CN114460537A - Method and device for adjusting model - Google Patents
Method and device for adjusting model Download PDFInfo
- Publication number
- CN114460537A CN114460537A CN202210037662.0A CN202210037662A CN114460537A CN 114460537 A CN114460537 A CN 114460537A CN 202210037662 A CN202210037662 A CN 202210037662A CN 114460537 A CN114460537 A CN 114460537A
- Authority
- CN
- China
- Prior art keywords
- positioning
- data
- positioning base
- unmanned equipment
- determining
- 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
Images
Classifications
-
- 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
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0257—Hybrid positioning
- G01S5/0258—Hybrid positioning by combining or switching between measurements derived from different systems
- G01S5/02585—Hybrid positioning by combining or switching between measurements derived from different systems at least one of the measurements being a non-radio measurement
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The specification discloses a method and a device for adjusting a model. First, sensing data and position information of each positioning base station are acquired. And inputting the sensing data into a positioning model to be adjusted, and predicting the position of the unmanned equipment in an actual test field to serve as predicted positioning data. And secondly, determining the difference of the distances from the at least two positioning base stations to the unmanned equipment according to the time when the at least two positioning base stations receive the signals sent by the signal transmitters on the unmanned equipment. Then, the actual positioning data of the unmanned device is determined. And finally, determining an adjustment strategy aiming at the positioning model according to the positioning deviation between the real positioning data and the estimated positioning data, and adjusting the positioning model according to the adjustment strategy. According to the method, the positioning base station receives the signals sent by the signal transmitter on the unmanned equipment, so that the condition that the received signals have large time delay is avoided, and the accuracy of the positioning data predicted by the positioning model is accurately judged.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for model adjustment.
Background
At present, unmanned equipment needs to plan a driving track according to positioning information and environment perception information of the unmanned equipment and control the unmanned equipment to drive according to the driving track. It can be seen that the positioning accuracy of the drone is a key factor affecting the autopilot performance of the drone.
In practical applications, Real Time Kinematic (RTK) is usually used to determine Real-Time positioning data of the unmanned device, so as to evaluate the accuracy of the positioning data predicted by the positioning model in Real Time. However, since the RTK measurement technology receives the signal of the RTK base station through the 4G network, this method is affected by the network signal, and if the received signal of the RTK base station has a large time delay, the accuracy of the determined real positioning data of the unmanned device is reduced, and the accuracy of the positioning data predicted by the positioning model cannot be determined.
Therefore, how to improve the accuracy of the real positioning data of the unmanned device is an urgent problem to be solved.
Disclosure of Invention
The present specification provides a method and an apparatus for model adjustment, which partially solve the above problems in the prior art.
The technical scheme adopted by the specification is as follows:
the present specification provides a method for model adjustment, where the method is used to test an unmanned device in a preset actual test site, where each positioning base station is arranged in the actual test site, and the method includes:
acquiring sensing data acquired when the unmanned equipment drives in the actual test field according to the determined track planning data and position information of each positioning base station in the actual test field;
inputting the sensing data into a positioning model to be adjusted, and estimating the position of the unmanned equipment in the actual test field to serve as estimated positioning data;
for at least two positioning base stations in each positioning base station, determining a difference value of distances from the at least two positioning base stations to the unmanned equipment according to the time when the at least two positioning base stations receive signals sent by signal transmitters on the unmanned equipment;
determining real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field and the difference value;
and determining an adjustment strategy aiming at the positioning model according to the positioning deviation between the real positioning data and the estimated positioning data, and adjusting the positioning model according to the adjustment strategy.
Optionally, determining trajectory planning data specifically includes:
constructing a simulation test environment corresponding to the actual test site based on a preset simulation scene editor;
and determining the trajectory planning data in the simulation test environment, wherein the trajectory planning data comprises the planning speed of the unmanned equipment on a plurality of specified positions in the actual test field.
Optionally, in the simulation test environment, determining the trajectory planning data specifically includes:
obtaining historical positioning data obtained by positioning based on the positioning model;
determining a corresponding road shape when the track point deviation occurs according to the historical positioning data;
and determining the trajectory planning data in the simulation test environment according to the road shape.
Optionally, in the simulation test environment, determining the trajectory planning data specifically includes:
aiming at any two adjacent specified positions, determining a track point sequence of the unmanned equipment when the unmanned equipment runs between the two adjacent specified positions according to a dynamic model corresponding to the unmanned equipment and the planning speed of the unmanned equipment on the two adjacent specified positions;
and determining trajectory planning data of the unmanned equipment in the simulation test environment according to the trajectory point sequence of the unmanned equipment when the unmanned equipment runs between any two adjacent specified positions.
Optionally, for at least two of the positioning base stations, determining a difference between distances from the at least two positioning base stations to the unmanned aerial vehicle according to a time when the at least two positioning base stations receive a signal sent by a signal transmitter on the unmanned aerial vehicle, specifically including:
for at least two positioning base stations in each positioning base station, determining a difference value of corresponding time of the at least two positioning base stations according to the time when the at least two positioning base stations receive signals sent by signal transmitters on the unmanned equipment;
and determining the difference of the distances from the at least two positioning base stations to the unmanned equipment according to the difference of the times corresponding to the at least two positioning base stations and the propagation speed corresponding to the signal sent by the signal transmitter on the unmanned equipment.
Optionally, determining the actual positioning data of the unmanned aerial vehicle according to the position information of the at least two positioning base stations in the actual test site and the difference, specifically including:
determining a running track of the unmanned equipment in the actual test field;
and determining the real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field, the driving track of the unmanned equipment in the actual test field and the difference value.
Optionally, determining the actual positioning data of the unmanned aerial vehicle according to the position information of the at least two positioning base stations in the actual test site and the difference, specifically including:
for each positioning base station combination, determining positioning data to be determined of the unmanned equipment corresponding to the positioning base station combination according to the position information of the positioning base station combination in the actual test field and the difference, wherein the positioning base station combination at least comprises three positioning base stations, and the positioning base stations contained in different positioning base station combinations are not identical;
determining an error value according to the positioning data to be determined of the unmanned equipment corresponding to each positioning base station combination;
and determining the real positioning data of the unmanned equipment according to the positioning data to be determined of the unmanned equipment corresponding to each positioning base station combination and the error value.
Optionally, determining a positioning deviation between the real positioning data and the estimated positioning data specifically includes:
for each moment, taking the position deviation between the position information of the unmanned equipment corresponding to the moment in the real positioning data and the position information of the unmanned equipment corresponding to the moment in the estimated positioning data as the position deviation corresponding to the moment;
and determining the positioning deviation between the real positioning data and the estimated positioning data according to the position deviation corresponding to each moment.
Optionally, the positioning base station includes: a UWB positioning base station, the signal transmitter comprises a UWB positioning tag.
This specification provides a device of model adjustment, the device is arranged in testing unmanned aerial vehicle in the actual test place of predetermineeing, be equipped with each location basic station in the actual test place, include:
the acquisition module is used for acquiring sensing data acquired when the unmanned equipment drives in the actual test field according to the determined track planning data and position information of each positioning base station in the actual test field;
the input module is used for inputting the sensing data into a positioning model to be adjusted, and estimating the position of the unmanned equipment in the actual test field to serve as estimated positioning data;
a determining module, configured to determine, for at least two of the positioning base stations, a difference between distances from the at least two positioning base stations to the unmanned device according to times at which the at least two positioning base stations receive signals sent by signal transmitters on the unmanned device;
the positioning module is used for determining real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field and the difference value;
and the adjusting module is used for determining an adjusting strategy aiming at the positioning model according to the positioning deviation between the real positioning data and the estimated positioning data, and adjusting the positioning model according to the adjusting strategy.
The present specification provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the above-described method of model adjustment.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned model adjustment method when executing the program.
The technical scheme adopted by the specification can achieve the following beneficial effects:
in the method for model adjustment provided in the present specification. Firstly, acquiring sensing data acquired when the unmanned equipment drives in an actual test field according to determined track planning data and position information of each positioning base station in the actual test field. And inputting the sensing data into a positioning model to be adjusted, and estimating the position of the unmanned equipment in the actual test field to serve as estimated positioning data. Secondly, for at least two positioning base stations in each positioning base station, determining the difference value of the distances from the at least two positioning base stations to the unmanned equipment according to the time when the at least two positioning base stations receive the signals sent by the signal transmitter on the unmanned equipment. And then, determining the real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field and the difference value. And finally, determining an adjustment strategy aiming at the positioning model according to the positioning deviation between the real positioning data and the estimated positioning data, and adjusting the positioning model according to the adjustment strategy.
In the method, the difference between the distances from the at least two positioning base stations to the unmanned equipment can be determined according to the time when the at least two positioning base stations receive the signals sent by the signal transmitters on the unmanned equipment, so as to determine the real positioning data of the unmanned equipment. Compared with the prior art, the method has the advantages that the positioning base station receives the signals sent by the signal transmitter on the unmanned equipment, the situation that the received signals have great time delay is avoided, the fact that the accuracy of the determined real positioning data of the unmanned equipment is low is avoided, and the accuracy of the positioning data predicted by the positioning model is accurately judged.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
FIG. 1 is a schematic flow chart of a method for model tuning in this specification;
fig. 2A and fig. 2B are schematic diagrams illustrating a method for determining real positioning data according to an embodiment of the present disclosure;
FIG. 3 is a schematic view of a model adjustment apparatus provided herein;
fig. 4 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for model adjustment in this specification, including the following steps:
s100: and acquiring sensing data acquired when the unmanned equipment drives in the actual test field according to the determined track planning data and position information of each positioning base station in the actual test field.
In the embodiment of the present specification, the execution subject for adjusting the positioning model may be a server, or may be an electronic device such as a desktop computer, and for convenience of description, the method for adjusting the model provided in the present specification will be described below with only the server as the execution subject.
In the embodiment of the present specification, each positioning base station is disposed in the actual test site, and the server may obtain sensing data acquired when the unmanned device travels in the actual test site according to the determined trajectory planning data, and position information of each positioning base station in the actual test site. The sensing data mentioned here may be sensing data acquired by a sensor such as a camera, a laser radar, an inertial measurement unit, or the like provided on the unmanned device, for example, image data acquired by the camera, point cloud data acquired by the laser radar, attitude data acquired by the inertial measurement unit, or the like. The position information mentioned here may be a spatial rectangular coordinate system defined in an actual test site, and coordinates of each positioning base station under the spatial rectangular coordinate system are determined (X, Y, Z).
It should be noted that the positioning base station includes: a UWB (ultra Wide band) location base station, the signal transmitter comprising a UWB location tag.
The unmanned device mentioned in the present specification may refer to an unmanned aerial vehicle, an unmanned vehicle, a robot, an automatic distribution device, and the like, which are capable of realizing automatic driving. Based on this, the unmanned device to which the model adjustment method provided by the present specification is applied may be used to perform delivery tasks in the delivery field, such as business scenarios for delivery of express delivery, logistics, takeaway, and the like using the unmanned device.
In this specification, the trajectory planning data may be determined in a simulation test environment. Specifically, the server may construct a simulation test environment matched with an actual test site based on a preset simulation scene editor. For example, if the actual test site is an annular site, a simulated annular site may be constructed.
Then, the server can determine the trajectory planning data in the constructed simulation test environment, wherein the server can determine the trajectory planning data based on an instruction input by a tester, that is, the tester can construct a corresponding driving trajectory based on an actual test requirement in the constructed simulation test environment. Meanwhile, some positions may be specified in the simulation test environment, and the travel speed at the specified positions may be specified when the unmanned aerial vehicle travels in the simulation test environment. Therefore, when the unmanned equipment runs in an actual test scene according to the trajectory planning data, the unmanned equipment can run at the specified positions according to the planning speed so as to further meet the test requirement.
Of course, in this specification, the server may determine the trajectory planning data in the simulation test environment based on historical positioning data obtained by the positioning model during positioning. Specifically, in practical application, when the positioning deviation occurs in the positioning model, the deviation will be reflected on the positioning data obtained by positioning, for example, the track point obtained by positioning has a deviation. When the track point deviates, the situation may be related to the road where the unmanned aerial vehicle is located, for example, when the unmanned aerial vehicle is in a straight road, the track point located by the positioning model may not deviate, and when the unmanned aerial vehicle is in a curved road, the situation that the track point located by the positioning model may deviate may occur.
Therefore, after the server obtains the historical positioning data obtained by positioning based on the positioning model, the server can determine the corresponding road shape when the track point deviation occurs according to the historical positioning data, and further determine the track planning data in the constructed simulation test environment according to the determined road shape. For example, through historical positioning data, the road shape of a road where the unmanned equipment is located when track point deviation occurs in history can be determined, and then in a simulation test environment, track planning data of the road with the road shape is determined.
In determining the trajectory planning data, the server may determine planned trajectory data of the unmanned device in the simulation test environment based on planning speeds at a plurality of designated locations. The server can determine a track point sequence of the unmanned device when the unmanned device drives between the two adjacent specified positions according to a dynamic model corresponding to the unmanned device (if the unmanned device is an unmanned vehicle, the dynamic model is a vehicle dynamic model) and the planned speeds of the unmanned device at the two adjacent specified positions aiming at any two adjacent specified positions, wherein for each track point contained in the track point sequence, the server can determine the approximate driving speed of the unmanned device at the track point according to the dynamic model corresponding to the unmanned device and the planned speeds of the unmanned device at the two adjacent specified positions.
For example, assuming that there are a specified location a and a specified location B, and there is a section of road between the specified location a and the specified location B, the server may determine the sequence of track points that the unmanned aerial vehicle passes through when driving on the section of road according to the planned speed of the unmanned aerial vehicle at the specified location a and the planned speed of the unmanned aerial vehicle at the specified location B.
Further, the server can determine trajectory planning data of the unmanned equipment in the simulation test environment according to a trajectory point sequence of the unmanned equipment when the unmanned equipment runs between any two adjacent specified positions.
S102: and inputting the sensing data into a positioning model to be adjusted, and estimating the position of the unmanned equipment in the actual test field to serve as estimated positioning data.
In this embodiment, the server may input the sensing data into the positioning model to be adjusted, and estimate a position of the unmanned device in the actual test site as estimated positioning data.
In this specification, the server may input image data acquired by the camera, point cloud data acquired by the laser radar, attitude data acquired by the inertial measurement unit, and the like into the positioning model, and estimate a position of the unmanned device in an actual test site as estimated positioning data.
For example, the server may perform matching of image feature points by a positioning model according to image feature points in several consecutive images captured by the camera, and determine a moving distance of the image feature points, thereby determining the position of the unmanned device. Similarly, the server can extract the feature points of the point cloud data through the positioning model according to the point cloud data acquired by the laser radar, and determine the moving distance of the feature points between the continuous frames, so as to determine the position of the unmanned equipment. Similarly, the server can determine the position of the unmanned equipment according to the attitude data acquired by the inertial measurement unit.
Furthermore, the server can combine the position of the unmanned equipment determined by the image data, the position of the unmanned equipment determined by the point cloud data and the position of the unmanned equipment determined by the attitude data, and estimate the position of the unmanned equipment in the actual test field as estimated positioning data.
S104: and for at least two positioning base stations in each positioning base station, determining the difference value of the distances from the at least two positioning base stations to the unmanned equipment according to the time when the at least two positioning base stations receive the signals sent by the signal transmitter on the unmanned equipment.
In practical application, because the RTK measurement technology receives the signal of the RTK base station through the 4G network, the RTK measurement technology is affected by the network signal, and a great time delay may occur in the received signal of the RTK base station, which may cause a decrease in accuracy of the determined real positioning data of the unmanned aerial vehicle. Based on this, the server can avoid the signal received by the positioning base station from having a large time delay by arranging the positioning base station in the actual test field.
In this embodiment, the server may determine, for at least two of the positioning base stations, a difference between distances from the at least two positioning base stations to the drone, according to times at which the at least two positioning base stations receive signals transmitted by the signal transmitter on the drone.
Specifically, first, the server synchronizes the positioning base station time corresponding to each positioning base station. Secondly, each positioning base station receives the signal sent by the signal transmitter on the unmanned equipment, obtains the timestamp of the signal received by each positioning base station, and sends the timestamp of the signal received by each positioning base station to the server. Finally, the server can determine the difference value of the distances from the positioning base stations to the unmanned equipment according to the time stamps of the signals received by the positioning base stations.
Further, the server may determine, for at least two of the positioning base stations, a difference between times corresponding to the at least two positioning base stations according to a time when the at least two positioning base stations receive a signal sent by a signal transmitter on the drone. And determining the difference of the distances from the at least two positioning base stations to the unmanned equipment according to the difference of the corresponding time of the at least two positioning base stations and the propagation speed corresponding to the signal sent by the signal transmitter on the unmanned equipment.
For example, if there are three positioning base stations, the positioning base station a, the positioning base station B, and the positioning base station C are respectively. The server may subtract the time stamps of the signals received by any two positioning base stations (e.g., positioning base station a and positioning base station B) to obtain a difference between corresponding times of the positioning base station a and the positioning base station B. And determining the difference of the corresponding distances from the positioning base station A to the unmanned equipment and from the positioning base station B to the unmanned equipment according to the difference of the corresponding time between the positioning base station A and the positioning base station B and the corresponding propagation speed of the signal sent by the signal transmitter on the unmanned equipment. Similarly, the server may obtain a difference between distances corresponding to the positioning base station a to the drone and the positioning base station C to the drone, and a difference between distances corresponding to the positioning base station B to the drone and the positioning base station C to the drone.
It can be seen that, because a plurality of positioning base stations are arranged in an actual test field, any two positioning base stations are divided into a group, and the server can determine the difference value of the distances from the plurality of groups of positioning base stations to the unmanned equipment.
S106: and determining the real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field and the difference value.
In this embodiment, the server may determine the actual positioning data of the unmanned device according to the position information of the at least two positioning base stations in the actual test site and the difference value. The real positioning data mentioned here contains real position information of the unmanned device at each moment, and can be used for representing a real driving track of the unmanned device.
In practical applications, the server may apply a Time Difference of Arrival (TDOA) method, and determine a hyperbola corresponding to two positioning base stations by using the positions of the two positioning base stations as a focus, and taking a Difference between the distances from the two positioning base stations to the drone as a major axis (knowing whether the Difference between the distances from the two positioning base stations to the drone is positive or negative, it may be determined whether the drone is located on the left branch or the right branch of the hyperbola).
In the embodiment of the specification, the server may determine the driving track of the unmanned device in the actual test site in advance. And determining the real positioning data of the unmanned equipment according to the position information of the two positioning base stations in the actual test field, the driving track of the unmanned equipment in the actual test field and the difference value. How to determine the actual positioning data of the unmanned device is shown in fig. 2A and fig. 2B.
Fig. 2A and fig. 2B are schematic diagrams for determining real positioning data according to an embodiment of the present disclosure.
In fig. 2A, solid triangles may be used to characterize the true location data where the drone is located. The server firstly obtains the predetermined running track of the unmanned equipment in the actual test field and the corresponding positions (a positioning base station A and a positioning base station B) of the two positioning base stations. And determining hyperbolas corresponding to the two positioning base stations by taking the positions of the two positioning base stations as focuses and taking the difference value of the distances from the two positioning base stations to the unmanned equipment as a long axis. And finally, determining the real positioning data of the unmanned equipment according to the driving track of the unmanned equipment in the actual test field and the intersection point between the hyperbolas corresponding to the two positioning base stations.
In practical application, the driving track of the unmanned aerial vehicle may be complex, and a plurality of intersection points may appear between the hyperbola determined by the two positioning base stations and the track curve of the unmanned aerial vehicle, so that the real positioning data of the unmanned aerial vehicle cannot be accurately determined. Based on this, the server can determine accurate real positioning data of the unmanned equipment through at least three positioning base stations.
In this embodiment, the server may group two positioning base stations into at least three groups. And determining hyperbolas corresponding to the at least three groups of positioning base stations, wherein the server can determine the estimated track of the unmanned equipment according to the hyperbolas corresponding to the at least three groups of positioning base stations. As shown in particular in fig. 2B.
As can be seen in fig. 2B, the solid triangles can be used to characterize the true location data where the drone is located. The test site comprises three positioning base stations, namely a positioning base station A, a positioning base station B and a positioning base station C. And intersecting a hyperbola corresponding to the positioning base station A and the positioning base station B, a hyperbola corresponding to the positioning base station A and the positioning base station C and a hyperbola corresponding to the positioning base station B and the positioning base station C at a point to determine the real positioning data of the unmanned equipment. The specific formula is as follows:
in the above formula, base station A (x) is located1、y1、z1) Positioning base station B (x)2、y2、z2) Positioning base station C (x)3、y3、z3)。di，12Can be used to characterize the difference in the distances from positioning base station a and positioning base station B to the drone. di，23Can be used to characterize the difference in the distances from positioning base station B and positioning base station C to the drone. di，31May be used to characterize the difference in the distance of positioning base station C from positioning base station a to the drone. The server may set the true location data of the drone to (x)i、yi、zi) The real positioning data of the unmanned equipment can be obtained by acquiring the position information of the positioning base station A, the positioning base station B and the positioning base station C in advance.
In practical application, often establish by a plurality of positioning base stations in the test field, the time that different positioning base stations received the signal that signal transmitter on the unmanned aerial vehicle sent may appear tiny error, if regard three positioning base stations as positioning base station combination, different positioning base station combinations may draw different unmanned aerial vehicle corresponding treat the definite positioning data. Based on this, the server can determine the error value according to the to-be-determined positioning data corresponding to the plurality of positioning base station combinations to determine accurate real positioning data of the unmanned device.
In this specification, for each positioning base station combination, the positioning data to be determined of the unmanned device corresponding to the positioning base station combination is determined according to the position information of the positioning base station combination in the actual test site and the difference value, where the positioning base station combination mentioned here includes at least three positioning base stations, and the positioning base stations included in different positioning base station combinations are not exactly the same. And secondly, determining an error value according to the positioning data to be determined of the unmanned equipment corresponding to each positioning base station combination. And finally, determining the real positioning data of the unmanned equipment according to the positioning data to be determined and the error value of the unmanned equipment corresponding to each positioning base station combination.
That is, if at least four positioning base stations are installed on the actual test site, the result of the combination of the at least four positioning base stations can be obtained, and the server can obtain the error value corresponding to the result of the combination of the at least four positioning base stations by the least square method. And determining the real positioning data of the unmanned equipment according to the positioning data to be determined and the error value of the unmanned equipment corresponding to each positioning base station combination.
In this specification embodiment, the server may set, for each time, a positional deviation between positional information of the unmanned aerial vehicle corresponding to the time in the actual positioning data and positional information of the unmanned aerial vehicle corresponding to the time in the estimated positioning data as a positional deviation corresponding to the time. And determining the positioning deviation between the real positioning data and the estimated positioning data according to the position deviation corresponding to each moment.
Specifically, the server can align the estimated positioning data with the real positioning data, determine the position information corresponding to the unmanned device at each moment in the estimated positioning data, find the position information corresponding to the unmanned device at the moment in the aligned real positioning data, and determine the position deviation between the position information of the unmanned device corresponding to the estimated positioning data and the real positioning data at the same moment as the position deviation corresponding to the moment. And determining the average position deviation between the estimated positioning data and the real positioning data according to the position deviation corresponding to each moment.
S108: and determining an adjustment strategy aiming at the positioning model according to the positioning deviation between the real positioning data and the estimated positioning data, and adjusting the positioning model according to the adjustment strategy.
In this embodiment, the server may determine an adjustment policy for the positioning model according to a positioning deviation between the real positioning data and the estimated positioning data, and adjust the positioning model according to the adjustment policy.
In the above process, it can be seen that the method can determine the difference between the distances from the at least two positioning base stations to the unmanned device according to the time when the at least two positioning base stations receive the signal sent by the signal transmitter on the unmanned device, so as to determine the actual positioning data of the unmanned device. Compared with the prior art, the method has the advantages that the positioning base station receives the signals sent by the signal transmitter on the unmanned equipment, the situation that the received signals have great time delay is avoided, the fact that the accuracy of the determined real positioning data of the unmanned equipment is low is avoided, and the accuracy of the positioning data predicted by the positioning model is accurately judged.
The above method for model adjustment provided for one or more embodiments of the present specification also provides a corresponding apparatus for model adjustment, based on the same idea, as shown in fig. 3.
Fig. 3 is a schematic diagram of a model adjustment apparatus provided in this specification, where the apparatus is used to test an unmanned device in a preset actual test site, where each positioning base station is arranged in the actual test site, and the apparatus includes:
an obtaining module 300, configured to obtain sensing data collected when the unmanned equipment drives in the actual test site according to the determined trajectory planning data, and position information of each positioning base station in the actual test site;
the input module 302 is configured to input the sensing data into a positioning model to be adjusted, and estimate a position of the unmanned equipment in the actual test site as estimated positioning data;
a determining module 304, configured to determine, for at least two of the positioning base stations, a difference between distances from the at least two positioning base stations to the unmanned device according to times at which the at least two positioning base stations receive signals sent by a signal transmitter on the unmanned device;
a positioning module 306, configured to determine real positioning data of the unmanned device according to the position information of the at least two positioning base stations in the actual test site and the difference;
an adjusting module 308, configured to determine an adjusting strategy for the positioning model according to a positioning deviation between the actual positioning data and the estimated positioning data, and adjust the positioning model according to the adjusting strategy.
Optionally, the obtaining module 300 is specifically configured to construct, based on a preset simulation scenario editor, a simulation test environment corresponding to the actual test site, and determine the trajectory planning data in the simulation test environment, where the trajectory planning data includes planning speeds of the unmanned aerial device at a plurality of specified positions in the actual test site.
Optionally, the obtaining module 300 is specifically configured to obtain historical positioning data obtained by positioning based on the positioning model, determine a road shape corresponding to the track point deviation according to the historical positioning data, and determine the track planning data in the simulation test environment according to the road shape.
Optionally, the obtaining module 300 is specifically configured to, for any two adjacent designated positions, determine a track point sequence of the unmanned aerial vehicle when the unmanned aerial vehicle travels between the two adjacent designated positions according to a dynamic model corresponding to the unmanned aerial vehicle and a planned speed of the unmanned aerial vehicle at the two adjacent designated positions; and determining trajectory planning data of the unmanned equipment in the simulation test environment according to the trajectory point sequence of the unmanned equipment when the unmanned equipment runs between any two adjacent specified positions.
Optionally, the determining module 304 is specifically configured to, for at least two of the positioning base stations, determine a difference between times corresponding to the at least two positioning base stations according to times at which the at least two positioning base stations receive signals sent by the signal transmitter on the unmanned device, and determine a difference between distances from the at least two positioning base stations to the unmanned device according to the difference between the times corresponding to the at least two positioning base stations and a propagation speed corresponding to a signal sent by the signal transmitter on the unmanned device.
Optionally, the positioning module 306 is specifically configured to determine a driving track of the unmanned aerial vehicle in the actual test site, and determine the real positioning data of the unmanned aerial vehicle according to the position information of the at least two positioning base stations in the actual test site, the driving track of the unmanned aerial vehicle in the actual test site, and the difference.
Optionally, the positioning module 306 is specifically configured to, for each positioning base station combination, determine, according to the position information of the positioning base station combination in the actual test site and the difference, positioning data to be determined of the unmanned device corresponding to the positioning base station combination, where the positioning base station combinations at least include three positioning base stations, the positioning base stations included in different positioning base station combinations are not identical, determine, according to the positioning data to be determined of the unmanned device corresponding to each positioning base station combination, an error value, and determine, according to the positioning data to be determined of the unmanned device corresponding to each positioning base station combination and the error value, real positioning data of the unmanned device.
Optionally, the adjusting module 308 is specifically configured to, for each time, use a position deviation between the position information corresponding to the unmanned device at the time in the real positioning data and the position information corresponding to the unmanned device at the time in the estimated positioning data as a position deviation corresponding to the time, and determine a positioning deviation between the real positioning data and the estimated positioning data according to the position deviation corresponding to each time.
Optionally, the adjusting module 308 is specifically configured to, the positioning base station includes: a UWB positioning base station, the signal transmitter comprises a UWB positioning tag.
The present specification also provides a computer readable storage medium having stored thereon a computer program operable to perform a method of model tuning as provided above with respect to fig. 1.
This specification also provides a schematic block diagram of an electronic device corresponding to that of figure 1, shown in figure 4. As shown in fig. 4, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the model adjustment method described in fig. 1. Of course, besides the software implementation, this specification does not exclude other implementations, such as logic devices or combination of software and hardware, and so on, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (12)
1. A method for model adjustment is used for testing unmanned equipment in a preset actual test site, wherein each positioning base station is arranged in the actual test site, and the method comprises the following steps:
acquiring sensing data acquired when the unmanned equipment drives in the actual test field according to the determined track planning data and position information of each positioning base station in the actual test field;
inputting the sensing data into a positioning model to be adjusted, and estimating the position of the unmanned equipment in the actual test field to serve as estimated positioning data;
for at least two positioning base stations in each positioning base station, determining a difference value of distances from the at least two positioning base stations to the unmanned equipment according to the time when the at least two positioning base stations receive signals sent by signal transmitters on the unmanned equipment;
determining real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field and the difference value;
and determining an adjustment strategy aiming at the positioning model according to the positioning deviation between the real positioning data and the estimated positioning data, and adjusting the positioning model according to the adjustment strategy.
2. The method of claim 1, wherein determining trajectory planning data specifically comprises:
constructing a simulation test environment corresponding to the actual test site based on a preset simulation scene editor;
and determining the trajectory planning data in the simulation test environment, wherein the trajectory planning data comprises the planning speed of the unmanned equipment on a plurality of specified positions in the actual test field.
3. The method of claim 2, wherein determining the trajectory planning data in the simulated test environment specifically comprises:
obtaining historical positioning data obtained by positioning based on the positioning model;
determining a corresponding road shape when the track point deviation occurs according to the historical positioning data;
and determining the trajectory planning data in the simulation test environment according to the road shape.
4. The method of claim 2, wherein determining the trajectory planning data in the simulated test environment specifically comprises:
aiming at any two adjacent specified positions, determining a track point sequence of the unmanned equipment when the unmanned equipment runs between the two adjacent specified positions according to a dynamic model corresponding to the unmanned equipment and the planning speed of the unmanned equipment on the two adjacent specified positions;
and determining trajectory planning data of the unmanned equipment in the simulation test environment according to the trajectory point sequence of the unmanned equipment when the unmanned equipment runs between any two adjacent specified positions.
5. The method according to claim 1, wherein for at least two of the positioning base stations, determining a difference between distances from the at least two positioning base stations to the drone according to times at which the at least two positioning base stations receive signals transmitted by a signal transmitter on the drone specifically comprises:
for at least two positioning base stations in each positioning base station, determining a difference value of corresponding time of the at least two positioning base stations according to the time when the at least two positioning base stations receive signals sent by signal transmitters on the unmanned equipment;
and determining the difference of the distances from the at least two positioning base stations to the unmanned equipment according to the difference of the times corresponding to the at least two positioning base stations and the propagation speed corresponding to the signal sent by the signal transmitter on the unmanned equipment.
6. The method of claim 1, wherein determining the actual positioning data of the UAV according to the position information of the at least two positioning BSs in the actual test site and the difference comprises:
determining a running track of the unmanned equipment in the actual test field;
and determining the real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field, the driving track of the unmanned equipment in the actual test field and the difference value.
7. The method of claim 1, wherein determining the actual positioning data of the UAV according to the position information of the at least two positioning BSs in the actual test site and the difference comprises:
for each positioning base station combination, determining positioning data to be determined of the unmanned equipment corresponding to the positioning base station combination according to the position information of the positioning base station combination in the actual test field and the difference, wherein the positioning base station combination at least comprises three positioning base stations, and the positioning base stations contained in different positioning base station combinations are not identical;
determining an error value according to the positioning data to be determined of the unmanned equipment corresponding to each positioning base station combination;
and determining the real positioning data of the unmanned equipment according to the positioning data to be determined of the unmanned equipment corresponding to each positioning base station combination and the error value.
8. The method of claim 1, wherein determining a positioning deviation between the actual positioning data and the estimated positioning data comprises:
for each moment, taking the position deviation between the position information of the unmanned equipment corresponding to the moment in the real positioning data and the position information of the unmanned equipment corresponding to the moment in the estimated positioning data as the position deviation corresponding to the moment;
and determining the positioning deviation between the real positioning data and the estimated positioning data according to the position deviation corresponding to each moment.
9. The method of any one of claims 1 to 8, wherein the positioning the base station comprises: a UWB positioning base station, the signal transmitter comprises a UWB positioning tag.
10. The utility model provides a device of model adjustment, its characterized in that, the device is arranged in testing unmanned aerial vehicle in predetermined actual test place, be equipped with each location basic station in the actual test place, include:
the acquisition module is used for acquiring sensing data acquired when the unmanned equipment drives in the actual test field according to the determined track planning data and position information of each positioning base station in the actual test field;
the input module is used for inputting the sensing data into a positioning model to be adjusted, and predicting the position of the unmanned equipment in the actual test field to serve as predicted positioning data;
a determining module, configured to determine, for at least two of the positioning base stations, a difference between distances from the at least two positioning base stations to the unmanned device according to times at which the at least two positioning base stations receive signals sent by signal transmitters on the unmanned device;
the positioning module is used for determining real positioning data of the unmanned equipment according to the position information of the at least two positioning base stations in the actual test field and the difference value;
and the adjusting module is used for determining an adjusting strategy aiming at the positioning model according to the positioning deviation between the real positioning data and the estimated positioning data, and adjusting the positioning model according to the adjusting strategy.
11. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 9.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 9 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210037662.0A CN114460537A (en) | 2022-01-13 | 2022-01-13 | Method and device for adjusting model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210037662.0A CN114460537A (en) | 2022-01-13 | 2022-01-13 | Method and device for adjusting model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114460537A true CN114460537A (en) | 2022-05-10 |
Family
ID=81409531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210037662.0A Pending CN114460537A (en) | 2022-01-13 | 2022-01-13 | Method and device for adjusting model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114460537A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20240019532A1 (en) * | 2022-07-18 | 2024-01-18 | Dell Products L.P. | Event detection on far edge mobile devices using delayed positioning data |
-
2022
- 2022-01-13 CN CN202210037662.0A patent/CN114460537A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20240019532A1 (en) * | 2022-07-18 | 2024-01-18 | Dell Products L.P. | Event detection on far edge mobile devices using delayed positioning data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112766468B (en) | Trajectory prediction method and device, storage medium and electronic equipment | |
| WO2019126950A1 (en) | Positioning method, cloud server, terminal, system, electronic device and computer program product | |
| CN111077555B (en) | Positioning method and device | |
| CN111076739B (en) | Path planning method and device | |
| CN111238450B (en) | Visual positioning method and device | |
| CN112810625B (en) | Method and device for correcting track | |
| CN111288971B (en) | Visual positioning method and device | |
| CN111263299B (en) | Positioning method, positioning device, electronic equipment and storage medium | |
| CN110530398B (en) | Method and device for detecting precision of electronic map | |
| CN105953788A (en) | Positioning method and system for target object | |
| CN114460537A (en) | Method and device for adjusting model | |
| CN113674424B (en) | Method and device for drawing electronic map | |
| CN112734810A (en) | Obstacle tracking method and device | |
| CN112362084A (en) | Data calibration method, device and system | |
| WO2023115909A1 (en) | Unmanned device control method and apparatus, storage medium and electronic device | |
| CN114689074B (en) | Information processing method and navigation method | |
| CN116385999A (en) | Parking space identification method, device and equipment | |
| CN116176603A (en) | Method, device and equipment for determining course angle of vehicle | |
| CN117095371A (en) | Target detection method and detection device | |
| CN114299147A (en) | Positioning method, positioning device, storage medium and electronic equipment | |
| CN114332201A (en) | Model training and target detection method and device | |
| CN110244710B (en) | Automatic tracing method, device, storage medium and electronic equipment | |
| CN112712561A (en) | Picture construction method and device, storage medium and electronic equipment | |
| CN113485347B (en) | Motion trail optimization method and system | |
| CN113888624B (en) | Map construction method and 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 |