CN116534059B - Adaptive perception path decision method, device, computer equipment and storage medium - Google Patents
Adaptive perception path decision method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116534059B CN116534059B CN202310809880.6A CN202310809880A CN116534059B CN 116534059 B CN116534059 B CN 116534059B CN 202310809880 A CN202310809880 A CN 202310809880A CN 116534059 B CN116534059 B CN 116534059B
- Authority
- CN
- China
- Prior art keywords
- path
- target
- current
- attribute information
- frequency threshold
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000003044 adaptive effect Effects 0.000 title claims description 23
- 230000008447 perception Effects 0.000 title abstract description 21
- 230000015654 memory Effects 0.000 claims description 25
- 238000001514 detection method Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000013507 mapping Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The disclosure relates to the technical field of unmanned aerial vehicles, and discloses a self-adaptive perception path decision method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle and a current running path of the target vehicle; determining a decision execution frequency threshold value in the current period according to the first attribute information set; determining a current sliding window according to the decision execution frequency threshold; obtaining a reference planning path according to the first attribute information set and the second attribute information set; obtaining an offset result between the reference planning path and the current running path according to the reference planning path and the current running path; and obtaining a target planning path according to the offset result, the sliding window and the decision execution frequency threshold. The method solves the problems that the existing path decision scheme is not wide in applicability and inaccurate in path decision easily occurs when the perception information is unstable.
Description
Technical Field
The disclosure relates to the technical field of unmanned aerial vehicles, in particular to a self-adaptive perception path decision method, a self-adaptive perception path decision device, computer equipment and a storage medium.
Background
In unmanned systems, path-speed decoupling planning strategies are often employed for trajectory planning. The path planning combines the information of the intelligent bicycle and the surrounding environment to provide a spatially continuous local driving path for the bicycle, and the spatially continuous local driving path is used as a spatial basis of a final output product and a spatially continuous driving path.
In the running process of the unmanned vehicle, the planned path can change along with the change of the environment, and the decision to output the current frame path needs to ensure that the current frame path is consistent with the previous frame as much as possible, or the change range is within control tolerance, and the current frame path cannot fall into a 'hesitation' state of left-right jump. The environment information is transmitted through the sensing module, so that the stability of path planning is influenced by the sensing capability. When the environment is complex or the perception capability is relatively weak, proper measures need to be taken to avoid the influence on the path output as much as possible.
Disclosure of Invention
In view of this, the present disclosure provides a method, apparatus, computer device and storage medium for adaptive sensing path decision, so as to solve the problems of the existing path decision scheme that the applicability is not wide and the path decision is inaccurate when the sensing information is unstable.
In a first aspect, the present disclosure provides an adaptive perceptual path decision method, the method comprising:
acquiring a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle and a current running path of the target vehicle;
determining a decision execution frequency threshold value in the current period according to the first attribute information set;
determining a current sliding window according to the decision execution frequency threshold;
obtaining a reference planning path according to the first attribute information set and the second attribute information set;
obtaining an offset result between the reference planning path and the current running path according to the reference planning path and the current running path;
and obtaining a target planning path according to the offset result, the sliding window and the decision execution frequency threshold.
In the embodiment of the disclosure, a decision execution frequency threshold is determined according to a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle and a current running path of the target vehicle by acquiring the first attribute information set, a current sliding window is determined according to the decision execution frequency threshold, an offset result between a reference planning path and the current running path is obtained by determining the current reference planning path and the current running path, and finally the target planning path is obtained based on the offset result, the sliding window and the decision execution frequency threshold. Thus, the first attribute information set of the target obstacle, the second attribute information set of the target vehicle and the current running path of the target vehicle are fully considered, the decision execution frequency threshold and the sliding window are adaptively adjusted, the offset result of the lane change of the vehicle is further determined, the final target planning path is obtained, the problem that the path decision is inaccurate due to unstable perception information in the prior art is solved, meanwhile, the adaptive perception path decision in the embodiment of the disclosure can be applied to unmanned engineering vehicles, and the application range is widened.
In an alternative embodiment, determining a decision execution frequency threshold in the current period according to the first set of attribute information includes:
determining the confidence coefficient of the target obstacle according to the first attribute information set;
and determining a decision execution frequency threshold according to the confidence.
In the embodiment of the disclosure, the decision execution frequency threshold is determined based on the confidence of the target obstacle, and the decision execution frequency threshold is used as a judgment basis for path decision, so that an accurate target planning path can be found conveniently.
In an alternative embodiment, determining the current sliding window based on the decision execution frequency threshold includes:
obtaining average perceived obstacle confidence in a plurality of periods according to the decision execution frequency threshold;
and obtaining a corresponding sliding window according to the average perceived obstacle confidence.
In the embodiment of the disclosure, an average perceived obstacle confidence in a plurality of periods is determined according to a decision execution frequency threshold, a sliding window is obtained based on the average perceived obstacle confidence, the sliding window is used as a reference value for calculating the occurrence frequency of the lane change, and the final offset direction of the target vehicle is determined.
In an alternative embodiment, obtaining the offset result between the reference planned path and the current travel path according to the reference planned path and the current travel path includes:
Constructing a target coordinate system according to the lane center line in the second attribute information set;
and converting the reference planning path and the current running path into a target coordinate system to obtain an offset result of the reference planning path compared with the current running path based on the target coordinate system.
In the embodiment of the disclosure, the reference planning path and the current running path are converted into the target coordinate system, so that the reference planning path and the current running path are transferred onto the same plane for comparison, and further a relatively accurate offset result is obtained.
In an alternative embodiment, obtaining the offset result of the reference planned path compared to the current driving path based on the target coordinate system includes:
acquiring a first configuration parameter and a second configuration parameter, wherein the first configuration parameter is a position point corresponding to the minimum distance when the reference planning path is transversely deviated from the current driving path, and the second configuration parameter is the product of the speed and the time interval of the target vehicle;
determining a detection distance when the reference planning path deviates from the current driving path according to the first configuration parameter and the second configuration parameter;
determining the offset distance of the reference planning path compared with the current running path according to the intersection point between the detection distance and the current running path;
Determining the offset direction of the reference planning path compared with the current driving path according to the offset distance and the offset distance threshold value;
and outputting an offset result according to the offset direction.
In the embodiment of the disclosure, the detection distance of the reference planning path when the reference planning path deviates from the current driving path is determined based on the first configuration parameter and the second configuration parameter, the deviation distance is determined based on the detection distance, the deviation direction of the target vehicle is obtained, the deviation result is output, the whole process is completed in an automatic process, the actual situation is met, and the accuracy and the stability of the perception information can be improved.
In an alternative embodiment, obtaining the target planned path according to the offset result, the sliding window and the decision execution frequency threshold value includes:
storing the offset result in a sliding window;
determining the number in the sliding window equal to the value of the offset result;
determining the frequency of the offset in the offset direction when the target vehicle changes lanes according to the number and the sliding window;
and comparing the frequency with a decision execution frequency threshold value to obtain a target planning path.
In the embodiment of the disclosure, the frequency of the offset in the offset direction is determined based on the number of the sliding windows stored in the sliding windows and the number equal to the offset result value, so that the offset direction of the target vehicle can be determined more accurately, and the judgment of the error offset caused by the error of the sensing sensor is avoided.
In an alternative embodiment, comparing the frequency with a decision-performing frequency threshold to obtain a target planned path includes:
under the condition that the frequency is greater than or equal to the decision execution frequency threshold, taking the reference planning path as a target planning path, and updating the target planning path to a vehicle running record database;
and under the condition that the frequency is smaller than the decision execution frequency threshold value, acquiring the historical driving track of the target vehicle, and taking the historical driving track as a target planning path.
In the embodiment of the disclosure, according to the comparison condition of the magnitude values between the frequency and the decision execution frequency threshold, the reference planned path is used as the target planned path or the historical driving track is used as the target planned path, so that whether the target vehicle has a lane change or not is ensured to have corresponding planned path output.
In a second aspect, the present disclosure provides an adaptive perceptual path decision making apparatus, the apparatus comprising:
the acquisition module is used for acquiring a first attribute information set of a plurality of target barriers, a second attribute information set of a target vehicle and a current running path of the target vehicle;
the first determining module is used for determining a decision execution frequency threshold value in the current period according to the first attribute information set;
The second determining module is used for determining a current sliding window according to the decision execution frequency threshold value;
the first obtaining module is used for obtaining a reference planning path according to the first attribute information set and the second attribute information set;
the second obtaining module is used for obtaining an offset result between the reference planning path and the current running path according to the reference planning path and the current running path;
and the third obtaining module is used for obtaining the target planning path according to the offset result, the sliding window and the decision execution frequency threshold.
In a third aspect, the present disclosure provides a computer device comprising: the processor is in communication connection with the memory, and the memory stores computer instructions, so that the processor executes the computer instructions to perform the adaptive sensing path decision method according to the first aspect or any implementation manner corresponding to the first aspect.
In a fourth aspect, the present disclosure provides a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the adaptive perceptual path decision method of the first aspect or any corresponding embodiment thereof.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the prior art, the drawings that are required in the detailed description or the prior art will be briefly described, it will be apparent that the drawings in the following description are some embodiments of the present disclosure, and other drawings may be obtained according to the drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a flow diagram of an adaptive perceptual path decision method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a mapping for determining a sliding window according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of an offset comparison of a reference planned path compared to a current travel path in accordance with an embodiment of the present disclosure;
FIG. 4 is an overall flow diagram of an adaptive perceptual path decision method according to an embodiment of the present disclosure;
FIG. 5 is a block diagram of an adaptive perceptual path decision means according to an embodiment of the present disclosure;
fig. 6 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present disclosure.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are some embodiments of the present disclosure, but not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person skilled in the art would obtain without making any inventive effort are within the scope of protection of this disclosure. In the current unmanned field, the planned path changes along with the change of the environment, and the environment information is transmitted through the perception module, so that the stability of path planning is influenced by the perception capability. When the environment is complex or the perception capability is relatively weak, inaccurate path planning often occurs.
Based on the above problems, in the current related art, an alternative path is generally obtained from the obstacle road segments based on the information such as the obstacle, the pose information of the vehicle, the driving path of the vehicle, and the like, and then an optimal path is selected from the alternative paths, so that the existing method is applicable to the situations of fewer obstacles, low road condition complexity and accurate perception information, and the corresponding defects are that: the method has the advantages that the method is not wide in application (such as difficult to achieve a good effect on unmanned engineering vehicle) and the problem of inaccurate path decision is easy to occur when the perception information is unstable.
In order to solve the technical problems of the related art described above, according to an embodiment of the present disclosure, there is provided an adaptive perception path decision method embodiment, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and although a logic order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different from that herein.
In this embodiment, an adaptive sensing path decision method is provided, and the method may be used in a system, where the system may include a road condition sensing module, a map module, a vehicle driving path recording module, a path planning module, and an information acquisition module disposed on a vehicle, where the road condition sensing module, the map module, the vehicle driving path recording module, and the path planning module may be integrally disposed on a cloud platform server side, and fig. 1 is a flowchart of adaptive sensing path decision according to an embodiment of the present disclosure, and as shown in fig. 1, the flowchart may be applied to the cloud platform server side, and includes the following steps:
Step S101, acquiring a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle, and a current travel path of the target vehicle.
In the embodiment of the disclosure, a first attribute information set of a plurality of target obstacles may be obtained from a road condition sensing module at a cloud platform server side, where the first attribute information is dynamic information which may represent that a target vehicle is on a driving road, and static information describing the target obstacle, such as a size, a shape, a heading, a position, and the like, and the first attribute information set is formed by the information.
And obtaining some information capable of representing the target vehicle, such as the current course, the current position, the current speed and the like, from an information acquisition module arranged in the target vehicle, forming a second attribute information set by the information, transmitting the second attribute information set to a cloud platform server side by the target vehicle, and receiving the second attribute information set of the target vehicle by the cloud platform server side.
And acquiring the current driving path of the target vehicle from a vehicle driving path recording module at the cloud platform server side.
Step S102, determining a decision execution frequency threshold in the current period according to the first attribute information set.
Optionally, determining the decision execution frequency threshold in the current period according to the first attribute information set of the target obstacle and the period of the current planned path. The decision execution frequency threshold is mainly used for planning lane change deviation of the target vehicle.
Step S103, determining the current sliding window according to the decision execution frequency threshold.
Optionally, after the decision execution frequency threshold is obtained, determining the decision execution frequency threshold of the first k cycles according to the decision execution frequency threshold, and setting a corresponding sliding window according to historical experience and actual conditions.
The sliding window is a step size for storing data, and can be understood as a storage container.
Step S104, obtaining a reference planning path according to the first attribute information set and the second attribute information set.
Optionally, according to information in the first attribute information set and the second attribute information set, a reference planning path obtained after the path planning module performs path planning is obtained.
If the manual connection or the path planning abnormality occurs, resetting the sliding window; otherwise, the path planning is successful.
Step S105, according to the reference planning path and the current running path, an offset result between the reference planning path and the current running path is obtained.
Optionally, after obtaining the planned reference planned path and the current running path of the target vehicle, an offset result between the reference planned path and the current running path may be obtained, where the offset result is generally based on the current running path, and an offset condition obtained by the reference planned path compared to the current running path is used as the offset result.
And step S106, obtaining a target planning path according to the offset result, the sliding window and the decision execution frequency threshold.
Optionally, in the embodiment of the present disclosure, the target planned path may be obtained according to an offset result between the reference planned path and the current travel path, a sliding window, and a decision execution frequency threshold.
In the embodiment of the disclosure, a decision execution frequency threshold is determined according to a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle and a current running path of the target vehicle by acquiring the first attribute information set, a current sliding window is determined according to the decision execution frequency threshold, an offset result between a reference planning path and the current running path is obtained by determining the current reference planning path and the current running path, and finally the target planning path is obtained based on the offset result, the sliding window and the decision execution frequency threshold. Thus, the first attribute information set of the target obstacle, the second attribute information set of the target vehicle and the current running path of the target vehicle are fully considered, the decision execution frequency threshold and the sliding window are adaptively adjusted, the offset result of the lane change of the vehicle is further determined, the final target planning path is obtained, the problem that the path decision is inaccurate due to unstable perception information in the prior art is solved, meanwhile, the adaptive perception path decision in the embodiment of the disclosure can be applied to unmanned engineering vehicles, and the application range is widened.
In some alternative embodiments, determining the decision execution frequency threshold for the current period based on the first set of attribute information includes:
determining the confidence coefficient of the target obstacle according to the first attribute information set;
and determining a decision execution frequency threshold according to the confidence.
Optionally, according to some attribute information within the first set of attribute information, such as headingPosition ofObtaining the confidence degree of the target obstacle>。
Calculating a decision execution frequency threshold for the current cycle according to the following formula:
wherein m is the number of obstacles to be considered,is the i +.>。
In the embodiment of the disclosure, the decision execution frequency threshold is determined based on the confidence of the target obstacle, and the decision execution frequency threshold is used as a judgment basis for path decision, so that an accurate target planning path can be found conveniently.
In some alternative embodiments, determining the current sliding window based on the decision execution frequency threshold includes:
obtaining average perceived obstacle confidence in a plurality of periods according to the decision execution frequency threshold;
and obtaining a corresponding sliding window according to the average perceived obstacle confidence.
Optionally, the average perceived obstacle confidence is calculated taking into account the decision execution frequency threshold for the first k cycles:
According toSetting the mapping relation between real numbers and integers to obtain the size N of the sliding window.
As shown in fig. 2, if100, the sliding window is 1; if->70, falls between [60, 80), the sliding window is 20. It should be noted that, the mapping relationship shown in fig. 2 may be flexibly set according to practical situations, and the current mapping relationship is set based on historical experience.
In the embodiment of the disclosure, an average perceived obstacle confidence in a plurality of periods is determined according to a decision execution frequency threshold, a sliding window is obtained based on the average perceived obstacle confidence, the sliding window is used as a reference value for calculating the occurrence frequency of the lane change, and the final offset direction of the target vehicle is determined.
In some alternative embodiments, obtaining the offset result between the reference planned path and the current travel path according to the reference planned path and the current travel path includes:
acquiring a lane center line;
constructing a target coordinate system according to the lane center line;
and converting the reference planning path and the current running path into a target coordinate system to obtain an offset result of the reference planning path compared with the current running path based on the target coordinate system.
Optionally, a lane center line to which the target vehicle belongs is obtained from the map module, a target coordinate system is constructed based on the lane center line, the target coordinate system can be an SL coordinate system, then the reference planning path and the current running path are converted into the SL coordinate system, the reference planning path for planning the time is compared with the current running path obtained by the vehicle running path recording module, and an offset result of the reference planning path compared with the current running path is obtained.
The SL coordinate system is a curve coordinate system, S represents the direction of the center line of the road, and L represents the direction perpendicular to the center line of the road. When the vehicle runs on the structured road, the SL coordinate system is more fit with the actual requirement than the XY coordinate system.
In the embodiment of the disclosure, the reference planning path and the current running path are converted into the target coordinate system, so that the reference planning path and the current running path are transferred onto the same plane for comparison, and further a relatively accurate offset result is obtained.
In some alternative embodiments, obtaining the offset result of the reference planned path compared to the current travel path based on the target coordinate system includes:
acquiring a first configuration parameter and a second configuration parameter, wherein the first configuration parameter is a position point corresponding to the minimum distance when the reference planning path is transversely deviated from the current driving path, and the second configuration parameter is the product of the speed and the time interval of the target vehicle;
Determining a detection distance when the reference planning path deviates from the current driving path according to the first configuration parameter and the second configuration parameter;
determining the offset distance of the reference planning path compared with the current running path according to the intersection point between the detection distance and the current running path;
determining the offset direction of the reference planning path compared with the current driving path according to the offset distance and the offset distance threshold value;
and outputting an offset result according to the offset direction.
Alternatively, as shown in fig. 3, there are 3 offset directions in the figure, respectively: 0 represents no offset, and keeps running; 1 represents left offset; 2 represents a right bias. In the embodiment of the disclosure, in order to obtain the offset direction of the target vehicle more accurately, a first configuration parameter and a second configuration parameter are set, where the first configuration parameter is a position point corresponding to the minimum distance when the reference planned path is compared with the current driving path, that ismin_sThe second configuration parameter is the product of the speed and time interval of the target vehicle, i.e. the speed×time_distance。
Then selecting the maximum value of the first configuration parameter and the second configuration parameter, and taking the maximum value as the detection distance when the reference planning path deviates from the current driving path, namely in FIG. 3 check_s。
From the slavecheck_sA dotted line is led out from the length terminal of the path (1) and forms an intersection point with the current running path, and the left side or the right side of the departure point intersects with the line (1) or the line (2) to further obtain the offset distance of the reference planning path compared with the current running path, namely the offset distance in fig. 3。
Obtaining a preset offset distance threshold, i.eFor example, set to +.>Meter, then determining the offset direction of the reference planned path compared with the current driving path according to the comparison condition of the offset distance and the offset distance threshold value:
the output number represents the offset result of the target vehicle.
Naturally, according to the actual setting, when the reference planned path in the path planning module is the parking path, the number 3 corresponding to the parking path is output. Since the parking path is not offset in direction, it is not shown in fig. 3.
In the embodiment of the disclosure, the detection distance of the reference planning path when the reference planning path deviates from the current driving path is determined based on the first configuration parameter and the second configuration parameter, the deviation distance is determined based on the detection distance, the deviation direction of the target vehicle is obtained, the deviation result is output, the whole process is completed in an automatic process, the actual situation is met, and the accuracy and the stability of the perception information can be improved. In some alternative embodiments, obtaining the target planned path according to the offset result, the sliding window, and the decision execution frequency threshold includes:
Storing the obtained offset result in a sliding window, so that at least one offset result is stored in the sliding window;
determining at least one offset result as the same number of offset results obtained;
determining the frequency of the offset in the offset direction when the target vehicle changes lanes according to the number and the sliding window;
and comparing the frequency with a decision execution frequency threshold value to obtain a target planning path.
Optionally, the offset result is stored in a sliding window; if the obtained deviation result is 0, outputting the current path planning, updating the record information of the vehicle running record module, ending the current planning, and entering the next period; otherwise, calculating the number of at least one stored offset result (such as 0,1, 2) in the sliding window, which is the same as the number of the currently obtained offset result (such as 0), and recording n (current n=2), and then calculating the offset frequency of the current offset direction of the track changeFrequency +.>And comparing the target planning path with a decision execution frequency threshold value to obtain a target planning path, wherein N is the size of a sliding window.
In the embodiment of the disclosure, the frequency of the offset in the offset direction is determined based on the number of the sliding windows stored in the sliding windows and the number equal to the offset result value, so that the offset direction of the target vehicle can be determined more accurately, and the judgment of the error offset caused by the error of the sensing sensor is avoided.
In some alternative embodiments, comparing the frequency to a decision-performing frequency threshold to obtain a target planned path includes:
under the condition that the frequency is greater than or equal to the decision execution frequency threshold, taking the reference planning path as a target planning path, and updating the target planning path to a vehicle running record database;
and under the condition that the frequency is smaller than the decision execution frequency threshold value, acquiring the historical driving track of the target vehicle, and taking the historical driving track as a target planning path.
Alternatively, ifOutputting the current path planThe reference planning path in the above embodiment is updated to the record information of the vehicle running record module, and then the sliding window is reset to finish the planning and enter the next period;
otherwise, the historical driving track of the target vehicle is obtained. If the historical driving track can be successfully obtained, outputting the historical driving track, ending the programming and entering the next period; if the historical driving track cannot be obtained, for example, when the current driving track is in the first frame, outputting a reference planning path, updating the reference planning path to the information recorded by the vehicle driving record module, ending the planning, and entering the next period.
In the embodiment of the disclosure, according to the comparison condition of the magnitude values between the frequency and the decision execution frequency threshold, the reference planned path is used as the target planned path or the historical driving track is used as the target planned path, so that whether the target vehicle has a lane change or not is ensured to have corresponding planned path output.
In some alternative implementations, as shown in fig. 4, fig. 4 is an overall flow diagram of an adaptive perceptual path decision method according to an embodiment of the disclosure, and the specific flow is as follows:
starting; judging whether a manual connection pipe exists or not; if the manual connection pipe exists, resetting the sliding window, and ending the flow; if the artificial takeover does not exist, calculating the size of a sliding window and the decision execution probability according to the confidence coefficient of the obstacle set to be considered, inputting the size of the sliding window and the decision execution probability into a path planning module, inputting obstacle information (map and obstacle) of an information acquisition module, inputting vehicle information (chassis and positioning) into the path planning module, and outputting path planning by the path planning module;
judging whether the path planning is abnormal or not; if so, resetting the sliding window; otherwise, acquiring a planned path, comparing the planned path with the path read from the vehicle driving path recording module under the SL coordinate system, and outputting the current comparison result: 0: keeping running; 1: left-hand offset; 2: right-hand deflection; 3: a parking path. Writing the comparison result into a sliding window;
Judging whether the comparison result is 0, if so, outputting the current planning path, updating the vehicle driving path recording module and ending the flow; if the value is not 0, reading the comparison result stored in the sliding window, and calculating the number in the sliding window equal to the value of the comparison result;
judging whether the number is larger than a preset probability value or not; if the current planned path is larger than the current planned path, the vehicle driving path recording module is updated, and the sliding window is reset; otherwise, judging whether the history track can be acquired; if the history track can be acquired, outputting the history track, and ending the flow; otherwise, outputting the current planning path and updating the vehicle driving path recording module.
The embodiment also provides an adaptive sensing path decision device, which is used for implementing the foregoing embodiments and preferred implementations, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The embodiment provides an adaptive sensing path decision device, as shown in fig. 5, including:
An obtaining module 501, configured to obtain a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle, and a current travel path of the target vehicle;
a first determining module 502, configured to determine, according to the first attribute information set, a decision execution frequency threshold in the current period;
a second determining module 503, configured to determine a current sliding window according to the decision execution frequency threshold;
a first obtaining module 504, configured to obtain a reference planning path according to the first attribute information set and the second attribute information set;
a second obtaining module 505, configured to obtain an offset result between the reference planned path and the current running path according to the reference planned path and the current running path;
a third obtaining module 506, configured to obtain a target planned path according to the offset result, the sliding window, and the decision execution frequency threshold.
In the embodiment of the disclosure, a decision execution frequency threshold is determined according to a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle and a current running path of the target vehicle by acquiring the first attribute information set, a current sliding window is determined according to the decision execution frequency threshold, an offset result between a reference planning path and the current running path is obtained by determining the current reference planning path and the current running path, and finally the target planning path is obtained based on the offset result, the sliding window and the decision execution frequency threshold. Thus, the first attribute information set of the target obstacle, the second attribute information set of the target vehicle and the current running path of the target vehicle are fully considered, the decision execution frequency threshold and the sliding window are adaptively adjusted, the offset result of the lane change of the vehicle is further determined, the final target planning path is obtained, the problem that the path decision is inaccurate due to unstable perception information in the prior art is solved, meanwhile, the adaptive perception path decision in the embodiment of the disclosure can be applied to unmanned engineering vehicles, and the application range is widened.
In some alternative embodiments, the first determining module 502 includes:
a first determining unit, configured to determine a confidence level of the target obstacle according to the first attribute information set;
and the second determining unit is used for determining a decision execution frequency threshold according to the confidence level.
In some alternative embodiments, the second determining module 503 includes:
the first obtaining unit is used for obtaining the average perceived obstacle confidence in a plurality of periods according to the decision execution frequency threshold;
and the second obtaining unit is used for obtaining a corresponding sliding window according to the average perceived obstacle confidence.
In some alternative embodiments, the second obtaining module 505 includes:
an acquisition unit configured to acquire a lane center line;
a construction unit for constructing a target coordinate system according to the lane center line;
and the third obtaining unit is used for converting the reference planning path and the current running path into a target coordinate system and obtaining an offset result of the reference planning path compared with the current running path based on the target coordinate system.
In some alternative embodiments, the third deriving unit comprises:
the first acquisition submodule is used for acquiring a first configuration parameter and a second configuration parameter, wherein the first configuration parameter is a position point corresponding to the minimum distance when the reference planning path generates transverse deviation compared with the current driving path, and the second configuration parameter is the product of the speed and the time interval of the target vehicle;
The first determining submodule is used for determining a detection distance when the reference planning path deviates from the current running path according to the first configuration parameter and the second configuration parameter;
the second determining submodule is used for determining the offset distance of the reference planning path compared with the current running path according to the intersection point between the detection distance and the current running path;
a third determining submodule, configured to determine an offset direction of the reference planned path compared with the current travel path according to the offset distance and the offset distance threshold;
and the output sub-module is used for outputting an offset result according to the offset direction.
In some alternative embodiments, the third deriving module 506 includes:
the storage unit is used for storing the obtained offset result in the sliding window, so that at least one offset result is stored in the sliding window;
a third determining unit configured to determine at least one offset result by the same amount as the obtained offset result;
a fourth determining unit for determining a frequency of an offset in which an offset direction occurs when the target vehicle changes lanes, according to the number and the sliding window;
and a fourth obtaining unit, configured to compare the frequency with a decision execution frequency threshold value to obtain a target planned path.
In some alternative embodiments, the fourth deriving unit comprises:
the updating sub-module is used for taking the reference planning path as a target planning path and updating the target planning path to the vehicle running record database under the condition that the frequency is greater than or equal to the decision execution frequency threshold value;
and the second acquisition sub-module is used for acquiring the historical driving track of the target vehicle and taking the historical driving track as a target planning path under the condition that the frequency is smaller than the decision execution frequency threshold value.
The adaptive perceptual path decision means in this embodiment are presented in the form of functional units, here referred to as ASIC circuits, processors and memories executing one or more software or fixed programs, and/or other devices that can provide the above described functionality.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The embodiment of the disclosure also provides a computer device, which is provided with the adaptive sensing path decision device shown in the above figure 5.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a computer device according to an alternative embodiment of the disclosure, as shown in fig. 6, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 6.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform a method for implementing the embodiments described above.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created from the use of the computer device of the presentation of a sort of applet landing page, and the like. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
The presently disclosed embodiments also provide a computer readable storage medium, and the methods described above according to the presently disclosed embodiments may be implemented in hardware, firmware, or as recordable storage medium, or as computer code downloaded over a network that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and is to be stored in a local storage medium, such that the methods described herein may be stored on such software processes on a storage medium using a general purpose computer, special purpose processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present disclosure have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the disclosure, and such modifications and variations are within the scope defined by the appended claims.
Claims (10)
1. An adaptive perceptual path decision method, the method comprising:
acquiring a first attribute information set of a plurality of target obstacles, a second attribute information set of a target vehicle and a current running path of the target vehicle;
determining a decision execution frequency threshold value in the current period according to the first attribute information set;
determining a current sliding window according to the decision execution frequency threshold;
obtaining a reference planning path according to the first attribute information set and the second attribute information set;
obtaining an offset result between the reference planning path and the current running path according to the reference planning path and the current running path;
and obtaining a target planning path according to the offset result, the sliding window and the decision execution frequency threshold.
2. The method of claim 1, wherein determining a decision execution frequency threshold for a current period from the first set of attribute information comprises:
Determining the confidence of the target obstacle according to the first attribute information set;
and determining the decision execution frequency threshold according to the confidence level.
3. The method of claim 2, wherein determining the current sliding window based on the decision execution frequency threshold comprises:
obtaining average perceived obstacle confidence in a plurality of periods according to the decision execution frequency threshold;
and obtaining the corresponding sliding window according to the average perceived obstacle confidence.
4. The method of claim 1, wherein the obtaining an offset result between the reference planned path and the current travel path from the reference planned path and the current travel path comprises:
acquiring a lane center line;
constructing a target coordinate system according to the lane center line;
and converting the reference planning path and the current running path into the target coordinate system to obtain the offset result of the reference planning path compared with the current running path based on the target coordinate system.
5. The method of claim 4, wherein the deriving the offset result based on the reference planned path compared to the current travel path in the target coordinate system comprises:
Acquiring a first configuration parameter and a second configuration parameter, wherein the first configuration parameter is a position point corresponding to the minimum distance when the reference planning path generates lateral deviation compared with the current driving path, and the second configuration parameter is a product of the speed and the time interval of the target vehicle;
determining a detection distance of the reference planning path when the reference planning path deviates from the current running path according to the first configuration parameter and the second configuration parameter;
determining an offset distance of the reference planning path compared with the current running path according to an intersection point between the detection distance and the current running path;
determining the offset direction of the reference planning path compared with the current driving path according to the offset distance and the offset distance threshold;
and outputting the offset result according to the offset direction.
6. The method according to claim 1 or 5, wherein the obtaining a target planned path according to the offset result, the sliding window, and the decision execution frequency threshold comprises:
storing the obtained offset result in a sliding window, so that at least one offset result is stored in the sliding window;
Determining that the at least one offset result is the same number as the offset result;
determining the frequency of the offset in the offset direction when the target vehicle changes lanes according to the number and the sliding window;
and comparing the frequency with the decision execution frequency threshold value to obtain the target planning path.
7. The method of claim 6, wherein comparing the frequency to the decision execution frequency threshold results in the target planned path, comprising:
taking the reference planning path as the target planning path and updating the target planning path to a vehicle running record database under the condition that the frequency is greater than or equal to the decision execution frequency threshold value;
and under the condition that the frequency is smaller than the decision execution frequency threshold value, acquiring a historical driving track of the target vehicle, and taking the historical driving track as the target planning path.
8. An adaptive perceptual path decision making apparatus, the apparatus comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring a first attribute information set of a plurality of target barriers, a second attribute information set of a target vehicle and a current running path of the target vehicle;
The first determining module is used for determining a decision execution frequency threshold value in the current period according to the first attribute information set;
the second determining module is used for determining a current sliding window according to the decision execution frequency threshold;
the first obtaining module is used for obtaining a reference planning path according to the first attribute information set and the second attribute information set;
the second obtaining module is used for obtaining an offset result between the reference planning path and the current running path according to the reference planning path and the current running path;
and a third obtaining module, configured to obtain a target planned path according to the offset result, the sliding window, and the decision execution frequency threshold.
9. A computer device, comprising:
a memory and a processor in communication with each other, the memory having stored therein computer instructions which, upon execution, cause the processor to perform the method of any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310809880.6A CN116534059B (en) | 2023-07-04 | 2023-07-04 | Adaptive perception path decision method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310809880.6A CN116534059B (en) | 2023-07-04 | 2023-07-04 | Adaptive perception path decision method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116534059A CN116534059A (en) | 2023-08-04 |
| CN116534059B true CN116534059B (en) | 2023-09-08 |
Family
ID=87454526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310809880.6A Active CN116534059B (en) | 2023-07-04 | 2023-07-04 | Adaptive perception path decision method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116534059B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117382639B (en) * | 2023-12-05 | 2024-02-23 | 上海集度汽车有限公司 | Vehicle control method, device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105424026A (en) * | 2015-11-04 | 2016-03-23 | 中国人民解放军国防科学技术大学 | Indoor navigation and localization method and system based on point cloud tracks |
| CN113165661A (en) * | 2018-12-17 | 2021-07-23 | 大众汽车股份公司 | Method and system for determining a modified trajectory of a vehicle |
| CN115179970A (en) * | 2022-09-14 | 2022-10-14 | 毫末智行科技有限公司 | Path planning method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11592830B2 (en) * | 2020-05-29 | 2023-02-28 | Zoox, Inc. | Trajectory generation using lateral offset biasing |
-
2023
- 2023-07-04 CN CN202310809880.6A patent/CN116534059B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105424026A (en) * | 2015-11-04 | 2016-03-23 | 中国人民解放军国防科学技术大学 | Indoor navigation and localization method and system based on point cloud tracks |
| CN113165661A (en) * | 2018-12-17 | 2021-07-23 | 大众汽车股份公司 | Method and system for determining a modified trajectory of a vehicle |
| CN115179970A (en) * | 2022-09-14 | 2022-10-14 | 毫末智行科技有限公司 | Path planning method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116534059A (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111009153B (en) | Training method, device and equipment of trajectory prediction model | |
| CN111932887B (en) | Method and equipment for generating lane-level track data | |
| CN113330454A (en) | Method and apparatus for multi-sensor data fusion for automated and autonomous vehicles | |
| CN116534059B (en) | Adaptive perception path decision method, device, computer equipment and storage medium | |
| CN112394725B (en) | Prediction and reaction field of view based planning for autopilot | |
| KR102620325B1 (en) | Methods, devices, electronic devices and storage media for determining traffic flow information | |
| US20220057231A1 (en) | Methods and apparatuses for detecting map calibration errors | |
| CN112465193B (en) | Parameter optimization method and device for multi-sensor data fusion | |
| CN114174137A (en) | Source lateral offset of ADAS or AD features | |
| CN111192327B (en) | Method and device for determining the orientation of an obstacle | |
| CN114663804A (en) | Driving area detection method, device, mobile equipment and storage medium | |
| CN114694111A (en) | Vehicle positioning | |
| EP3155454B1 (en) | Method and system for adapting a navigation system | |
| CN110109165B (en) | Method and device for detecting abnormal points in driving track | |
| CN115856979B (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN116279410A (en) | Heading error compensation method, system, device and storage medium | |
| CN113261007A (en) | Method and apparatus for multi-sensor data fusion for autonomous and autonomous vehicles | |
| CN116295490A (en) | Vehicle positioning method and device, electronic equipment and storage medium | |
| CN114104005B (en) | Decision-making method, device and equipment of automatic driving equipment and readable storage medium | |
| US20220404506A1 (en) | Online validation of lidar-to-lidar alignment and lidar-to-vehicle alignment | |
| CN114358038A (en) | Two-dimensional code coordinate calibration method and device based on vehicle high-precision positioning | |
| CN118289009B (en) | Method and device for determining the yaw angle of a trailer | |
| WO2024150372A1 (en) | Software update system, control center, and software update device | |
| CN118500413B (en) | Unmanned navigation method and system | |
| CN114889593B (en) | Lane departure intervention method, device, equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |