle can provide a new idea for evaluating the performance of the roadside system in future.

The above functions, if implemented in the form of software functional units and sold or used as a separate product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.