CN113343448A - Control effect evaluation method and device, electronic equipment and storage medium - Google Patents

Control effect evaluation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113343448A
CN113343448A CN202110573994.6A CN202110573994A CN113343448A CN 113343448 A CN113343448 A CN 113343448A CN 202110573994 A CN202110573994 A CN 202110573994A CN 113343448 A CN113343448 A CN 113343448A
Authority
CN
China
Prior art keywords
information
offset information
target
offset
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.)
Granted
Application number
CN202110573994.6A
Other languages
Chinese (zh)
Other versions
CN113343448B (en
Inventor
窦凤谦
阎兴
边学鹏
张亮亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jingdong Kunpeng Jiangsu Technology Co Ltd
Original Assignee
Jingdong Kunpeng Jiangsu Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jingdong Kunpeng Jiangsu Technology Co Ltd filed Critical Jingdong Kunpeng Jiangsu Technology Co Ltd
Priority to CN202110573994.6A priority Critical patent/CN113343448B/en
Publication of CN113343448A publication Critical patent/CN113343448A/en
Application granted granted Critical
Publication of CN113343448B publication Critical patent/CN113343448B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393Score-carding, benchmarking or key performance indicator [KPI] analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00Details relating to CAD techniques
    • G06F2111/10Numerical modelling

Abstract

The embodiment of the invention discloses a control effect evaluation method, a control effect evaluation device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a group of preset time points, and determining group offset information of each preset time point according to actual running associated information and reference running associated information of the target vehicle at each preset time point in the group of preset time points; determining an initial effect evaluation value of the target vehicle according to each group of offset information and vehicle running state information corresponding to each group of offset information; and determining the target control effect of the target vehicle according to the initial effect evaluation value and the preset effect evaluation value. The technical scheme of the embodiment of the invention solves the problem that the control effect of the target vehicle is not good because the control mode or the control coefficient of the target vehicle cannot be optimized because no corresponding effect evaluation method is used for evaluating the control effect of the target vehicle at present, and realizes the technical effect of effectively evaluating the control effect of the target vehicle.

Description

Control effect evaluation method and device, electronic equipment and storage medium
Technical Field
The embodiment of the invention relates to the technical field of unmanned driving, in particular to a control effect evaluation method and device, electronic equipment and a storage medium.
Background
At present, along with the rapid development of the unmanned technology, more and more unmanned vehicles are controlled. The unmanned vehicle can travel based on different control methods. In determining which control method is superior to an unmanned vehicle, it is estimated based on the control effect on the unmanned vehicle. The existing method for determining whether the driving effect of the unmanned vehicle is better or not has no uniform determination mode, and mostly relies on manual judgment.
When the present invention is implemented based on the above-described embodiments, the inventors have found that the following problems occur:
when the control effect is determined based on the running state of the unmanned vehicle which is monitored manually, manual participation is needed, and the problems of high labor cost and inaccuracy exist. Further, when the control effect is evaluated based on manual participation, the control effect of the target vehicle cannot be accurately and effectively evaluated due to the fact that the evaluation standards are not uniform, human errors exist, and the like.
Disclosure of Invention
The invention provides a control effect evaluation method, a control effect evaluation device, electronic equipment and a storage medium, which are used for effectively and accurately evaluating a target control effect on a target vehicle.
In a first aspect, an embodiment of the present invention provides a control effect evaluation method, where the method includes:
acquiring a group of preset time points, and determining group offset information of each preset time point according to actual running associated information and reference running associated information of the target vehicle at each preset time point in the group of preset time points; wherein the set of offset information includes at least one offset information; the reference driving related information is determined based on a preset generated reference planned path;
determining an initial effect evaluation value of the target vehicle according to each group of offset information and vehicle running state information corresponding to each group of offset information;
and determining the target control effect of the target vehicle according to the initial effect evaluation value and a preset effect evaluation value.
In a second aspect, an embodiment of the present invention further provides a control effect evaluation apparatus, where the apparatus includes:
the group offset information determining module is used for acquiring a group of preset time points and determining group offset information of each preset time point according to actual running associated information and reference running associated information of the target vehicle at each preset time point in the group of preset time points; wherein the set of offset information includes at least one offset information; the reference driving related information is determined based on a preset generated reference planned path;
the initial effect evaluation value determining module is used for determining the initial effect evaluation value of the target vehicle according to each group of offset information and the vehicle running state information corresponding to each group of offset information;
and the target control effect determining module is used for determining the control effect of the target vehicle according to the initial effect evaluation value and a preset evaluation effect value.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the control effect evaluation method according to any one of the embodiments of the present invention.
In a fourth aspect, the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are used for executing the control effect evaluation method according to any one of the embodiments of the present invention.
The technical scheme of the embodiment of the invention determines the group offset information of each preset time point by processing the actual running related information and the corresponding reference running related information of each preset time point, determines the initial effect evaluation value of the target vehicle according to each group of offset information and the corresponding vehicle running state information, and can determine the target control effect of the target vehicle based on the initial effect evaluation value and the preset effect evaluation value, thereby solving the technical problems that the control effect of the current control mode on the target vehicle is not evaluated by a corresponding effect evaluation method in the prior art, the control mode or the control coefficient of the target vehicle cannot be optimized, and the control effect is poor, effectively evaluating the control effect of the target vehicle, and further effectively adjusting the control mode or the control coefficient corresponding to the target vehicle according to the evaluation result, thereby improving the technical effects of the running safety and the accuracy of the target vehicle.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, a brief description is given below of the drawings used in describing the embodiments. It should be clear that the described figures are only views of some of the embodiments of the invention to be described, not all, and that for a person skilled in the art, other figures can be derived from these figures without inventive effort.
Fig. 1 is a schematic flow chart of a control effect evaluation method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a control effect evaluation method according to a second embodiment of the present invention;
fig. 3 is a schematic flow chart of a control effect evaluation method according to a third embodiment of the present invention;
fig. 4 is a schematic flow chart illustrating a control effect evaluation method according to a fourth embodiment of the present invention;
fig. 5 is a schematic flowchart of a control effect evaluation method according to a fifth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a control effect evaluation apparatus according to a sixth embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to a seventh embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a schematic flow chart of a control effect evaluation method according to an embodiment of the present invention, which is applicable to a situation where a control effect of a current control mode on an unmanned vehicle is determined, and the method may be executed by a control effect evaluation device, where the device may be implemented in the form of software and/or hardware, and the hardware may be an electronic device, and the electronic device may be a mobile terminal, a PC terminal, or the like.
Before the technical solution of the present embodiment is introduced, an application scenario is exemplarily described.
Before the unmanned vehicle (unmanned vehicle) runs, a corresponding running path, namely a reference planned path, can be planned for the unmanned vehicle according to a starting point, an end point and a passing point of the unmanned vehicle. The reference planned path may be sent to the respective target vehicle to cause the target vehicle to travel according to the reference planned path. The reference planned path is a series of discrete reference points, and each discrete reference point may include position information, length information between every two discrete points, speed information, acceleration information, time information, and the like. The division of the discrete reference points (discrete points) may be based on time information or distance information, and the specific division manner is not specifically limited herein. The control targets of the unmanned vehicle are mainly as follows: the target vehicle is caused to reach a specific location at a specific speed at a specific time.
In the process that the target vehicle runs on the basis of the reference planned path, no corresponding evaluation method is available for evaluating the control effect of the current control mode on the unmanned vehicle, and therefore the problem that whether the control mode or the control coefficient corresponding to the target vehicle is optimized or not cannot be determined exists. Based on the above problems, the driving effect of the unmanned vehicle can be evaluated based on the technical solution of the embodiment.
As shown in fig. 1, the method includes:
s110, a group of preset time points is obtained, and group offset information of each preset time point is determined according to actual running related information and reference running related information of the target vehicle at each preset time point in the group of preset time points.
When the target vehicle travels according to the reference planned path, the travel related information of the target vehicle may be acquired in real time, or discrete time points for acquiring the travel related information of the target vehicle may be preset, so that the actual travel related information of the target vehicle is acquired at each discrete time point, and the set discrete time points may be used as preset time points. The set of respective preset time points may be regarded as a set of preset time points. For example, if the vehicle travels for 1 hour, each minute may be taken as a time point, and then 60 preset time points may be obtained and taken as a group of preset time points. The preset time points may be determined at equal distance intervals, for example, when the driving distance of the vehicle is 3000m, the time point corresponding to each 5m position is taken as the preset time point, 600 preset time points may be obtained at this time, and 600 preset time points may be taken as a group of preset time points.
Each unmanned vehicle can be a target vehicle, the technical scheme of the embodiment can be adopted for the evaluation of the control effect of each unmanned vehicle, and for the purpose of clearly describing the technical scheme of the embodiment, the evaluation of the control effect of one of the unmanned vehicles can be taken as an example for description. At this time, the vehicle whose control effect is currently determined may be the target vehicle.
It should be noted that, during the running process of the unmanned vehicle, the running path of the unmanned vehicle may be determined according to the starting position and the ending position of the vehicle and the position of the route during the running process. The travel path determined at this time may be used as the reference planned path. It should also be noted that the reference planned path is composed of at least two discrete time points.
Wherein the driving related information includes position information and speed information of the target vehicle; accordingly, the actual travel related information includes actual position information and actual speed information of the target vehicle at each preset time point, and the reference travel related information includes reference position information and reference speed information of the target vehicle at each preset time point. That is, the actual travel associated information and the reference travel associated information of the target vehicle may be determined at each preset time point. The reference travel related information is determined based on the reference planned path at the current time. The driving related information includes at least one reference item, such as at least one of position information, speed information, acceleration information, and heading angle information. Accordingly, the offset information of each reference item may be determined separately, and the set of the offset information of the reference item at each time point may be taken as the group offset information. That is, the group offset information includes at least one offset information, each of which is determined based on the actual travel related information and the reference travel related information. Since the preset time point includes a plurality of time points, when the time for the target vehicle to travel reaches the preset time point, S110 may be performed, that is, the actual travel related information and the reference travel related information of the target vehicle are collected.
It should be noted that the number of the preset time points may be multiple, and therefore, the number of the group offset information may also be multiple. The number of the group offset information is the same as the number of the preset time points. For example, assuming that there are 1000 preset time points in a group of preset time points, the above steps may be repeatedly performed to obtain group offset information corresponding to each preset time point. If the steps are repeatedly executed, the following steps are obtained: the group offset information corresponding to the first preset time point is 1 ', the group offset information corresponding to the second preset time point is 2', and the group offset information corresponding to the third preset time point is 3 '…, and the group offset information corresponding to the 1000 th preset time point is 1000'. In order to improve the accuracy of the determined control effect, the number of the preset time points is as large as possible, and accordingly, the number of the obtained group offset information is larger. When determining the control effect based on as much data as possible, the accuracy and precision of determining the control effect can be improved. That is, in order to improve the evaluation effect on the target vehicle, the larger the number of time points in a set of preset time points, the better.
In this embodiment, before determining the group offset information according to the actual associated running information and the reference associated running information at the current preset time point, the running associated information and the reference associated information at each preset time point may be acquired.
Optionally, based on a preset driving information acquisition device, acquiring actual driving associated information of the target vehicle at each preset time point; and determining reference driving associated information at each preset time point according to the reference planning path received in advance.
Wherein at least one sensor may be provided on each unmanned vehicle. Each sensor can acquire actual speed information, position information, course angle information, acceleration information and the like of the target vehicle at each moment. Meanwhile, the position information of the target vehicle at each preset time point can be acquired. It should be noted that the sensor may collect actual position information of the target vehicle at each preset time point. According to the actual position information and the acquisition time interval, the actual speed information of the target vehicle at each preset time point can be determined. The reference planned path is predetermined and is made up of discrete points. Each discrete point includes location information and velocity information. Accordingly, the reference travel related information of the target vehicle at each preset time point may be determined based on the reference planned path.
It should be noted that, in this embodiment, a specific collection manner for determining the actual driving related information of the target vehicle at each preset time point is not specifically limited.
Specifically, the reference planned path is predetermined, and the reference planned path is composed of a plurality of discrete points, each of which includes corresponding reference association information. Therefore, the reference travel related information of the current preset time point can be determined according to the reference planned path. Meanwhile, when it is detected that the running time of the target vehicle reaches one of the preset time points, that is, the current preset time point, the actual running related information of the target vehicle at the current preset time point may be determined based on the vehicle-mounted sensor.
In this embodiment, the reason and the advantage for determining the actual driving related information and the reference driving related information at each preset time point are that the group offset information can be determined according to the actual driving related information and the reference driving related information, and then the control effect of the target vehicle can be evaluated based on the group offset information at each preset time point.
And S120, determining an initial effect evaluation value of the target vehicle according to each group of offset information and the vehicle running state information corresponding to each group of offset information.
The vehicle driving state may be understood as a driving state of the vehicle during actual driving, and optionally, the driving state may be at least one of a straight driving state, a turning state, an acceleration state, a deceleration state, or a combination of a plurality of states. The vehicle running state at each preset time point can be determined. The initial effect evaluation value is an effect evaluation value determined based on the group offset information of the target vehicle and the vehicle running state. The initial effect evaluation value can preliminarily evaluate the control effect of the current control mode on the target vehicle.
Specifically, the vehicle running state information corresponding to each group offset information may be determined while obtaining the group offset information at each preset time point. And determining an initial effect evaluation value of the target vehicle according to each group of offset information and corresponding vehicle running state information.
It should be further noted that the driving effect of the target vehicle may be evaluated when the target vehicle drives to the end point according to the reference planned route, or the control effect of the target vehicle may be determined based on the scheme of the embodiment when the vehicle drives to each preset time point.
And S130, determining a target control effect on the target vehicle according to the initial effect evaluation value and the preset effect evaluation value.
The preset effect evaluation value may be determined according to actual experience, or may be an effect evaluation value obtained through theoretical calculation. The target control effect is a driving control effect on the target vehicle finally determined through a series of processing.
Specifically, a target control effect value corresponding to the target vehicle may be determined according to the initial effect evaluation value and the preset effect evaluation value, and the control effect of the current control method on the target vehicle may be determined based on the target effect control value.
Illustratively, the preset effect evaluation value is 100, and the initial effect evaluation value is GcBy calculating the difference 100-G between the preset effect evaluation value and the initial effect evaluation valuecAnd determining a target effect control value, and determining the control effect on the target vehicle according to the target effect control value, wherein optionally, the larger the target effect control value is, the poorer the target control effect is, and correspondingly, the smaller the target effect control value is, the better the target control effect is.
On the basis of the above technical solution, it should be further noted that the control of the target vehicle is mostly determined based on the control coefficient in the controller, and therefore, whether the control coefficient in the controller is appropriate and the specific adjustment manner of the control coefficient can be determined based on the target control effect.
The technical scheme of the embodiment of the invention determines the group offset information of each preset time point by processing the actual running related information and the corresponding reference running related information of each preset time point, determines the initial effect evaluation value of the target vehicle according to each group of offset information and the corresponding vehicle running state information, and can determine the target control effect of the target vehicle based on the initial effect evaluation value and the preset effect evaluation value, thereby solving the technical problems that the control effect of the current control mode on the target vehicle is not evaluated by a corresponding effect evaluation method in the prior art, the control mode or the control coefficient of the target vehicle cannot be optimized, and the control effect is poor, effectively evaluating the control effect of the target vehicle, and further effectively adjusting the control mode or the control coefficient corresponding to the target vehicle according to the evaluation result, thereby improving the technical effects of the running safety and the accuracy of the target vehicle.
Example two
Fig. 2 is a flowchart illustrating a control effect evaluation method according to a second embodiment of the present invention, where on the basis of the foregoing embodiment, each group offset information includes at least one of position information, speed information, and heading angle information, and at this time, the "determining group offset information at each preset time point according to actual driving related information and reference driving related information of the target vehicle at each preset time point in a group of preset time points" may be further refined. For specific implementation, reference may be made to the technical solution of this embodiment, where the same or corresponding technical terms as those in the foregoing embodiment are not described herein again.
As shown in fig. 2, the method includes:
s210, determining position offset information in each set of offset information according to the actual position information and the reference position information of the target vehicle at each preset time point.
The actual travel related information or the reference travel related information includes the position information of the target vehicle at each preset time point, so that the position offset of the target vehicle at each preset time point can be determined according to the position information in the actual travel related information and the reference position information in the reference travel related information. This amount of positional deviation may be used as the amount of positional deviation information of the target vehicle. That is, the group offset information includes position offset information corresponding to each preset time point.
It should be noted that, at the starting time, the actual traveling related information of the target vehicle is the same as the reference traveling related information, and there may be a certain deviation between the actual related information and the reference related information during the actual traveling of the target vehicle, where the deviation may be caused by a road condition reason or an unreasonable setting of a control coefficient of the controller in the unmanned vehicle.
The position information includes not only lateral position information of the target vehicle but also longitudinal position information of the target vehicle.
In this embodiment, the determining the position offset information in each set of offset information according to the actual position information and the reference position information of the target vehicle at each preset time point includes: and determining transverse position offset information in the position offset information according to the actual transverse position information and the reference transverse position information of the target vehicle at each preset time point, and determining longitudinal position offset information according to the actual longitudinal position information and the reference longitudinal position information.
Specifically, the longitudinal position difference may be obtained according to actual longitudinal position information in the actual position information and reference longitudinal position information in the reference association information. The longitudinal position difference is taken as the longitudinal position offset information. In the same manner, the lateral offset position information of the target vehicle at each preset time point can be determined.
For example, if the lateral position offset information at one of the preset time points is determined, the following may be: if the preset time point is t3When t is determined3Actual longitudinal position information s _ real of time3And reference longitudinal position information s3Determining the longitudinal position offset information s _ error ═ s _ real3-s3. At the same time, can be according to t3Actual lateral position information l _ real of time3And reference lateral position information l3Determining the lateral position offset information l _ error ═ l _ real3-l3
S220, determining the speed offset and the course angle offset in each group of offset information according to the actual speed information, the actual course angle information, the reference speed information and the reference course angle information of the target vehicle at each preset time point.
The actual speed information of the target vehicle at the current preset time point can be determined based on the actual speed information of the target vehicle acquired by the vehicle-mounted sensor or the acquired position information and the time information. Accordingly, the actual heading angle information of the target vehicle may also be determined based on onboard sensors. According to the actual speed information and the reference speed information, the speed offset can be determined; and determining the course angle offset according to the actual course angle information and the reference course angle information.
Illustratively, the actual speed information of the target vehicle at the current preset time point is V1The reference velocity information is V1', velocity offset V _ error ═ V1-V1'; the actual course angle information of the target vehicle at the current preset time point is h1The reference course angle information is h1', heading angle offset is: h _ error ═ h1’-h1
It should be noted that, the specific numerical values in the group offset information corresponding to each preset time point may be the same or different, and whether the specific numerical values are the same or not is related to the actual running related information and the reference running related information in the running process of the vehicle.
And S230, determining an initial effect evaluation value of the target vehicle according to each group of offset information and the vehicle running state information corresponding to each group of offset information.
It is to be understood that each group of offset information includes at least one of lateral position offset information, longitudinal position offset information, speed offset, and heading angle offset. According to each group offset information and the vehicle running state information corresponding to the group offset information, the initial effect evaluation value of the target vehicle can be determined.
And S240, determining the target control effect of the target vehicle according to the initial effect evaluation value and the preset evaluation effect value.
According to the technical scheme of the embodiment of the invention, the transverse position offset, the longitudinal position offset, the course angle offset and the speed offset of the target vehicle at each preset time point can be determined according to the actual running associated information and the reference running associated information of each preset time point, the offset information can be used as a reference item for determining the initial effect evaluation value of the target vehicle, the target control effect on the target vehicle can be determined based on the reference item, the technical effect of automatically evaluating the control effect of the target vehicle is realized, and meanwhile, the accuracy and the convenience of evaluation are improved.
EXAMPLE III
Fig. 3 is a flowchart illustrating a control effect evaluation method according to a third embodiment of the present invention, and based on the foregoing embodiments, the method may refine "determining an initial effect evaluation value of the target vehicle according to each group of offset information and vehicle driving state information corresponding to the group of offset information". The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.
As shown in fig. 3, the method includes:
s310, a group of preset time points is obtained, and group offset information of each preset time point is determined according to actual running related information and reference running related information of the target vehicle at each preset time point in the group of preset time points.
And S320, processing the offset information with the same offset name in each set of offset information to obtain target offset information of each offset information set.
Based on the above, the group offset information includes at least one offset information, and each offset information corresponds to a corresponding offset name. The offset information corresponding to the same offset name may be regarded as one offset information group. That is, all offset information associated with the same offset name is included in the offset information group. The number of offset information groups is identical to the number of offset names, and the number of offset information in the offset information groups is identical to the number of group offset information. The number of the target offset information is the same as that of the offset information groups, and each offset information group has one corresponding target offset information, namely the target offset information is obtained by processing the data in the offset information group.
For the same offset name, the offset information corresponding to the current offset name can be acquired from each group of offset information, and the target offset information of each offset information group can be obtained by processing the offset information of the offset name.
In this embodiment, the obtaining the target offset information of each offset information group by processing the offset information of the same offset name in each group of offset information includes: determining offset information corresponding to each offset name from each set of offset information, and taking the offset information as an offset information set corresponding to each offset name; wherein the number of the offset information groups is consistent with the number of the offset names; and determining target offset information of each offset information group according to the offset quantity and the offset information in each offset information group.
Specifically, the group offset information includes offset information corresponding to different offset names, for example, the offset names may be: the group offset information comprises transverse position offset information corresponding to a transverse position offset name, longitudinal position offset information corresponding to a longitudinal position offset name, course angle offset corresponding to a course angle offset name and speed offset corresponding to a speed offset name. The offset information of the same offset name in each set of offset information may be acquired, and the offset information of the same offset name may be used as one offset information set, at which time, an offset information set corresponding to the number of offset names may be obtained. For each offset information group, the offset number and the offset information in the current offset information group are determined, and the target offset information in the current offset information group, that is, the target offset information, can be determined.
Optionally, for a numerical value corresponding to each offset information in the current offset information group, a median of the numerical value may be used as the target offset value of the current offset information group, or a mode of the numerical value may be used as the target offset value of the current offset information group, or a numerical value corresponding to ninety-nine percent of the numerical value may be determined, and the numerical value at this time is used as the target offset value.
Note that the number of target offset values corresponds to the number of offset information sets.
In this embodiment, the determining the target offset information of the current offset information group according to the offset amount and the offset information in the current offset information group includes: sorting the offset information in the current offset information group from high to low to obtain offset sorting; and determining the last offset information which is higher than a preset proportion threshold value according to the offset quantity and the offset sequence, and taking the last offset information as the target offset information.
Wherein the preset proportional threshold may be ninety nine percent.
Specifically, the offset values in the current offset information group may be sorted from high to low, and after the sorting is completed, the first ninety-nine percent value may be determined, and the last offset value of the ninety-nine percent value may be used as the target offset value. The target offset value for each set of offset information may be determined in this manner.
S330, determining an initial effect evaluation value of the target vehicle according to the target offset information and the vehicle running state corresponding to the target time point of the target offset information.
After determining the target offset information in each offset information group, a target time point corresponding to each target offset information may be determined. Meanwhile, the vehicle running state at the target time point may be determined. The vehicle driving state at each time point comprises at least one of straight running, turning, accelerating and decelerating or a combination of several kinds of straight running, turning, accelerating and decelerating.
Specifically, for each target offset value, a target preset time point corresponding to the current target offset value may be determined, and meanwhile, a vehicle driving state of the target preset time point may be determined, and a weight value corresponding to each reference item in the vehicle driving state may be determined. A partial effect evaluation value in the initial effect evaluation value may be determined based on the weight value and the current target offset value. Based on the partial effect evaluation value corresponding to each target offset value, an initial effect evaluation value of the target vehicle can be determined.
And S340, determining the target control effect of the target vehicle according to the initial effect evaluation value and a preset evaluation effect value.
The technical scheme of the embodiment of the invention determines the group offset information of each preset time point by processing the actual running related information and the corresponding reference running related information of each preset time point, determines the initial effect evaluation value of the target vehicle according to each group of offset information and the corresponding vehicle running state information, and can determine the target control effect of the target vehicle based on the initial effect evaluation value and the preset effect evaluation value, thereby solving the technical problems that the control effect of the current control mode on the target vehicle is not evaluated by a corresponding effect evaluation method in the prior art, the control mode or the control coefficient of the target vehicle cannot be optimized, and the control effect is poor, effectively evaluating the control effect of the target vehicle, and further effectively adjusting the control mode or the control coefficient corresponding to the target vehicle according to the evaluation result, thereby improving the technical effects of the running safety and the accuracy of the target vehicle.
Example four
Fig. 4 is a flowchart of a control effect evaluation method according to a fourth embodiment of the present invention, and based on the foregoing embodiment, further details may be performed on "determining an initial effect evaluation value of the target vehicle according to the vehicle driving states corresponding to the target offset values and the target time points of the target offset values", and a specific implementation manner thereof may refer to the technical solution of this embodiment. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.
As shown in fig. 4, the method includes:
s410, acquiring a group of preset time points, and determining group offset information of each preset time point according to actual running related information and reference running related information of the target vehicle at each preset time point in the group of preset time points.
And S420, processing the offset information with the same offset name in each set of offset information to obtain target offset information of each offset information set.
It is to be understood that after obtaining the respective sets of offset information, the offset information corresponding to each offset name may be extracted from the respective sets of offset information, so that all the offset information corresponding to the same offset name may be taken as the set of offset information.
The offset information group to be described includes not only the offset value corresponding to the same offset name, but also a preset time point corresponding to the offset value.
And S430, determining the actual running state of the vehicle corresponding to each target offset information at the corresponding target time point.
It should be noted that, at each preset time point, not only the actual driving related information of the target vehicle may be collected, but also the vehicle actual driving state of the target vehicle may be included. The actual driving state may be at least one of an acceleration state, a deceleration state, a straight-driving state, or a turning state of the target vehicle at a preset time point, and one or more combinations of the above states may be used as a reference item, for example, the reference item may be straight-driving acceleration, straight-driving deceleration, turning acceleration, or turning deceleration.
Specifically, after the target offset value in each offset information group is determined, a corresponding preset time point of each target offset value may be determined and used as the target time point. Meanwhile, the actual driving state of the vehicle corresponding to the target time point can be determined.
Optionally, the determining the actual driving state of the vehicle corresponding to each target offset information at the corresponding target time point includes: determining target time points corresponding to the target offset information, and acquiring front wheel steering angle information and vehicle acceleration value information of the target time points; and aiming at each target time point, determining the actual running state of the target vehicle at the current target time point according to the steering angle information of the front wheels and the acceleration value information of the vehicle at the current target time point.
Wherein the determination of the actual driving state of the vehicle may be determined by a front wheel steering angle and a vehicle acceleration value. For example, a steering angle sensor for detecting the rotation angle of the front wheels may be provided on the front wheels so as to determine whether the subject vehicle is running straight or turning, based on the rotation angle of the front wheels. Meanwhile, acceleration and deceleration of the target vehicle at each time may also be determined based on the acceleration sensor.
It should be noted that, in the present embodiment, not only the offset amount of each preset time point is considered, but also the driving conditions of the target vehicle are combined, so as to improve the control efficiency of the objective evaluation controller.
In the present embodiment, the vehicle actual running state includes the straight running state WsTurning state WbAcceleration and deceleration Wa_dAt least one or more combinations thereof. For example, the steering angle δ of the front wheel and the vehicle acceleration a may be input into the condition synthesis module to obtain the actual driving state of the vehicle. The actual running state of the vehicle at each preset time point may be determined separately based on the above-described manner.
S440, determining an initial effect evaluation value of the target vehicle according to the target offset information and the corresponding weight value corresponding to each reference index item in the corresponding actual running state of the vehicle.
The reference index item may correspond to an actual driving state of the vehicle, and for example, the reference index item may be a straight acceleration/deceleration index, a curve acceleration/deceleration index, and the like. Optionally, the reference index item includes at least one of a driving index item, a speed index item and a heading angle index item. Each reference index item has a corresponding weight value, and an initial effect evaluation value of the target vehicle can be determined according to the weight value and corresponding target offset information, such as a target offset value.
On the basis of the above-described embodiment, the target offset value may be one corresponding to the positional offset amount and one corresponding to the speed offset amount and the heading angle offset amount, and therefore, the initial evaluation value may also be one composed of the above-described three kinds.
It can be understood that: the initial effect evaluation value includes at least one of: a position effect estimate, a speed effect estimate, and a heading angle effect estimate. The corresponding effect evaluation values may be determined separately, and a specific determination manner may be as follows:
determining the location effect estimate value may be: determining a position effect evaluation value of the target vehicle according to the target position offset information and a driving index weight value of the corresponding actual driving state of the vehicle; the driving index weight value comprises at least one of a straight driving index weight value and a turning index weight value. The target time point corresponding to the target position offset information and the vehicle running state corresponding to the target time point may be determined first, and meanwhile, the running index weight value corresponding to each reference item index of the actual running state of the vehicle may be determined, and the position effect evaluation value of the target vehicle may be determined according to the state index weight value and the target position offset value. The driving index weight value includes at least one of a straight-driving index weight value and a turning index weight value.
In this embodiment, the determining the position effect evaluation value of the target vehicle according to the target position offset information and the driving index weight value of the corresponding actual driving state of the vehicle includes: determining a transverse position effect evaluation value according to the transverse offset information and a straight index weight value or a turning index weight value in the driving index weight values; and determining a longitudinal position effect evaluation value according to the longitudinal offset information and an acceleration weighted value in the driving index weighted values.
It is understood that the positional offset information includes lateral offset information and longitudinal offset information. Accordingly, the position effect evaluation value also includes a lateral position effect evaluation value and a longitudinal position effect evaluation value.
Determining the lateral position effect evaluation value may be: and determining whether the actual running state of the vehicle is straight running or turning according to the target time point of the target position offset information, and taking the weight values corresponding to the straight running state and the turning state as running index weight values. And determining the transverse position effect evaluation value according to the transverse position offset information and the running index weight value in the target position offset.
For example, the lateral position effect evaluation value of the target vehicle may be determined based on the formula:
gl=gw_s·l_s_e_99+gw_b·l_b_e_99
wherein, glRepresenting the lateral position effect evaluation value, gw_sRepresenting a weight value, g, of a straight-ahead state indicatorw_bIndicating a curve state indicator weight value,/_s_e_99A lateral position shift amount l representing a straight traveling state_b_e_99The lateral position displacement amount indicating the turning state.
It should be noted that the target vehicle may have only one of a straight-ahead state and a turning state during traveling, and therefore, the above-mentioned i_s_e_99And l_b_e_99One of which is present as far as possible.
Also, g isw_sGreater than gw_bThat is, the straight-going state index weight value is greater than the turning state index weight value.
Determining the longitudinal position effect estimate may be: and determining a longitudinal position effect evaluation value according to the longitudinal position offset and the acceleration index weight value of the target time point.
Illustratively, it can be based on the formula gs=gw_ad·s_e_99A longitudinal position effect evaluation value is determined.
Wherein, gsRepresenting the longitudinal position effect evaluation value, gw_adRepresents the target vehicle acceleration and deceleration weight value, s_e_99Indicating the longitudinal position offset value.
Based on the above formula, a lateral position effect evaluation value and a longitudinal position effect evaluation value of the target vehicle at the target time point may be determined, respectively, and a position effect evaluation value may be determined based on the longitudinal position effect evaluation value and the lateral position effect evaluation value, e.g., by accumulating the lateral position effect evaluation value and the longitudinal position effect evaluation value to obtain a position effect evaluation value.
Determining the speed effect estimate may be: and determining the speed effect evaluation value of the target vehicle according to the target speed offset information and the speed index weight value.
The speed values have corresponding weight values of speed indicators, or the weight values of speed indicators may be the same regardless of the speed values. If the speed index weight values are different, the speed index weights corresponding to different speed offset ranges can be preset. The speed index weight value may be determined according to the range to which the target speed offset belongs. After determining the speed index weight value, a speed effect evaluation value of the target vehicle may be determined according to the speed index weight value and the corresponding target speed offset.
For example, the velocity effect estimate may be determined based on the following equation: gv=gv’·v_e_99Wherein g isvRepresenting an evaluation value of velocity effect, gv' represents a velocity weight value, v_e_99Indicating the target speed offset.
Determining the heading angle effect estimate may be: and determining a course angle effect evaluation value of the target vehicle according to the target course angle offset information and the course angle index weight value of the corresponding vehicle running state.
The state index weight value mainly refers to a course angle weight value in a straight-going state or a course angle weight value in a turning state. The weight value in the straight-going state is smaller than the weight value of the course angle in the turning state. The course angle weight value can be determined according to the actual running state of the target vehicle, and the course angle effect evaluation value of the target vehicle is determined according to the course angle weight value and the corresponding target course angle offset value.
For example, the heading angle effect estimate may be determined based on the following equation:
gh=gh_w_s·hs_e_99+gh_w_b·h_b_e_99
wherein, ghA value representing an estimate of the effect of the heading angle,gh_w_sindicating the weight value of course angle g in straight-ahead drivingh_w_bIndicates the course angle weight value h in the turning states_e_99Indicates the straight heading angle offset, h_b_e_99And (4) turning course angle offset.
It should be noted that the target vehicle may have only one of a straight-ahead state and a turning state during traveling, and therefore, the above-mentioned h_s_e_99And h_b_e_99One of which is present as far as possible. The straight-going index weight value is greater than the turning index weight value, and the straight-going course angle index weight value in the course angle index weight values is less than the turning course angle index weight value
When obtaining an initial effect evaluation value based on the effect evaluation values described above, the effect evaluation values may be: and determining an initial effect evaluation value of the target vehicle according to the position effect evaluation value, the speed effect evaluation value and the course angle effect evaluation value.
Specifically, the initial effect evaluation value of the target vehicle can be obtained by accumulating the position effect evaluation value, the speed effect evaluation value, and the course angle effect evaluation value.
S450, determining the target control effect of the target vehicle according to the initial effect evaluation value and a preset evaluation effect value.
According to the technical scheme, the position effect evaluation value, the course angle effect evaluation value and the speed effect evaluation value are determined respectively, the initial effect evaluation value of the target vehicle can be determined according to the effect evaluation values, the target effect evaluation value of the target vehicle is further determined, the control effect of the controller in the target vehicle can be determined according to the target effect evaluation value, the control effect of the target vehicle is evaluated from multiple aspects, and therefore the technical effect of evaluating accuracy is improved.
EXAMPLE five
Fig. 5 is a flowchart illustrating a control effect evaluation method according to a fifth embodiment of the present invention, and based on the foregoing embodiments, the initial effect evaluation value may be updated according to the accident effect evaluation value, and then the control effect on the target vehicle may be determined according to the updated initial effect evaluation value. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.
As shown in fig. 5, the method includes:
s510, a group of preset time points is obtained, and group offset information of each preset time point is determined according to actual running related information and reference running related information of the target vehicle at each preset time point in the group of preset time points.
S520, determining an initial effect evaluation value of the target vehicle according to each group of offset information and the vehicle running state information corresponding to each group of offset information.
S530, acquiring an accident effect evaluation value, and updating the initial effect evaluation value based on the accident effect evaluation value.
It should be noted that, during the actual driving of the vehicle, a vehicle accident may be encountered, the cause of the accident may be caused by the road condition or the abnormal driving of another vehicle, and based on the above reason, in order to further improve the accuracy of determining the target control effect, the influence of the vehicle accident on the target control effect may be further considered on the basis of the above embodiments.
The accident effect evaluation value is the corresponding evaluation value when the target vehicle has an accident. The evaluation value may characterize the impact of the target control effectiveness value of the target vehicle to which the accident corresponds. After determining the accident effectiveness evaluation value, the initial effectiveness evaluation value may be updated based on the accident effectiveness evaluation value, and the target effectiveness evaluation value of the target vehicle may be determined based on the updated initial effectiveness evaluation value.
Optionally, before the obtaining of the accident effect evaluation value, the method further includes: determining an accident effect evaluation value; the determining of the accident effect evaluation value comprises the following steps: when a trigger target event is detected, determining a target trigger time corresponding to the target event; obtaining group to-be-processed offset information according to the to-be-determined running information and the theoretical running information corresponding to the target trigger time; and determining the accident effect evaluation value according to the group of to-be-processed offset information and preset group offset information.
Wherein, the target event can be the event that the accident happens to the target vehicle. The target trigger time is the time when the target event occurs. And determining that the running information is the actual running information of the target vehicle at the target trigger moment. The theoretical travel information is determined based on the reference planned path. Theoretical driving information of the target trigger moment can be determined based on the reference planned path. The group to-be-processed offset information is determined based on the actual travel information and the theoretical travel information at the target trigger time. For a specific determination method, reference may be made to the above description, which is not repeated herein. The preset group offset information includes preset offset values corresponding to the respective offset names. And determining an accident effect evaluation value according to each offset information in the group of to-be-processed offset information and each offset information in the preset group of offset information.
In this embodiment, the determining the accident effect evaluation value according to the set of to-be-processed offset information and the preset set of offset information includes: and when the to-be-processed transverse position offset value in the set of to-be-processed offset information is smaller than a preset transverse position offset threshold value, the to-be-processed longitudinal position offset value is smaller than a preset longitudinal offset threshold value, the to-be-processed speed offset value is smaller than a preset speed offset threshold value, and the to-be-processed course angle offset value is smaller than a preset course angle offset threshold value, determining the accident effect evaluation value as a first preset accident effect evaluation value.
It should be noted that the tolerance of the unmanned vehicle to the accident is extremely low, so the evaluation of the effect of the accident is determined separately. And when the group to-be-processed offset information and the preset group offset information meet the preset relationship, the accident effect evaluation value is a first preset accident effect evaluation value, otherwise, the accident effect evaluation value is another accident effect evaluation value.
Specifically, if the transverse position offset value is smaller than a preset transverse position offset threshold value, the longitudinal position offset value to be processed is smaller than a preset longitudinal offset threshold value, the speed offset value to be processed is smaller than a preset speed offset threshold value, and the course angle offset value to be processed is smaller than a preset course angle offset threshold value, the accident effect evaluation value is determined to be a first preset accident effect evaluation value. That is, although an accident occurs at this time, the target vehicle does not deviate from the reference planned path at the target triggering time, which may be caused by a malfunction of another vehicle. On the contrary, if there is an offset value that does not satisfy the above condition, the accident effect evaluation value is another accident effect evaluation value.
Illustratively, when a trigger target event is detected, a target trigger time of the trigger target event is determined, and to-be-processed offset information of the target trigger time, such as a lateral position offset, a longitudinal position offset, a speed offset, and a heading angle offset, which are respectively denoted as l _ e _ t, s _ e _ t, v _ e _ t, h _ e _ t, and the like, is obtained. The preset group offset information is l, s, v, h. The accident effectiveness assessment value may be determined based on the following formula:
Figure BDA0003083676460000241
wherein l _ e _ t, s _ e _ t, v _ e _ t and h _ e _ t are respectively transverse position deviation, longitudinal position deviation, speed deviation and course angle deviation when an accident occurs, l, s, v and h are respectively transverse position deviation, longitudinal position deviation, speed deviation and course angle deviation threshold values, and g is carried out if all the deviations are smaller than the threshold valueaIs 0, otherwise gaIs 40.
In addition, the above-mentioned gaThe values of (a) are merely exemplary and are not specifically limited herein. After determining the accident effect evaluation value based on the above manner, the initial effect evaluation value may be updated based on the accident effect evaluation value, and the updating may be performed by adding the accident effect evaluation value to the calculated initial effect evaluation value to obtain an updated initial effect evaluation value.
And S540, determining that the target control effect of the target vehicle meets a preset condition under the condition that the initial effect evaluation value is smaller than a preset effect evaluation value.
The preset condition may be a condition corresponding to a reasonable control effect, that is, a condition that the control effect on the target vehicle is possible at present.
Specifically, the research and development personnel can set a preset effect evaluation value according to actual requirements, and can determine whether the target control effect of the target vehicle is a reasonable control effect or an optimal control effect based on the size relationship between the preset effect evaluation value and the initial effect evaluation value.
Of course, it is also mentioned in the above-described embodiment that, based on the initial effect evaluation value and the preset effect evaluation value, the determination of the target control effect on the target vehicle may be: the preset effect evaluation value is set to 100, the initial effect evaluation value is determined to be Cs, and the target control effect value G is 100-Cs, i.e., the target control effect: G-100-Gl-gs-gh-gv-gaAnd determining whether the control effect on the target vehicle meets a preset condition according to the positive and negative of G, namely whether the control effect is a reasonable control effect. If the current control effect meets the preset condition, the unmanned vehicle can be controlled to run in the mode; if the target control effect is negative, the target control effect does not meet the preset condition, prompt information can be sent to the worker, and if the control effect of the worker on the unmanned vehicle is not good, information such as a control coefficient of a controller in the unmanned vehicle can be adjusted.
According to the technical scheme of the embodiment of the invention, not only is the target control effect of the offset information on the target vehicle considered, but also the influence of the vehicle accident on the evaluation effect of the target vehicle is considered, namely, the embodiment can be combined with the offset information and the accident effect evaluation to comprehensively determine the control effect of the current control coefficient or the control method on the target vehicle, so that the accuracy and the convenience for determining the target control effect are improved.
EXAMPLE six
Fig. 6 is a schematic structural diagram of a control effect evaluation apparatus according to a sixth embodiment of the present invention, including: a group offset information determining module 610, an initial effect valuation determining module 620, and a target control effect determining module 630. Wherein the content of the first and second substances,
the group offset information determining module 610 is configured to acquire a group of preset time points, and determine group offset information of each preset time point according to actual driving related information and reference driving related information of the target vehicle at each preset time point in the group of preset time points; wherein the set of offset information includes at least one offset information; the reference driving related information is determined based on a preset generated reference planned path; an initial effect evaluation value determining module 620, configured to determine an initial effect evaluation value of the target vehicle according to each set of offset information and vehicle driving state information corresponding to each set of offset information; and a target control effect determining module 630, configured to determine a control effect of the target vehicle according to the initial effect evaluation value and a preset evaluation effect value.
On the basis of the above technical solution, the apparatus further includes: an information collection module comprising:
the actual running related information acquisition unit is used for acquiring actual running related information of the target vehicle at each preset time point based on a preset running information acquisition device;
and the reference running related information extracting unit is used for determining the reference running related information at each preset time point according to the reference planning path received in advance.
On the basis of the above technical solutions, the group offset information determining module includes:
the position offset determining unit is used for determining position offset information in each set of offset information according to actual position information and reference position information of the target vehicle at each preset time point;
and the other offset determining unit is used for determining the speed offset and the course angle offset in each set of offset information according to the actual speed information, the actual course angle information, the reference speed information and the reference course angle information of the target vehicle at each preset time point.
On the basis of the above technical solutions, the position offset determining unit is further configured to determine, according to actual lateral position information and reference lateral position information of the target vehicle at each preset time point, lateral position offset information in each position offset information, and determine, according to actual longitudinal position information and reference longitudinal position information, longitudinal position offset information in each position offset information, on the basis of the above technical solutions, where the initial effect evaluation value determining module includes:
a target offset information determining unit, configured to obtain target offset information of each offset information group by processing offset information of the same offset name in each group of offset information; wherein the offset information group corresponds to each offset name; the offset name comprises at least one of a position offset name, a speed offset name and a course angle offset name;
the initial effect evaluation value determining unit is used for determining the initial effect evaluation value of the target vehicle according to each target offset value and the vehicle running state corresponding to the target time point of the target offset value; the target time point is a time point in a group of preset time points.
On the basis of the above technical solutions, the target offset information determining unit is configured to: determining offset information corresponding to each offset name from each set of offset information, and taking the offset information as an offset information set corresponding to each offset name; wherein the number of the offset information groups is consistent with the number of the offset names; on the basis of the above technical solutions, the target offset information determining unit is further configured to determine the target offset information of each offset information group according to the offset amount and the offset information in each offset information group, and on the basis of the above technical solutions, the target offset information determining unit is further configured to:
sorting the offset information in each offset information group from high to low to obtain offset sorting; determining the last offset information higher than a preset proportion threshold according to the offset quantity and the offset sequence, and taking the last offset information as the target offset information on the basis of the above technical solutions, where the initial effect evaluation value determining unit is further configured to:
determining the actual running state of the vehicle corresponding to each target offset information at the corresponding target time point; and determining an initial effect evaluation value of the target vehicle according to the target offset information and the corresponding weight value corresponding to each reference index item in the corresponding actual running state of the vehicle.
On the basis of the above technical solutions, the initial effect evaluation value determining unit is further configured to determine the initial effect evaluation value
Determining target time points corresponding to the target offset information, and acquiring front wheel steering angle information and vehicle acceleration value information of the target time points; and determining the actual running state of the target vehicle at each target time point according to the front wheel steering angle information and the vehicle acceleration value information of each target time point.
On the basis of the above technical solutions, the target offset information includes at least one of target position offset information, target speed offset information, and target course angle offset information, the reference index item includes at least one of a driving index item, a speed index item, and a course angle index item, and the initial effect evaluation value determining unit is further configured to determine a position effect evaluation value of the target vehicle according to the target position offset information and a driving index weight value of a corresponding actual driving state of the vehicle; the driving index weight value comprises at least one of a straight driving index weight value and a turning index weight value; determining a speed effect evaluation value of the target vehicle according to the target speed offset information and the speed index weight value; determining a course angle effect evaluation value of the target vehicle according to the target course angle offset information and a course angle index weight value of the corresponding vehicle running state; and determining an initial effect evaluation value of the target vehicle according to the position effect evaluation value, the speed effect evaluation value and the course angle effect evaluation value.
On the basis of the above technical solutions, the position offset information includes lateral offset information and longitudinal offset information, and the initial effect evaluation value determining unit is further configured to determine a lateral position effect evaluation value according to a straight index weight value or a turning index weight value among the lateral offset information and the driving index weight value; and determining a longitudinal position effect evaluation value according to the longitudinal offset information and an acceleration weighted value in the driving index weighted values.
On the basis of the technical schemes, the straight-going index weight value is greater than the turning index weight value, and the straight-going course angle index weight value in the course angle index weight values is smaller than the turning course angle index weight value.
On the basis of the above technical solutions, the apparatus further includes: the accident effect evaluation value acquisition module is used for acquiring an accident effect evaluation value; updating the initial effect evaluation value based on the accident effect evaluation value.
On the basis of the above technical solutions, the accident effect evaluation value acquisition module is further configured to, before being configured to acquire an accident effect evaluation value: determining an accident effect evaluation value;
when a trigger target event is detected, determining a target trigger time corresponding to the target event; obtaining group to-be-processed offset information according to the to-be-determined running information and the theoretical running information corresponding to the target trigger time; and determining the accident effect evaluation value according to the group of to-be-processed offset information and preset group offset information.
On the basis of the above technical solutions, the accident effect evaluation value determining module is further configured to:
and when the to-be-processed transverse position offset information in the set of to-be-processed offset information is smaller than a preset transverse position offset threshold, the to-be-processed longitudinal position offset information is smaller than a preset longitudinal offset threshold, the to-be-processed speed offset information is smaller than a preset speed offset threshold, and the to-be-processed course angle offset information is smaller than a preset course angle offset threshold, determining the accident effect evaluation value as a first preset accident effect evaluation value.
On the basis of the foregoing technical solutions, the target effect determining module is further configured to determine that the control effect on the target vehicle satisfies a preset condition when the initial effect evaluation value is smaller than a preset effect evaluation value.
The technical scheme of the embodiment of the invention determines the group offset information of each preset time point by processing the actual running related information and the corresponding reference running related information of each preset time point, determines the initial effect evaluation value of the target vehicle according to each group of offset information and the corresponding vehicle running state information, and can determine the target control effect of the target vehicle based on the initial effect evaluation value and the preset effect evaluation value, thereby solving the technical problems that the control effect of the current control mode on the target vehicle is not evaluated by a corresponding effect evaluation method in the prior art, the control mode or the control coefficient of the target vehicle cannot be optimized, and the control effect is poor, effectively evaluating the control effect of the target vehicle, and further effectively adjusting the control mode or the control coefficient corresponding to the target vehicle according to the evaluation result, thereby improving the technical effects of the running safety and the accuracy of the target vehicle.
The control effect evaluation device provided by the embodiment of the invention can execute the control effect evaluation method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
It should be noted that, the units and modules included in the apparatus are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiment of the invention.
EXAMPLE seven
Fig. 7 is a schematic structural diagram of an electronic device according to a seventh embodiment of the present invention. FIG. 7 illustrates a block diagram of an exemplary electronic device 70 suitable for use in implementing embodiments of the present invention. The electronic device 70 shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 7, the electronic device 70 is embodied in the form of a general purpose computing device. The components of the electronic device 70 may include, but are not limited to: one or more processors or processing units 701, a system memory 702, and a bus 703 that couples various system components including the system memory 702 and the processing unit 701.
Bus 703 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 70 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 70 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 702 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)704 and/or cache memory 705. The electronic device 70 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, the storage system 706 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, commonly referred to as a "hard drive"). Although not shown in FIG. 7, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 703 via one or more data media interfaces. Memory 702 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 708 having a set (at least one) of program modules 707 may be stored, for example, in memory 702, such program modules 707 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 707 generally perform the functions and/or methodologies of the described embodiments of the invention.
The electronic device 70 may also communicate with one or more external devices 709 (e.g., keyboard, pointing device, display 710, etc.), with one or more devices that enable a user to interact with the electronic device 70, and/or with any devices (e.g., network card, modem, etc.) that enable the electronic device 70 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 711. Also, the electronic device 70 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 712. As shown, the network adapter 712 communicates with the other modules of the electronic device 70 over a bus 703. It should be appreciated that although not shown in FIG. 7, other hardware and/or software modules may be used in conjunction with electronic device 70, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 701 executes various functional applications and data processing by running a program stored in the system memory 702, for example, to implement the control effect evaluation method provided by the embodiment of the present invention.
Example eight
An eighth embodiment of the present invention also provides a storage medium containing computer-executable instructions for performing a control effect evaluation method when executed by a computer processor.
The method comprises the following steps:
acquiring a group of preset time points, and determining group offset information of each preset time point according to actual running associated information and reference running associated information of the target vehicle at each preset time point in the group of preset time points; wherein the set of offset information includes at least one offset information; the reference driving related information is determined based on a preset generated reference planned path;
determining an initial effect evaluation value of the target vehicle according to each group of offset information and vehicle running state information corresponding to each group of offset information;
and determining the target control effect of the target vehicle according to the initial effect evaluation value and a preset effect evaluation value.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (19)

1. A control effect evaluation method, comprising:
acquiring a group of preset time points, and determining group offset information of each preset time point according to actual running associated information and reference running associated information of the target vehicle at each preset time point in the group of preset time points; wherein the set of offset information includes at least one offset information; the reference driving related information is determined based on a preset generated reference planned path;
determining an initial effect evaluation value of the target vehicle according to each group of offset information and vehicle running state information corresponding to each group of offset information;
and determining the target control effect of the target vehicle according to the initial effect evaluation value and a preset effect evaluation value.
2. The method according to claim 1, further comprising, before determining the group offset information for each preset time point based on the actual travel related information and the reference travel related information for the target vehicle at each preset time point in a group of preset time points:
acquiring actual running related information of the target vehicle at each preset time point based on a preset running information acquisition device;
and determining reference driving associated information at each preset time point according to the reference planning path received in advance.
3. The method of claim 1, wherein the driving correlation information includes at least one of position information, speed information and course angle information, and the determining the group offset information for each preset time point according to the actual driving correlation information and the reference driving correlation information of the target vehicle at each preset time point in a group of preset time points comprises:
determining position offset information in each set of offset information according to the actual position information and the reference position information of the target vehicle at each preset time point;
and determining the speed offset and the course angle offset in each set of offset information according to the actual speed information, the actual course angle information, the reference speed information and the reference course angle information of the target vehicle at each preset time point.
4. The method according to claim 3, wherein the determining the position offset information in each of the sets of offset information according to the actual position information and the reference position information of the target vehicle at each preset time point comprises:
and determining the transverse position offset information in each position offset information according to the actual transverse position information and the reference transverse position information of the target vehicle at each preset time point, and determining the longitudinal position offset information in each position offset information according to the actual longitudinal position information and the reference longitudinal position information.
5. The method according to claim 1, wherein determining an initial effect evaluation value of the target vehicle based on the respective sets of offset information and vehicle running state information corresponding to the set of offset information comprises:
processing the offset information with the same offset name in each set of offset information to obtain target offset information of each offset information set; wherein the offset information group corresponds to each offset name; the offset name comprises at least one of a position offset name, a speed offset name and a course angle offset name;
determining an initial effect evaluation value of the target vehicle according to the target offset information and the vehicle running state corresponding to the target time point of the target offset information;
the target time point is a time point in a group of preset time points.
6. The method of claim 5, wherein obtaining the target offset information for each offset information group by processing the offset information of the same offset name in each group of offset information comprises:
determining offset information corresponding to each offset name from each set of offset information, and taking the offset information as an offset information set corresponding to each offset name; wherein the number of the offset information groups is consistent with the number of the offset names;
and determining target offset information of each offset information group according to the offset quantity and the offset information in each offset information group.
7. The method of claim 6, wherein determining the target offset information for each offset information group according to the offset amount and the offset information in each offset information group comprises:
sorting the offset information in each offset information group from high to low to obtain offset sorting;
and determining the last offset information which is higher than a preset proportion threshold value according to the offset quantity and the offset sequence, and taking the last offset information as the target offset information.
8. The method according to claim 5, wherein determining the initial effect evaluation value of the target vehicle according to the target offset information and the vehicle driving state corresponding to the target time point of the target offset information comprises:
determining the actual running state of the vehicle corresponding to each target offset information at the corresponding target time point;
and determining an initial effect evaluation value of the target vehicle according to the target offset information and the corresponding weight value corresponding to each reference index item in the corresponding actual running state of the vehicle.
9. The method according to claim 8, wherein the determining the actual driving state of the vehicle corresponding to each target offset information at the corresponding target time point comprises:
determining target time points corresponding to the target offset information, and acquiring front wheel steering angle information and vehicle acceleration value information of the target time points;
and determining the actual running state of the target vehicle at each target time point according to the front wheel steering angle information and the vehicle acceleration value information of each target time point.
10. The method according to claim 8, wherein the target offset information includes at least one of target position offset information, target speed offset information and target course angle offset information, the reference index item includes at least one of a driving index item, a speed index item and a course angle index item, and the determining the initial effect evaluation value of the target vehicle according to the respective target offset information and the corresponding weight value corresponding to the respective reference index item in the corresponding actual driving state of the vehicle includes:
determining a position effect evaluation value of the target vehicle according to the target position offset information and a driving index weight value of the corresponding actual driving state of the vehicle; the driving index weight value comprises at least one of a straight driving index weight value and a turning index weight value;
determining a speed effect evaluation value of the target vehicle according to the target speed offset information and the speed index weight value;
determining a course angle effect evaluation value of the target vehicle according to the target course angle offset information and a course angle index weight value of the corresponding vehicle running state;
and determining an initial effect evaluation value of the target vehicle according to the position effect evaluation value, the speed effect evaluation value and the course angle effect evaluation value.
11. The method according to claim 10, wherein the positional offset information includes lateral offset information and longitudinal offset information, and the determining the positional effect evaluation value of the target vehicle based on the target positional offset information and a running index weight value of a corresponding vehicle actual running state includes:
determining a transverse position effect evaluation value according to the transverse offset information and a straight index weight value or a turning index weight value in the driving index weight values;
and determining a longitudinal position effect evaluation value according to the longitudinal offset information and an acceleration weighted value in the driving index weighted values.
12. The method of claim 10, wherein the straight index weight value is greater than the curve index weight value, and wherein a straight course angle index weight value is less than a curve course angle index weight value in the course angle index weight values.
13. The method of claim 1, further comprising:
acquiring an accident effect evaluation value;
updating the initial effect evaluation value based on the accident effect evaluation value.
14. The method of claim 13, wherein prior to said obtaining an accident effectiveness assessment value, the method further comprises:
when a trigger target event is detected, determining a target trigger time corresponding to the target event;
obtaining group to-be-processed offset information according to the to-be-determined running information and the theoretical running information corresponding to the target trigger time;
and determining the accident effect evaluation value according to the group of to-be-processed offset information and preset group offset information.
15. The method of claim 14, wherein determining the accident effectiveness assessment value based on the set of pending offset information and a preset set of offset information comprises:
and when the to-be-processed transverse position offset information in the set of to-be-processed offset information is smaller than a preset transverse position offset threshold, the to-be-processed longitudinal position offset information is smaller than a preset longitudinal offset threshold, the to-be-processed speed offset information is smaller than a preset speed offset threshold, and the to-be-processed course angle offset information is smaller than a preset course angle offset threshold, determining the accident effect evaluation value as a first preset accident effect evaluation value.
16. The method of claim 13, wherein determining the target control effect of the target vehicle based on the initial effect assessment value and a preset effect assessment value comprises:
and determining that the target control effect on the target vehicle meets a preset condition under the condition that the initial effect evaluation value is smaller than a preset effect evaluation value.
17. A control effect evaluation apparatus characterized by comprising:
the group offset information determining module is used for acquiring a group of preset time points and determining group offset information of each preset time point according to actual running associated information and reference running associated information of the target vehicle at each preset time point in the group of preset time points; wherein the set of offset information includes at least one offset information; the reference driving related information is determined based on a preset generated reference planned path;
the initial effect evaluation value determining module is used for determining the initial effect evaluation value of the target vehicle according to each group of offset information and the vehicle running state information corresponding to each group of offset information;
and the target control effect determining module is used for determining the target control effect of the target vehicle according to the initial effect evaluation value and a preset evaluation effect value.
18. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the control effect evaluation method of any one of claims 1-16.
19. A storage medium containing computer-executable instructions for performing the control effect evaluation method of any one of claims 1-16 when executed by a computer processor.
CN202110573994.6A 2021-05-25 2021-05-25 Control effect evaluation method, device, electronic equipment and storage medium Active CN113343448B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110573994.6A CN113343448B (en) 2021-05-25 2021-05-25 Control effect evaluation method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110573994.6A CN113343448B (en) 2021-05-25 2021-05-25 Control effect evaluation method, device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113343448A true CN113343448A (en) 2021-09-03
CN113343448B CN113343448B (en) 2024-03-05

Family

ID=77471474

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110573994.6A Active CN113343448B (en) 2021-05-25 2021-05-25 Control effect evaluation method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113343448B (en)

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009119921A (en) * 2007-11-12 2009-06-04 Mitsubishi Electric Corp Vehicular steering device and vehicle control device
CN103234763A (en) * 2013-04-09 2013-08-07 北京理工大学 System and method for quantitatively evaluating unmanned vehicles
CN106020203A (en) * 2016-07-15 2016-10-12 百度在线网络技术(北京)有限公司 Method and device for controlling unmanned vehicle
WO2017126102A1 (en) * 2016-01-22 2017-07-27 ボルボ トラック コーポレーション Driving evaluation device, driving evaluation method, reference data provision method, reference data provision device, and reference data provision program
CN108647437A (en) * 2018-05-09 2018-10-12 公安部交通管理科学研究所 A kind of autonomous driving vehicle evaluation method and evaluation system
CN109784630A (en) * 2018-12-12 2019-05-21 北京百度网讯科技有限公司 Automatic Pilot level evaluation method, device, computer equipment and storage medium
CN109910878A (en) * 2019-03-21 2019-06-21 山东交通学院 Automatic driving vehicle avoidance obstacle method and system based on trajectory planning
CN109991974A (en) * 2018-01-02 2019-07-09 中国移动通信有限公司研究院 Automatic Pilot path follower method, device and control equipment
CN110599025A (en) * 2019-09-06 2019-12-20 武汉理工大学 Method for evaluating reliability index of driving behavior of automatic driving automobile
CN111583645A (en) * 2020-05-09 2020-08-25 北京京东乾石科技有限公司 Quality evaluation method, device, server and medium for vehicle cooperative driving
CN111605587A (en) * 2019-02-26 2020-09-01 比亚迪股份有限公司 Train, automatic train operation system and operation parameter optimization method and system thereof
WO2020187254A1 (en) * 2019-03-18 2020-09-24 长城汽车股份有限公司 Longitudinal control method and system for automatic driving vehicle

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009119921A (en) * 2007-11-12 2009-06-04 Mitsubishi Electric Corp Vehicular steering device and vehicle control device
CN103234763A (en) * 2013-04-09 2013-08-07 北京理工大学 System and method for quantitatively evaluating unmanned vehicles
WO2017126102A1 (en) * 2016-01-22 2017-07-27 ボルボ トラック コーポレーション Driving evaluation device, driving evaluation method, reference data provision method, reference data provision device, and reference data provision program
CN106020203A (en) * 2016-07-15 2016-10-12 百度在线网络技术(北京)有限公司 Method and device for controlling unmanned vehicle
CN109991974A (en) * 2018-01-02 2019-07-09 中国移动通信有限公司研究院 Automatic Pilot path follower method, device and control equipment
CN108647437A (en) * 2018-05-09 2018-10-12 公安部交通管理科学研究所 A kind of autonomous driving vehicle evaluation method and evaluation system
CN109784630A (en) * 2018-12-12 2019-05-21 北京百度网讯科技有限公司 Automatic Pilot level evaluation method, device, computer equipment and storage medium
CN111605587A (en) * 2019-02-26 2020-09-01 比亚迪股份有限公司 Train, automatic train operation system and operation parameter optimization method and system thereof
WO2020187254A1 (en) * 2019-03-18 2020-09-24 长城汽车股份有限公司 Longitudinal control method and system for automatic driving vehicle
CN109910878A (en) * 2019-03-21 2019-06-21 山东交通学院 Automatic driving vehicle avoidance obstacle method and system based on trajectory planning
CN110599025A (en) * 2019-09-06 2019-12-20 武汉理工大学 Method for evaluating reliability index of driving behavior of automatic driving automobile
CN111583645A (en) * 2020-05-09 2020-08-25 北京京东乾石科技有限公司 Quality evaluation method, device, server and medium for vehicle cooperative driving

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
王健: "汽车在两种转向工况下的路径规划与路径跟踪研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》, pages 035 - 10 *
王斌;: "智能汽车避障风险评估及轨迹规划", 汽车技术, no. 06, pages 32 - 37 *

Also Published As

Publication number Publication date
CN113343448B (en) 2024-03-05

Similar Documents

Publication Publication Date Title
CN109444932B (en) Vehicle positioning method and device, electronic equipment and storage medium
CN110288096B (en) Prediction model training method, prediction model training device, prediction model prediction method, prediction model prediction device, electronic equipment and storage medium
EP3699052A1 (en) Method and device for eliminating steady-state lateral deviation and storage medium
CN110134126B (en) Track matching method, device, equipment and medium
CN108974054B (en) Seamless train positioning method and system
CN110834642A (en) Vehicle deviation identification method and device, vehicle and storage medium
CN111856521A (en) Data processing method and device, electronic equipment and storage medium
CN107450511A (en) Assess method, apparatus, equipment and the computer-readable storage medium of wagon control model
CN111380546A (en) Vehicle positioning method and device based on parallel road, electronic equipment and medium
CN111984018A (en) Automatic driving method and device
CN110851490A (en) Vehicle travel common stay point mining method and device based on vehicle passing data
CN113085901B (en) Unmanned vehicle control method and device, electronic equipment and storage medium
CN110186472B (en) Vehicle yaw detection method, computer device, storage medium, and vehicle system
CN108528453A (en) It is a kind of towards collaborative truck information uncertainty with control method for vehicle of speeding
CN112432643B (en) Driving data generation method and device, electronic equipment and storage medium
CN114475656A (en) Travel track prediction method, travel track prediction device, electronic device, and storage medium
CN110450788B (en) Driving mode switching method, device, equipment and storage medium
CN113343448B (en) Control effect evaluation method, device, electronic equipment and storage medium
US11688213B2 (en) Telematics data processing for collision detection
CN109270566B (en) Navigation method, navigation effect testing method, device, equipment and medium
CN113619589B (en) Method and device for determining driving behavior information, electronic equipment and storage medium
CN114550466B (en) Parking space state detection method and device and electronic equipment
CN114895274A (en) Guardrail identification method
CN113799715A (en) Method and device for determining vehicle abnormal reason, communication equipment and storage medium
CN113947947A (en) Vehicle collision early warning method and device, electronic 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