CN114485658A - Device and method for precision evaluation of roadside sensing system - Google Patents
Device and method for precision evaluation of roadside sensing system Download PDFInfo
- Publication number
- CN114485658A CN114485658A CN202111490796.XA CN202111490796A CN114485658A CN 114485658 A CN114485658 A CN 114485658A CN 202111490796 A CN202111490796 A CN 202111490796A CN 114485658 A CN114485658 A CN 114485658A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- result
- data
- positioning
- roadside
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims description 44
- 238000005259 measurement Methods 0.000 claims abstract description 35
- 230000008447 perception Effects 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 238000013519 translation Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
- G01C21/1652—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments with ranging devices, e.g. LIDAR or RADAR
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C22/00—Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Abstract
The invention relates to a roadside perception system precision evaluation oriented device, which comprises: roadside perception system: the system comprises a road side sensor, a mobile edge calculation unit and a road side unit, and is used for acquiring a road side sensing result; data standard vehicle: the system comprises a laser radar, a GNSS receiver, an inertia measurement unit, a router and a vehicle-mounted unit, and is used for acquiring a self-vehicle positioning result and uploading the self-vehicle positioning result and a received roadside sensing result; cloud server: the system comprises a cloud server of the roadside sensing system and a cloud server of an evaluation system, wherein the cloud server of the roadside sensing system is used for displaying the state of the roadside sensing system in real time, and the cloud server of the evaluation system is used for evaluating the precision of the roadside sensing system and outputting an evaluation result.
Description
Technical Field
The invention relates to the field of precision evaluation of roadside sensing systems, in particular to a device and a method for precision evaluation of a roadside sensing system.
Background
In the prior art, systematic evaluation, especially on-line evaluation, is less performed on a road side sensing system, and a common evaluation mode is to confirm an evaluation result by placing a calibration board, a marker or a vehicle at a fixed position and rely on providing a more accurate true value through an external measurement means for evaluation.
In the building and testing process of the vehicle-road cooperative system, the installation positions of all sensors are determined in the prior art through modes of surveying and mapping and the like, but the deviation between the actual installation position and the actual position cannot be eliminated in a closed loop mode, so a certain error exists in the final sensing result, and the position measurement is performed in the surveying and mapping mode mainly through placing markers or vehicles in the region in the existing error evaluation mode.
The positioning accuracy of the roadside sensing system in the vehicle-road cooperation is the premise of large-scale application, the roadside sensing system can be accurately and quickly evaluated as a supplier to be built or a site owner to check and accept the system, and most of the existing accuracy evaluation work depends on static markers and a surveying and mapping mode, so that the speed is low and the evaluation under a dynamic condition cannot be performed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a device and a method for estimating the accuracy of a roadside sensing system.
The purpose of the invention can be realized by the following technical scheme:
an apparatus for precision evaluation of a roadside-oriented sensing system, the apparatus comprising:
roadside sensing system: the system comprises a road side sensor, a mobile edge calculation unit and a road side unit, and is used for acquiring a road side sensing result;
data standard vehicle: the system comprises a laser radar, a GNSS receiver, an inertia measurement unit, a router and a vehicle-mounted unit, and is used for acquiring a self-vehicle positioning result and uploading the self-vehicle positioning result and a received roadside sensing result;
cloud server: the system comprises a cloud server of the roadside sensing system and a cloud server of an evaluation system, wherein the cloud server of the roadside sensing system is used for displaying the state of the roadside sensing system in real time, and the cloud server of the evaluation system is used for evaluating the precision of the roadside sensing system and outputting an evaluation result.
The roadside sensor is used for acquiring a sensing result;
the mobile edge computing unit is connected with a cloud server of the roadside sensing system and used for computing and identifying sensing results, and uploading the sensing results to the cloud server of the roadside sensing system after obtaining the roadside sensing results;
the road side unit is used for broadcasting the acquired road side sensing result.
The laser radar and the inertia measurement unit are used in a matched mode to achieve a positioning function in an indoor environment, and an indoor self-vehicle positioning result is obtained;
the GNSS receiver and the inertial measurement unit are matched for use to realize a positioning function under an outdoor environment, and an outdoor self-vehicle positioning result is obtained;
the router is connected with a cloud server of the evaluation system and used for uploading the positioning result of the vehicle and the received positioning results of all vehicles broadcasted by the roadside sensing system to the cloud server of the evaluation system.
The cloud server of the roadside sensing system is used for displaying the state of the roadside sensing system in real time and monitoring and storing the roadside sensing result in real time;
the cloud server of the evaluation system is used for receiving the vehicle positioning result and the roadside sensing result uploaded by the router of the vehicle end, processing and analyzing the vehicle positioning result and the roadside sensing result, outputting a corresponding data comparison result, namely an evaluation result, for the purpose of evaluation, and displaying the evaluation result in real time.
A method of applying the apparatus as described, the method comprising:
step 1: the method comprises the steps that a self-vehicle positioning result is obtained, when the self-vehicle positioning device is indoors, indoor vehicle positioning is carried out through a carried laser radar and an inertial measurement unit based on a synchronous positioning and mapping technology, indoor positioning data, namely an indoor self-vehicle positioning result, is obtained, when the self-vehicle positioning device is outdoors, outdoor vehicle positioning is carried out through a carried GNSS receiver and the inertial measurement unit, and outdoor positioning data, namely an outdoor self-vehicle positioning result, is obtained;
step 2: reading a road side sensing result of RSU broadcast acquired by OBU equipment by loading an OBU drive, and cleaning and converting a data format of the road side sensing result;
and step 3: the indoor self-vehicle positioning result or the outdoor self-vehicle positioning result and the roadside sensing result are subjected to data packaging, and are uploaded to a cloud server through a router in a remote communication mode;
and 4, step 4: and (3) receiving the indoor positioning data, the outdoor positioning data and the roadside perception result broadcasted by the RSU uploaded in the step (3) through a cloud server of the deployed evaluation system, and performing data processing and calculation to obtain an evaluation result.
In the step 1, the process of obtaining the indoor self-vehicle positioning result specifically comprises the following steps:
step 101: carrying a laser radar and an inertia measurement unit on a vehicle, and calibrating the position of the vehicle to enable data generated by the laser radar to surround a vehicle body coordinate system;
step 102: the method comprises the following steps that a vehicle runs at a certain region of an indoor environment at a low speed to collect data, and the collected data are subjected to map construction through an SLAM method;
step 103: after the vehicle loads the constructed map, the vehicle drives to the area again and then starts the positioning function, the positioning function is matched with data in the map through the current data of the laser radar, so that the position and the posture of the vehicle are determined, meanwhile, the inertial measurement unit is matched for data fusion, and indoor positioning data, including high-frequency vehicle self position, posture information and speed information, are output.
In the step 102, the SLAM method includes a front-end laser radar odometer, data fusion of an inertial measurement unit, back-end optimization, and closed-loop detection.
In the step 1, the process of obtaining the outdoor self-vehicle positioning result specifically comprises the following steps:
step 104: the method comprises the steps that a GNSS receiver and an inertia measurement unit are carried on a vehicle, and the position of the vehicle is calibrated, so that data generated by the GNSS receiver surround a vehicle body coordinate system;
step 105: the vehicle starts RTK service of the GNSS receiver to obtain accurate vehicle position and attitude in a region with good signals, and meanwhile, outdoor positioning data including high-frequency vehicle self position, attitude information and speed information are output by matching with the inertial measurement unit.
In the step 103, the process of obtaining the high-frequency vehicle position, attitude information and speed information specifically includes the following steps:
step 103 a: assuming that P is the current data of the laser radar under a vehicle body coordinate system, Q is the data in a constructed map, a three-dimensional translation matrix of the vehicle body is T, a three-dimensional rotation matrix is R, and R belongs to SO (3), the sum of errors of each point in the current data of the laser radar after being changed and the nearest point of the data in the map is solved to be minimum, SO that the values of the three-dimensional rotation matrix R and the three-dimensional translation matrix T are solved, and the expression is as follows:
wherein, argminR，TRepresenting a function, p, for obtaining the value of the variable R, T at which the latter formula reaches a minimumiFor the ith point in the current data of the laser radar, qiThe method comprises the steps that the nearest point of data in a map corresponding to the ith point in the current data of the laser radar is obtained, and N is the number of points in the current data of the laser radar;
step 103 b: calculating according to the three-dimensional rotation matrix R and the three-dimensional translation matrix T to obtain the position (x) of the vehicle0，y0) And attitude information yaw0Vehicle self position (x)0，y0) And attitude information yaw0Are respectively expressed as
xo＝T1
y0＝T2
Wherein, T1And T2Are all elements of a three-dimensional translation matrix T, R32And R33Are all elements in a three-dimensional rotation matrix R;
step 103 d: obtaining vehicle speed information v according to the information of the wheel speed meter of the vehicle0。
In the step 4, the process of obtaining the evaluation result specifically includes the following steps:
step 401: based on the position information (x) in the indoor or outdoor self-vehicle positioning resulto，yo) Position information (x) of roadside sensing resultr，yr) Calculating the position error epPosition error epThe expression of (a) is:
step 402: based on the direction information yaw in the indoor or outdoor positioning result of the own vehicle0The heading information yawr of the roadside sensing result, the heading error e is calculateddOrientation error edThe expression of (a) is:
ed＝yawr-yawo；
step 403: according to speed information v in indoor or outdoor self-vehicle positioning resultsoSpeed information v of roadside perception resultrCalculating the velocity error evVelocity error evThe expression of (a) is:
ev＝vr-vo；
step 404: according to the position error, the orientation error and the speed error in a period of time, respectively calculating the root mean square values of the position error, the orientation error and the speed error, wherein the formula for calculating each root mean square value is respectively
Wherein, RMSE (e)p) Root mean square value of position error, RMSE (e)d) RMSE (e) as root mean square value of orientation errorv) Is the root mean square value of the velocity error.
Compared with the prior art, the invention has the following advantages:
1. the method can quickly and dynamically evaluate the roadside perception precision;
2. the system can provide an accurate vehicle positioning result under an outdoor road environment, comprises the position and the posture of the vehicle, can be used for establishing a point cloud map of the outdoor environment and marking the point cloud map as a high-precision map, can provide an accurate vehicle positioning result under an indoor scene, comprises the position and the posture of the vehicle, can be used for establishing a point cloud map of the indoor environment and marking the point cloud map as a high-precision map, evaluates the precision of a road side sensing system based on the high-precision positioning result of a data standard vehicle, can compare and analyze various data in a cloud evaluation server, and improves the evaluation efficiency;
3. the road side sensing result sent by the RSU can be received, and data matched with the vehicle and other sensing data are identified so as to accurately identify target vehicles around the vehicle and match the road side sensing result sent by the RSU;
4. the method can combine and upload the received road side broadcast data and the position data of the road side broadcast data and provide the road side broadcast data for remote development and operation and maintenance personnel to check;
5. the method can be suitable for different indoor and outdoor scenes, has good environmental adaptability and mobility, and can be rapidly deployed in new scenes.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
FIG. 2 is a schematic flow chart of the method of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
Examples
As shown in fig. 1, the invention provides a device for precision evaluation of a roadside sensing system, which comprises the roadside sensing system, a data standard vehicle and a cloud server, wherein the roadside sensing system comprises a roadside sensor, a mobile edge computing unit (MEC) and a roadside unit (RSU), a result sensed by the roadside sensor is computed and identified through the MEC, a roadside sensing result is obtained and broadcasted through the RSU, and the MEC uploads the obtained roadside sensing result to the cloud server to perform real-time monitoring, storage and the like on the roadside sensing result.
The data standard vehicle comprises a laser radar, a GNSS receiver, an inertia measurement unit, a 4G/5G router and an on-board unit (OBU), wherein the laser radar is matched with the inertia measurement unit to realize a high-precision positioning function in an indoor environment, the GNSS receiver is matched with the inertia measurement unit to realize the high-precision positioning function in an outdoor environment, the OBU obtains positioning results of all vehicles on the current road by receiving road side sensing results broadcasted by the RSU, and finally the router uploads the vehicle positioning results and the received positioning results of all vehicles broadcasted by the road side sensing system to a cloud server, the cloud server is summarized by an evaluation system, the evaluation result is calculated, and the evaluation result is displayed in real time.
The cloud server comprises a cloud server of the road side sensing system and a cloud server of the evaluation system, the cloud server of the road side sensing system is used for displaying states and the like of the MEC, the RSU and road side sensors in real time, even if no data standard vehicle exists, the cloud server of the evaluation system is an essential system for operation and maintenance, the cloud server of the evaluation system is used for receiving a vehicle positioning result and a road side sensing result uploaded by a router of a vehicle end, the vehicle positioning result and the road side sensing result are processed and analyzed simultaneously, and finally, a corresponding data comparison result is output for evaluation as a purpose, namely, an evaluation result is obtained, and development and maintenance personnel use the evaluation result.
The invention also provides a method for evaluating the precision of the roadside-oriented sensing system, which comprises the following steps:
step 1: the method comprises the steps that a self-vehicle positioning result is obtained, when the self-vehicle positioning device is indoors, indoor vehicle positioning is carried out through a carried laser radar and an inertial measurement unit based on a synchronous positioning and mapping technology, indoor positioning data, namely an indoor self-vehicle positioning result, is obtained, when the self-vehicle positioning device is outdoors, outdoor vehicle positioning is carried out through a carried GNSS receiver and the inertial measurement unit, and outdoor positioning data, namely an outdoor self-vehicle positioning result, is obtained;
step 2: reading a road side sensing result of RSU broadcast acquired by OBU equipment by loading an OBU drive, and cleaning and converting a data format of the road side sensing result;
and 3, step 3: and carrying out data packing on the indoor vehicle positioning result or the outdoor vehicle positioning result and the roadside sensing result, and uploading the data to a cloud server through a router in a remote communication mode.
And 4, step 4: and (3) receiving the indoor positioning data, the outdoor positioning data and the road side sensing result of the RSU broadcast uploaded in the step (3) through a cloud server of the deployed evaluation system, performing data processing and calculation to obtain an evaluation result, and providing a web service based on a B/S framework for the outside through the built web server for development and testing personnel to use.
The map construction and high-precision positioning, namely indoor vehicle positioning, are carried out by a laser radar and an inertia measurement unit based on a synchronous positioning and mapping (SLAM) technology, and the process of map construction and high-precision positioning specifically comprises the following steps:
carrying a laser radar and an inertia measurement unit on a vehicle, and calibrating the position of the vehicle to enable data results generated by the laser radar to surround a vehicle body coordinate system;
the method comprises the steps that a vehicle runs at a low speed in an indoor environment to acquire data, and the acquired data are mapped by an SLAM method, wherein the SLAM method comprises data fusion of a front-end laser radar odometer and an inertia measurement unit, rear-end optimization and closed-loop detection;
after the vehicle loads the constructed map, the vehicle drives to the area again and then starts the positioning function, the positioning function is matched with the data in the map through the current data of the laser radar, so that the position and the posture of the vehicle are determined, meanwhile, the inertial measurement unit is matched for data fusion, indoor positioning data are output, and the indoor positioning data comprise high-frequency vehicle self-position and posture information, so that high-precision indoor positioning is realized.
The outdoor vehicle positioning is carried out through the carried GNSS receiver and the inertia measurement unit, and the outdoor vehicle positioning process specifically comprises the following steps:
the method comprises the steps that a GNSS receiver and an inertia measurement unit are carried on a vehicle, and the position of the vehicle is calibrated, so that data results generated by the GNSS receiver surround a vehicle body coordinate system;
the vehicle starts RTK service and obtains accurate vehicle position and gesture in the good region of signal, cooperates the output outdoor positioning data of inertial measurement unit simultaneously, and outdoor positioning data includes vehicle self position and the gesture information of high frequency to realize the outdoor location of high accuracy.
The process of obtaining the evaluation result specifically includes the following steps:
step 401: based on the position information (x) in the indoor or outdoor self-vehicle positioning resulto，yo) Position information (x) of roadside sensing resultr，yr) Calculating the position error epPosition error epThe expression of (a) is:
step 402: based on the direction information yaw in the indoor or outdoor positioning result of the own vehicle0Heading information yaw of roadside perception resultrCalculating an orientation error edOrientation error edThe expression of (a) is:
ed＝yawr-yawo；
step 403: according to speed information v in indoor or outdoor self-vehicle positioning resultsoSpeed information v of roadside perception resultrCalculating the velocity error evVelocity error evThe expression of (a) is:
ev＝vr-vo；
step 404: according to the position error, the orientation error and the speed error in a period of time, respectively calculating the root mean square values of the position error, the orientation error and the speed error, wherein the formula for calculating each root mean square value is respectively
Wherein, RMSE (e)p) Root mean square value of position error, RMSE (e)d) RMSE (e) as root mean square value of orientation errorv) Is the root mean square value of the velocity error.
The invention proposes a concept of a data standard vehicle, combines the roadside sensing result and the self-positioning result through an accurate vehicle self-positioning system and a vehicle-road cooperative communication system, and evaluates the combination; meanwhile, the result sensed by the data standard vehicle and the result sensed by the roadside are combined for evaluation through the accurate environment sensing capability.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and those skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A device for precision evaluation of a roadside sensing system is characterized by comprising:
roadside perception system: the system comprises a road side sensor, a mobile edge calculation unit and a road side unit, and is used for acquiring a road side sensing result;
data standard vehicle: the system comprises a laser radar, a GNSS receiver, an inertia measurement unit, a router and a vehicle-mounted unit, and is used for acquiring a self-vehicle positioning result and uploading the self-vehicle positioning result and a received roadside sensing result;
cloud server: the system comprises a cloud server of the roadside sensing system and a cloud server of an evaluation system, wherein the cloud server of the roadside sensing system is used for displaying the state of the roadside sensing system in real time, and the cloud server of the evaluation system is used for evaluating the precision of the roadside sensing system and outputting an evaluation result.
2. The roadside oriented perception system precision evaluation device according to claim 1, wherein the roadside sensor is used for obtaining a perception result;
the mobile edge computing unit is connected with a cloud server of the roadside sensing system and used for computing and identifying sensing results, and uploading the sensing results to the cloud server of the roadside sensing system after obtaining the roadside sensing results;
the road side unit is used for broadcasting the acquired road side sensing result.
3. The roadside oriented sensing system precision evaluation device of claim 1, wherein the lidar and the inertial measurement unit are used in cooperation to realize a positioning function in an indoor environment to obtain an indoor self-vehicle positioning result;
the GNSS receiver and the inertial measurement unit are matched for use to realize a positioning function under an outdoor environment, and an outdoor self-vehicle positioning result is obtained;
the router is connected with a cloud server of the evaluation system and used for uploading the positioning result of the vehicle and the received positioning results of all vehicles broadcasted by the roadside sensing system to the cloud server of the evaluation system.
4. The roadside sensing system precision evaluation oriented device according to claim 1, wherein the cloud server of the roadside sensing system is used for displaying the state of the roadside sensing system in real time and monitoring and storing the roadside sensing result in real time;
the cloud server of the evaluation system is used for receiving the vehicle positioning result and the roadside sensing result uploaded by the router of the vehicle end, processing and analyzing the vehicle positioning result and the roadside sensing result, outputting a corresponding data comparison result, namely an evaluation result, for the purpose of evaluation, and displaying the evaluation result in real time.
5. A method of using the apparatus of any of claims 1 to 4, the method comprising:
step 1: the method comprises the steps that a self-vehicle positioning result is obtained, when the self-vehicle positioning device is indoors, indoor vehicle positioning is carried out through a carried laser radar and an inertial measurement unit based on a synchronous positioning and mapping technology, indoor positioning data, namely an indoor self-vehicle positioning result, is obtained, when the self-vehicle positioning device is outdoors, outdoor vehicle positioning is carried out through a carried GNSS receiver and the inertial measurement unit, and outdoor positioning data, namely an outdoor self-vehicle positioning result, is obtained;
step 2: reading a road side sensing result of RSU broadcast acquired by OBU equipment by loading an OBU drive, and cleaning and converting a data format of the road side sensing result;
and step 3: the indoor self-vehicle positioning result or the outdoor self-vehicle positioning result and the roadside sensing result are subjected to data packaging, and are uploaded to a cloud server through a router in a remote communication mode;
and 4, step 4: and (3) receiving the indoor positioning data, the outdoor positioning data and the roadside perception result broadcasted by the RSU uploaded in the step (3) through a cloud server of the deployed evaluation system, and performing data processing and calculation to obtain an evaluation result.
6. The method according to claim 5, wherein the step 1 of obtaining the indoor positioning result of the vehicle specifically comprises the following steps:
step 101: carrying a laser radar and an inertia measurement unit on a vehicle, and calibrating the position of the vehicle to enable data generated by the laser radar to surround a vehicle body coordinate system;
step 102: the method comprises the following steps that a vehicle runs at a certain region of an indoor environment at a low speed to collect data, and the collected data are mapped through an SLAM method;
step 103: after the vehicle loads the constructed map, the vehicle drives to the area again and then starts the positioning function, the positioning function is matched with data in the map through the current data of the laser radar, so that the position and the posture of the vehicle are determined, meanwhile, the inertial measurement unit is matched for data fusion, and indoor positioning data, including high-frequency vehicle self position, posture information and speed information, are output.
7. The method of claim 6, wherein in step 102, the SLAM method comprises front-end lidar odometry, data fusion of inertial measurement units, back-end optimization, and closed-loop detection.
8. The method according to claim 6, wherein in the step 1, the process of obtaining the outdoor positioning result of the vehicle specifically comprises the following steps:
step 104: the method comprises the steps that a GNSS receiver and an inertia measurement unit are carried on a vehicle, and the position of the vehicle is calibrated, so that data generated by the GNSS receiver surround a vehicle body coordinate system;
step 105: the vehicle starts RTK service of the GNSS receiver to obtain accurate vehicle position and attitude in a region with good signals, and meanwhile, outdoor positioning data including high-frequency vehicle self position, attitude information and speed information are output by matching with the inertial measurement unit.
9. The method according to claim 6, wherein the step 103 of obtaining high frequency vehicle position, attitude information and speed information comprises the following steps:
step 103 a: assuming that P is the current data of the laser radar under a vehicle body coordinate system, Q is the data in a constructed map, a three-dimensional translation matrix of the vehicle body is T, a three-dimensional rotation matrix is R, and R belongs to SO (3), the sum of errors of each point in the current data of the laser radar after being changed and the nearest point of the data in the map is solved to be minimum, SO that the values of the three-dimensional rotation matrix R and the three-dimensional translation matrix T are solved, and the expression is as follows:
wherein, argminR,TRepresenting a function, p, for obtaining the value of the variable R, T at which the latter formula reaches a minimumiFor the ith point in the current data of the laser radar, qiThe method comprises the steps that the nearest point of data in a map corresponding to the ith point in the current data of the laser radar is obtained, and N is the number of points in the current data of the laser radar;
step 103 b: calculating according to the three-dimensional rotation matrix R and the three-dimensional translation matrix T to obtain the position (x) of the vehicle0,y0) And attitude information yaw0Vehicle self position (x)0,y0) And attitude information yaw0Are respectively expressed as
xo＝T1
y0＝T2
Wherein, T1And T2Are all elements of a three-dimensional translation matrix T, R32And R33Are all elements in a three-dimensional rotation matrix R;
step 103 d: obtaining vehicle speed information v according to the information of the wheel speed meter of the vehicle0。
10. The method according to claim 5, wherein the step 4 of obtaining the evaluation result specifically comprises the steps of:
step 401: based on the position information (x) in the indoor or outdoor self-vehicle positioning resulto,yo) Position information (x) of roadside sensing resultr,yr) Calculating the position error epPosition error epThe expression of (a) is:
step 402: based on the direction information yaw in the indoor or outdoor positioning result of the own vehicle0Heading information yaw of roadside perception resultrCalculating an orientation error edOrientation error edThe expression of (a) is:
ed＝yawr-yawo；
step 403: according to speed information v in indoor or outdoor self-vehicle positioning resultsoSpeed information v of roadside perception resultrCalculating the velocity error evVelocity error evThe expression of (a) is:
ev＝vr-vo；
step 404: according to the position error, the orientation error and the speed error in a period of time, respectively calculating the root mean square values of the position error, the orientation error and the speed error, wherein the formula for calculating each root mean square value is respectively
Wherein, RMSE (e)p) Root mean square value of position error, RMSE (e)d) RMSE (e) as root mean square value of orientation errorv) Is the root mean square value of the velocity error.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111490796.XA CN114485658A (en) | 2021-12-08 | 2021-12-08 | Device and method for precision evaluation of roadside sensing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111490796.XA CN114485658A (en) | 2021-12-08 | 2021-12-08 | Device and method for precision evaluation of roadside sensing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114485658A true CN114485658A (en) | 2022-05-13 |
Family
ID=81492712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111490796.XA Pending CN114485658A (en) | 2021-12-08 | 2021-12-08 | Device and method for precision evaluation of roadside sensing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114485658A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294771A (en) * | 2022-09-29 | 2022-11-04 | 智道网联科技(北京)有限公司 | Monitoring method and device for road side equipment, electronic equipment and storage medium |
| CN116449347A (en) * | 2023-06-14 | 2023-07-18 | 蘑菇车联信息科技有限公司 | Calibration method and device of roadside laser radar and electronic equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110645979A (en) * | 2019-09-27 | 2020-01-03 | 北京交通大学 | Indoor and outdoor seamless positioning method based on GNSS/INS/UWB combination |
| CN110650461A (en) * | 2018-06-27 | 2020-01-03 | 华为技术有限公司 | Communication method, communication apparatus, and storage medium |
| CN110672097A (en) * | 2019-11-25 | 2020-01-10 | 北京中科深智科技有限公司 | Indoor positioning and tracking method, device and system based on laser radar |
| CN110906954A (en) * | 2019-12-02 | 2020-03-24 | 武汉中海庭数据技术有限公司 | High-precision map test evaluation method and device based on automatic driving platform |
| CN111045017A (en) * | 2019-12-20 | 2020-04-21 | 成都理工大学 | Method for constructing transformer substation map of inspection robot by fusing laser and vision |
| CN210952856U (en) * | 2019-11-26 | 2020-07-07 | 北京中科深智科技有限公司 | Indoor positioning and tracking device and system based on laser radar |
| CN111522043A (en) * | 2020-04-30 | 2020-08-11 | 北京联合大学 | Unmanned vehicle laser radar rapid re-matching positioning method |
| WO2021000800A1 (en) * | 2019-06-29 | 2021-01-07 | 华为技术有限公司 | Reasoning method for road drivable region and device |
| CN113074732A (en) * | 2021-03-22 | 2021-07-06 | 东南大学 | Indoor and outdoor seamless positioning system and positioning method thereof |
| CN113110502A (en) * | 2021-05-11 | 2021-07-13 | 上海东古智能科技有限公司 | Security patrol robot system applied to smart park |
| CN113340325A (en) * | 2021-06-01 | 2021-09-03 | 上海智能网联汽车技术中心有限公司 | System, method and medium for verifying vehicle-road cooperative roadside perception fusion precision |
| CN113607166A (en) * | 2021-10-08 | 2021-11-05 | 广东省科学院智能制造研究所 | Indoor and outdoor positioning method and device for autonomous mobile robot based on multi-sensor fusion |
| CN113658441A (en) * | 2021-07-08 | 2021-11-16 | 江苏大学 | High-flexibility variable-view-angle roadside sensing device and beyond-the-horizon sensing method for automatic driving |
| CN113654566A (en) * | 2021-07-27 | 2021-11-16 | 上海智能网联汽车技术中心有限公司 | Positioning performance evaluation method of road side system, storage medium and vehicle-road cooperative system |
-
2021
- 2021-12-08 CN CN202111490796.XA patent/CN114485658A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110650461A (en) * | 2018-06-27 | 2020-01-03 | 华为技术有限公司 | Communication method, communication apparatus, and storage medium |
| WO2021000800A1 (en) * | 2019-06-29 | 2021-01-07 | 华为技术有限公司 | Reasoning method for road drivable region and device |
| CN110645979A (en) * | 2019-09-27 | 2020-01-03 | 北京交通大学 | Indoor and outdoor seamless positioning method based on GNSS/INS/UWB combination |
| CN110672097A (en) * | 2019-11-25 | 2020-01-10 | 北京中科深智科技有限公司 | Indoor positioning and tracking method, device and system based on laser radar |
| CN210952856U (en) * | 2019-11-26 | 2020-07-07 | 北京中科深智科技有限公司 | Indoor positioning and tracking device and system based on laser radar |
| CN110906954A (en) * | 2019-12-02 | 2020-03-24 | 武汉中海庭数据技术有限公司 | High-precision map test evaluation method and device based on automatic driving platform |
| CN111045017A (en) * | 2019-12-20 | 2020-04-21 | 成都理工大学 | Method for constructing transformer substation map of inspection robot by fusing laser and vision |
| CN111522043A (en) * | 2020-04-30 | 2020-08-11 | 北京联合大学 | Unmanned vehicle laser radar rapid re-matching positioning method |
| CN113074732A (en) * | 2021-03-22 | 2021-07-06 | 东南大学 | Indoor and outdoor seamless positioning system and positioning method thereof |
| CN113110502A (en) * | 2021-05-11 | 2021-07-13 | 上海东古智能科技有限公司 | Security patrol robot system applied to smart park |
| CN113340325A (en) * | 2021-06-01 | 2021-09-03 | 上海智能网联汽车技术中心有限公司 | System, method and medium for verifying vehicle-road cooperative roadside perception fusion precision |
| CN113658441A (en) * | 2021-07-08 | 2021-11-16 | 江苏大学 | High-flexibility variable-view-angle roadside sensing device and beyond-the-horizon sensing method for automatic driving |
| CN113654566A (en) * | 2021-07-27 | 2021-11-16 | 上海智能网联汽车技术中心有限公司 | Positioning performance evaluation method of road side system, storage medium and vehicle-road cooperative system |
| CN113607166A (en) * | 2021-10-08 | 2021-11-05 | 广东省科学院智能制造研究所 | Indoor and outdoor positioning method and device for autonomous mobile robot based on multi-sensor fusion |
Non-Patent Citations (2)
| Title |
|---|
| TAKAHIRO FURUYAMA, YASUHIRO HIRAYAMA, AND MANABU SAWADA CORPORATE R&D DIV. 3 DENSO CORPORATION YOKOSUKA CITY, JAPAN: "Performance evaluation of Prioritized CSMA protocol for single-channel Roadside-to-Vehicle and Vehicle-to-Vehicle communication systems", 2011 17TH ASIA-PACIFIC CONFERENCE ON COMMUNICATIONS (APCC), pages 461 - 466 * |
| 戴仁月: "融合扩张卷积网络与SLAM的无监督单目深度估计", 《激光与光电子学进展》, vol. 57, no. 6, pages 1 - 9 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294771A (en) * | 2022-09-29 | 2022-11-04 | 智道网联科技(北京)有限公司 | Monitoring method and device for road side equipment, electronic equipment and storage medium |
| CN116449347A (en) * | 2023-06-14 | 2023-07-18 | 蘑菇车联信息科技有限公司 | Calibration method and device of roadside laser radar and electronic equipment |
| CN116449347B (en) * | 2023-06-14 | 2023-10-03 | 蘑菇车联信息科技有限公司 | Calibration method and device of roadside laser radar and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022206978A1 (en) | Roadside millimeter-wave radar calibration method based on vehicle-mounted positioning apparatus | |
| CN112525162B (en) | System and method for measuring image distance of power transmission line by unmanned aerial vehicle | |
| CN109084786B (en) | Map data processing method | |
| CN103150786B (en) | Non-contact type unmanned vehicle driving state measuring system and measuring method | |
| CN113340325B (en) | System, method and medium for verifying vehicle-road cooperative roadside perception fusion precision | |
| CN108414238A (en) | Automatic parking function real steering vectors system and test method | |
| CN108898879A (en) | parking data detection system and method | |
| CN114485658A (en) | Device and method for precision evaluation of roadside sensing system | |
| CN103941746A (en) | System and method for processing unmanned aerial vehicle polling image | |
| CN107607091A (en) | A kind of method for measuring unmanned plane during flying flight path | |
| CN105445729A (en) | Unmanned plane three-dimensional flight track precision detection method and system | |
| CN115189762B (en) | Method and device for detecting communication availability of satellite-to-ground laser communication ground station | |
| CN113075686B (en) | Cable trench intelligent inspection robot graph building method based on multi-sensor fusion | |
| CN108711172A (en) | Unmanned plane identification based on fine grit classification and localization method | |
| CN105372650A (en) | Unmanned plane flight track precision detection method and device | |
| CN115588040A (en) | System and method for counting and positioning coordinates based on full-view imaging points | |
| CN116560357A (en) | Tunnel inspection robot system based on SLAM and inspection control method | |
| CN114360093A (en) | Roadside parking space inspection method based on Beidou RTK, SLAM positioning and image analysis | |
| CN113592951A (en) | Method and device for calibrating external parameters of vehicle-road cooperative middle-road side camera and electronic equipment | |
| CN117310627A (en) | Combined calibration method applied to vehicle-road collaborative road side sensing system | |
| CN113727434B (en) | Vehicle-road cooperative auxiliary positioning system and method based on edge computing gateway | |
| US20220404170A1 (en) | Apparatus, method, and computer program for updating map | |
| CN112461199B (en) | NBIoT-based antenna attitude detection method and terminal | |
| CN111881899B (en) | Robot positioning deployment method, device, equipment and storage medium | |
| CN116635739A (en) | Road side millimeter wave radar calibration method based on vehicle-mounted positioning device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |