CN109491369B - Method, device, equipment and medium for evaluating performance of vehicle actual control unit - Google Patents
Method, device, equipment and medium for evaluating performance of vehicle actual control unit Download PDFInfo
- Publication number
- CN109491369B CN109491369B CN201811479522.9A CN201811479522A CN109491369B CN 109491369 B CN109491369 B CN 109491369B CN 201811479522 A CN201811479522 A CN 201811479522A CN 109491369 B CN109491369 B CN 109491369B
- Authority
- CN
- China
- Prior art keywords
- control unit
- ideal
- actual
- time period
- data output
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for evaluating the performance of an actual control unit of a vehicle. The method comprises the following steps: planning a target path based on a high-precision map, controlling an ideal decision planning control module to perform ideal simulation driving according to the target path, and collecting planning data output by a decision planning unit in the ideal decision planning control module and ideal track data and ideal motion state data output by the ideal control unit in the ideal simulation driving process; the planning data output by the decision planning unit in the first time period is used as the input of an actual control unit to be tested, the actual control unit is controlled to work, and the actual track data and the actual motion state data output by the actual control unit in the second time period are collected; and determining the performance of the actual control unit according to the trajectory data and the motion state data output by the ideal control unit and the actual control unit in the second time period. The evaluation efficiency of the vehicle actual control unit is improved.
Description
Technical Field
The embodiment of the invention relates to an automatic driving technology, in particular to a method, a device, equipment and a medium for evaluating the performance of a vehicle actual control unit.
Background
In the road testing process of the automatic driving vehicle, the driving paths are all non-quantitative and uncontrollable, so that in order to ensure the driving safety of the automatic driving vehicle, testing of actual control algorithms of the automatic driving vehicle under various driving paths is necessary. The actual control algorithm is applied to an actual control unit, the actual control unit actually controls the running of the vehicle based on the planning data output by the decision planning control module, at present, when the actual control module of the vehicle is subjected to effect evaluation, the effect evaluation is usually performed on the actual control module before the vehicle leaves a factory, and the evaluation of the actual control module is very inefficient in the actual running process of the vehicle.
Disclosure of Invention
The embodiment of the invention provides a performance evaluation method, a performance evaluation device, performance evaluation equipment and performance evaluation media for an actual vehicle control unit, which can be used for carrying out simulation test on the actual vehicle control unit based on data output by an ideal decision planning control module aiming at different paths, so that the evaluation efficiency of the actual vehicle control unit is improved.
In a first aspect, an embodiment of the present invention provides a method for evaluating performance of a vehicle actual control unit, the method including:
planning a target path based on a high-precision map, controlling an ideal decision planning control module to perform ideal simulation driving according to the target path, and acquiring planning data output by a decision planning unit in the ideal decision planning control module and ideal trajectory data and ideal motion state data output by the ideal control unit in an ideal simulation driving process;
taking planning data output by the decision planning unit in a first time period as input of an actual control unit to be tested, controlling the actual control unit to work, and collecting actual trajectory data and actual motion state data output by the actual control unit in a second time period, wherein the first time period is before the second time period;
and determining the performance of the actual control unit according to the ideal track data and the ideal motion state data output by the ideal control unit in the second time period and the actual track data and the actual motion state data output by the actual control unit in the second time period.
In a second aspect, an embodiment of the present invention further provides a performance evaluation device of a vehicle actual control unit, including:
the driving control module is used for planning a target path based on the high-precision map and controlling the ideal decision planning control module to perform ideal simulation driving according to the target path;
the ideal data acquisition module is used for acquiring planning data output by a decision planning unit in the ideal decision planning control module and ideal track data and ideal motion state data output by an ideal control unit in an ideal simulation driving process;
the actual data acquisition module is used for taking planning data output by the decision planning unit in a first time period as input of an actual control unit to be tested, controlling the actual control unit to work, and acquiring actual trajectory data and actual motion state data output by the actual control unit in a second time period, wherein the first time period is before the second time period;
and the performance determining module is used for determining the performance of the actual control unit according to the ideal track data and the ideal motion state data output by the ideal control unit in the second time period and the actual track data and the actual motion state data output by the actual control unit in the second time period.
In a third aspect, an embodiment of the present invention further provides an apparatus, including:
one or more processors;
storage means 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 performance evaluation method of the vehicle physical control unit according to any of the embodiments of the invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements a performance evaluation method of a vehicle actual control unit according to any embodiment of the present invention.
According to the scheme of the embodiment of the invention, the ideal decision planning control module outputs planning data, ideal track data and ideal motion state data in the process of driving according to the target path planned by the high-precision map, inputs the planning data into the actual control unit to obtain the actual track data and the actual motion state data, and carries out performance evaluation on the actual control unit together with the ideal track data and the ideal motion state data. The simulation test of the actual control unit is realized on the basis of the data output by the ideal decision planning control module aiming at different paths, and the evaluation efficiency of the actual control unit of the automatic driving vehicle is improved.
Drawings
FIG. 1 is a flow chart of a method for evaluating the performance of a vehicle physical control unit according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for evaluating the performance of a vehicle physical control unit according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a performance evaluation device of a vehicle actual control unit according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus according to a fourth 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 flowchart of a method for evaluating performance of an actual control unit of a vehicle according to an embodiment of the present invention, where the embodiment is applicable to a situation where a performance evaluation is performed on an actual control unit of an autonomous vehicle, and the method may be implemented by a performance evaluation device or apparatus of an actual control unit of a vehicle according to an embodiment of the present invention, where the device may be implemented in a hardware and/or software manner, and may be configured in an autonomous vehicle. As shown in fig. 1, the method specifically comprises the following steps:
s101, planning a target path based on a high-precision map, controlling an ideal decision planning control module to perform ideal simulation driving according to the target path, and collecting planning data output by a decision planning unit in the ideal decision planning control module and ideal track data and ideal motion state data output by the ideal control unit in an ideal simulation driving process.
The high-precision map can be map data essential in the driving process of the automatic driving vehicle, and plays roles in high-precision positioning, environment perception assistance, decision-making and planning control and the like in the automatic driving process. The high-precision map comprises detailed information of roads such as lane lines, lane line central lines, lane attribute changes and the like; the curvature, gradient, course, and other mathematical parameter information of the road; and road component information such as traffic signs, land-list signs, etc. The high-precision map can be obtained by downloading from the Internet, and can also be obtained by off-line manufacturing based on three-dimensional point cloud data acquired by a radar laser and positioning data of a global positioning system. The ideal decision planning control module can be a core module in the automatic driving vehicle, and the module can comprise a decision planning unit and an ideal control unit, wherein the decision planning unit can generate a driving strategy according to the high-precision map data and the current driving condition of the vehicle in the driving process of the automatic driving vehicle, and generate planning data according to the strategy. The ideal control unit can be planning data generated by the perfect execution decision planning unit to obtain ideal running track and ideal motion state data. For example, according to a high-precision map and the positioning condition of an automatic driving vehicle, the decision planning unit finds that a turn is needed in the front and the vehicle is running straight currently, a turn decision instruction is generated, turn planning data (such as the rotational inertia of a steering wheel, the rotation angle of a front wheel, the rotation angle of a rear wheel, the vehicle speed and the like) is generated according to the turn decision instruction, and the ideal control unit perfectly executes the planning data to obtain ideal running track and motion state data. And controlling the automatic driving vehicle to run according to the generated turning planning data.
Optionally, in the embodiment of the present invention, the target path is planned based on the high-precision map, and the optimal target path for the current driving is automatically planned by the system based on the map data between the starting point position and the ending point position in the high-precision map after the tester inputs the starting point position and the ending point position in the automatic driving vehicle system; or the target path can be manually planned by a tester in an automatic driving vehicle system based on a high-precision map. The target path may include a left/right turn of 45 degrees, a u-turn, a single/multi-lane around a dogbone, etc. And after the planning of the target path is finished, the automatic driving vehicle controls the ideal decision planning control module to perform ideal simulation driving according to the planned target path. That is, the vehicle ideally travels along the target path, but during the actual traveling of the autonomous vehicle, the vehicle may not perfectly travel along the planned target path, and if there is an obstacle on the road during the traveling, the traveling path may need to be changed to detour. Therefore, in the ideal simulation driving process of the automatic driving vehicle, the decision planning control module needs to adjust the driving strategy at the next moment in real time to generate planning data for controlling the driving at the next moment, so as to control the vehicle to safely drive on the road. Specifically, in the ideal simulation driving process of the vehicle, a decision planning unit in the ideal decision planning control module generates planning data for controlling the automatic driving vehicle at the next moment according to the current driving condition and the high-precision map data of the current position. The ideal control unit perfectly executes the planning data to obtain ideal track data and ideal motion state data. The ideal track data is the track data obtained by perfectly executing the planning data, and the track data may include position coordinates of each track point, time corresponding to each track point, a heading of the track, and the like. The ideal motion state may be perfect execution plan data, resulting in motion state data, which may include velocity and/or rotational angle.
It should be noted that the planning data is a driving basis for the next driving of the autonomous vehicle, and therefore the planning data output by the decision planning unit of the autonomous vehicle at the current time is actually the planning data for controlling the driving of the vehicle at the next time. Therefore, the ideal trajectory data and the ideal moving state data output by the ideal control unit executing the planning data are the ideal trajectory data and the ideal moving state data of the vehicle at the next time.
And S102, taking the planning data output by the decision planning unit in the first time period as the input of the actual control unit to be tested, controlling the actual control unit to work, and collecting the actual track data and the actual motion state data output by the actual control unit in the second time period.
The first time period and the second time period may be two adjacent time periods, and the first time period is before the second time period, and the planning data output by the decision planning unit in the first time period is used for controlling the automatic driving vehicle to run in the second time period. For example, when the current time decision planning unit analyzes that an obstacle exists in front of the vehicle, a deceleration avoidance strategy is generated, and planning data for controlling deceleration and steering of the vehicle is generated, wherein the planning data for deceleration and steering is used for controlling deceleration and steering of the vehicle when the vehicle runs at the next time. The actual control unit may be a control unit that actually controls the running of the autonomous vehicle. Compared with an ideal control unit, the control unit considers the dynamic influence factor of the actual running process of the vehicle, considers the influence of the dynamic factor when executing the planning data output by the decision planning unit, and ensures that the vehicle runs according to the understood track and the motion state of the ideal control unit as far as possible.
Specifically, the planning data which is output by the decision planning unit in the first time period and used for controlling the vehicle to run in the second time period is used as the input of the actual control unit to be tested in the S101, so that the actual control unit is controlled to control the automatic driving vehicle to run according to the input planning data, and then the data acquisition unit is used for acquiring actual track data and actual motion state data which are output by the vehicle when the actual control unit controls the automatic driving vehicle to run. The actual trajectory data and the actual motion state data are substantially actual trajectory data and actual motion state data of a second time period corresponding to the planning data of the first time period. Optionally, the data acquisition unit may acquire the actual trajectory data and the actual motion state data output by the actual control unit, and determine the acquisition period according to the calculation frequency of the control algorithm of the actual control unit, for example, if the calculation frequency of the control algorithm is 10Hz/s, the sampling period may be 1s for once acquisition.
And S103, determining the performance of the actual control unit according to the ideal track data and the ideal motion state data output by the ideal control unit in the second time period and the actual track data and the actual motion state data output by the actual control unit in the second time period.
Optionally, when the autonomous vehicle runs based on the planning data output by the decision planning unit, due to the influence of vehicle dynamics or actual environment conditions, the vehicle may not ensure that actual trajectory data and actual motion state data output by the actual control unit are completely consistent with ideal trajectory data and ideal motion state data output by the ideal control unit for perfectly executing the planning data. For example, the planned data is a turning angle of 30 degrees, the ideal control unit perfectly performs the planned data output is 30 degrees, and the actual control unit actually controls the actual turning angle of the vehicle to only 25 degrees due to the influence of frictional resistance. The performance of the actual control unit can be determined according to the deviation degree between the actual trajectory and actual motion state data and the ideal trajectory and ideal motion state data, and the performance evaluation of the actual control unit is completed.
Optionally, in the embodiment of the present invention, when determining the performance of the actual control unit according to the trajectory data and the motion state data of the ideal control unit and the actual control unit in the second time period, the performance of the actual control unit is divided into trajectory data output performance and motion state data output performance to be evaluated, for example, the ideal trajectory data output by the ideal control unit in the second time period may be compared with the actual trajectory data output by the actual control unit in the second time period, so as to determine the similarity between the two trajectory data, and further obtain the trajectory data output performance of the actual control unit; and comparing the ideal motion state data output by the ideal control unit in the second time period with the actual motion state data output by the actual control unit in the second time period, and determining the similarity degree of the two motion state data so as to obtain the motion state data output performance of the actual control unit. Or the overall performance of the actual control unit can be evaluated by combining the trajectory data output performance and the motion state data output performance of the actual control unit. If the track data output performance and the motion state output performance can be brought into a preset total performance calculation formula, and the total performance of the actual control unit is calculated; the weighting performance of the trajectory data output performance and the motion state data output performance may be calculated as the total performance of the actual control unit.
For example, comparing the ideal trajectory data output by the ideal control unit in the second time period with the actual trajectory data output by the actual control unit in the second time period, determining the similarity between the two trajectory data, and further obtaining the trajectory data output performance of the actual control unit, may be: calculating a distance average value between the actual track data and the ideal track data (for example, calculating a distance difference value of each corresponding track point in the two track data, and determining an average value of the distance difference values of all the track points), and judging a corresponding performance evaluation condition when the actual control unit outputs the track data according to the distance average value and a preset judgment standard, wherein if the distance average value is smaller, the corresponding performance evaluation effect of the actual control unit when the actual control unit outputs the track data is better; the performance evaluation result corresponding to the actual control unit when outputting the trajectory data can also be determined by drawing a trajectory diagram. Specifically, the method can comprise the following steps:
A. and drawing a first track map according to the ideal track data output by the ideal control unit in the second time period.
Specifically, a track graph with the abscissa as each time in the second time period and the ordinate as the position of the ideal track point is constructed, each track point data in the ideal track data is marked in the track graph according to the corresponding time and track position, and each track point marked in the track graph is subjected to curve fitting to obtain an ideal track data graph, namely the first track graph. Optionally, when the first trajectory graph is drawn, the ideal trajectory data may be input into the curve fitting software through curve fitting software, and the software may fit the input ideal trajectory data to obtain the first trajectory graph corresponding to the data.
B. And drawing a second track map according to the actual track data output by the actual control unit in the second time period.
Specifically, when the second track map is drawn, an actual track data map with the abscissa as each time in the second time period and the ordinate as the actual track point position may be constructed based on the actual track data, that is, the second track map, and the specific drawing manner may be the same as that for drawing the first track map, which is not described again.
C. And determining the performance of the actual control unit according to the consistency rate between the first track map and the second track map.
Specifically, the consistency rate between the first track map and the second track map is judged, and the higher the consistency rate between the first track map and the second track map is, the better the corresponding performance evaluation effect is when the actual control unit outputs the track data. Alternatively, when the coincidence rate between the first and second maps is determined, the coincidence rate and the error rate of the first and second maps may be calculated.
For example, comparing the ideal motion state data output by the ideal control unit in the second time period with the actual motion state data output by the actual control unit in the second time period, determining the similarity between the two motion state data, and further obtaining the motion state data output performance of the actual control unit, may be: and determining the performance of the actual control unit according to the consistency ratio between the ideal motion state data output by the ideal control unit in the second time period and the actual motion state data output by the actual control unit in the second time period. Specifically, at least one of the speed and/or the rotation angle in the actual motion state data may be compared with at least one of the speed and/or the rotation angle in the ideal motion state data to determine the similarity between the actual motion state data and the ideal motion state data, so as to obtain the motion state data output performance of the actual control unit. The higher the degree of similarity, the better the motion state data output performance of the actual control unit. Different weight values can be set for the speed and the rotation angle in the motion state data respectively (for example, different weight values can be set for different types of data according to the importance degree of the motion state data in the process of controlling the vehicle to run by the actual control unit); and then calculating the weighted similarity degree between the actual motion state data and the ideal motion state data, and taking the weighted similarity degree as the motion state data output performance of the actual control unit.
Optionally, in the embodiment of the present invention, when the consistency of the two trajectory data and the consistency of the two motion states are compared, the consistency of the corresponding time and/or the corresponding specific value may be compared. For example, it may be determined whether the corresponding times of the track points corresponding to each other in the two pieces of track data are consistent and/or whether the corresponding positions of the track points corresponding to each other in the two pieces of track data are consistent.
Optionally, when determining the performance of the actual control unit according to the ideal trajectory data and the ideal motion state data output by the ideal control unit in the second time period and the actual trajectory data and the actual motion state data output by the actual control unit in the second time period, the performance of the actual control unit may also be determined by using a pre-trained performance test model. Specifically, the ideal trajectory data, the ideal motion state data, the actual trajectory data, and the actual motion state data may be input into a pre-trained performance test model, and the model may analyze the input data according to an algorithm during training and output a performance analysis result of the actual control unit. The performance test model can be obtained by training the neural network model by adopting a plurality of neural network algorithms by taking a plurality of groups of ideal track data, ideal motion state data, actual track data and actual motion state data under different paths and different scenes and taking a performance analysis result of an actual control unit corresponding to each group of data as sample data in advance.
Optionally, in order to improve the accuracy of performance evaluation of the actual control unit, multiple different target paths may be planned based on the high-precision map, and the method may be performed multiple times under the multiple different target paths to determine the performance of the actual control unit under the different target paths. And analyzing to obtain the final performance evaluation result of the actual control unit according to the performance evaluation results of the actual control unit determined for multiple times.
The embodiment provides a performance evaluation method of an actual vehicle control unit, wherein an ideal decision planning control module outputs planning data, ideal track data and ideal motion state data in the process of driving according to a target path planned by a high-precision map, inputs the planning data into the actual control unit to obtain the actual track data and the actual motion state data, and performs performance evaluation on the actual control unit together with the ideal track data and the ideal motion state data. The simulation test of the actual control unit is realized on the basis of the data output by the ideal decision planning control module aiming at different paths, and the evaluation efficiency of the actual control unit of the automatic driving vehicle is improved.
Example two
Fig. 2 is a flowchart of a method for evaluating performance of a vehicle actual control unit according to a second embodiment of the present invention, which is further optimized based on the second embodiment, and specifically shows a specific process introduction of forming the actual control unit of the autonomous vehicle before evaluating performance of the vehicle actual control unit. As shown in fig. 2, the method includes:
s201, a vehicle dynamic model is constructed according to the static attribute parameters of the vehicle.
The static attribute parameters may be fixed parameters of the vehicle itself, which cause an error between the decision planning control value and the actual output value of the vehicle. For example, vehicle empty mass, vehicle track, vehicle wheel base, and the like may be included. The vehicle empty mass may be the mass of the vehicle itself when the vehicle is not carrying any objects; the wheel track of the vehicle can be the distance between a left wheel and a right wheel which are symmetrically arranged on the vehicle; the wheelbase of the vehicle may be the distance between the front and rear wheels on the same side of the vehicle. The vehicle dynamics model can be a model established for researching the relation between the stress condition acting on the vehicle and the vehicle motion, and can comprise a 2-degree-of-freedom 1/4 model, a 7-degree-of-freedom 1/2 model, a 15-degree-of-freedom vehicle model and the like.
Optionally, when the vehicle dynamics model is constructed according to the static attribute parameters of the vehicle, the reason for error between the ideal output value and the actual output value caused by analysis can be used, so that the degree of freedom of the vehicle is determined, and the vehicle dynamics model conforming to the current automatic driving wheel is constructed according to the static attribute parameters of the vehicle; or, an existing vehicle dynamics model (e.g., a 2-degree-of-freedom 1/4 model, a 7-degree-of-freedom 1/2 model, or a 15-degree-of-freedom vehicle model) in the existing dynamics theory may be used, and the vehicle dynamics model of the current autonomous vehicle may be constructed in combination with the static attribute parameters of the current autonomous vehicle, for example, the obtained static attribute parameters of the vehicle may be introduced into third-party dynamics software, and the software may automatically construct the vehicle dynamics model of the autonomous vehicle.
Optionally, when the vehicle dynamics model is constructed according to the static attribute parameters of the vehicle, a vehicle dynamics model may be constructed for a type of automatic driving vehicle of the same model or similar vehicle.
S202, calibrating the vehicle dynamic model according to the relation between the vehicle actual running parameters collected in the actual running process of the vehicle on the road to form an actual control unit.
The actual vehicle driving parameters may refer to driving parameters output by the autonomous vehicle in the actual road running process, and may include: acceleration, speed, accelerator, brake, steering wheel moment of inertia, torque, friction coefficient, front wheel angle, rear wheel angle, vehicle steering error, etc. of the autonomous vehicle.
In order to prevent the situation that parameters of the vehicle dynamics model are inaccurate due to different measurement errors or different driving environments of the vehicle dynamics model constructed in step S201, the constructed vehicle dynamics model needs to be calibrated before the actual control unit is generated based on the vehicle dynamics model, so that the situation that the performance of the generated actual control unit is poor due to errors of the vehicle dynamics model is avoided.
Optionally, there is usually a certain corresponding relationship between the collected vehicle actual driving parameters, for example, a relationship between acceleration and speed, a relationship between an accelerator, a relationship between a steering wheel inertia and a front wheel rotation angle, a rear wheel rotation angle, and the like. In the embodiment of the invention, the vehicle dynamics model can be calibrated through the relation between the driving parameters output in the actual driving process of the automatic driving vehicle, for example, the model formula parameters related to the acceleration, the speed and the accelerator in the vehicle dynamics model can be adjusted according to the relation between the acceleration and the speed and the accelerator. The vehicle dynamics model can also be calibrated by the relationship between the driving parameters output during the actual driving of the autonomous vehicle and the relationship between the ideal driving parameters planned by the ideal decision planning control module through the dynamics model of the vehicle. Specifically, the parameter values in the vehicle dynamics model can be adjusted by comparing the relationship between the actual driving parameters with the relationship between the planned ideal driving parameters, so as to complete the calibration of the vehicle dynamics model; or constructing a cost function according to the relation between the actual running parameters and the relation between the running parameters obtained by the simulation test, solving the corresponding dynamic model formula parameter when the error is minimum, and further completing the calibration of the vehicle dynamic model; the method can also be based on a neural network model, the relation between actual driving parameters and the relation between planned ideal driving parameters are input into the neural network model, and the neural network model analyzes and outputs the optimal parameter value corresponding to the dynamic model according to sample data in training and a corresponding algorithm, so that the calibration of the vehicle dynamic model is completed. It should be noted that, the embodiment of the present invention may also calibrate the vehicle dynamics model according to the relationship between the vehicle actual driving parameters acquired by the vehicle in the road actual operation process in other manners, which is not limited in this embodiment.
Optionally, after the vehicle dynamics model is calibrated, an actual control unit in the autonomous vehicle may be formed based on the vehicle dynamics model, and the actual control unit thus constructed avoids a situation where an actual output differs from an output of an ideal control unit in the ideal decision-making planning control module due to static attribute parameters of the vehicle and vehicle dynamics factors. The accuracy of the result output by the actual control unit according to the planning data is improved. Specifically, according to the calibrated vehicle dynamics model, the actual control unit may be formed by: and embedding a formula corresponding to the calibrated vehicle dynamic model into a control algorithm of an actual control unit, and for each planning data input into the actual control unit, processing the planning data based on the vehicle dynamic model formula in the control algorithm and then controlling the automatic driving vehicle to run.
And S203, planning a target path based on the high-precision map, controlling an ideal decision planning control module to perform ideal simulation driving according to the target path, and collecting planning data output by a decision planning unit in the ideal decision planning control module and ideal track data and ideal motion state data output by the ideal control unit in the ideal simulation driving process.
And S204, taking the planning data output by the decision planning unit in the first time period as the input of the actual control unit to be tested, controlling the actual control unit to work, and acquiring the actual trajectory data and the actual motion state data output by the actual control unit in the second time period.
And S205, determining the performance of the actual control unit according to the ideal track data and the ideal motion state data output by the ideal control unit in the second time period and the actual track data and the actual motion state data output by the actual control unit in the second time period.
The embodiment provides a performance evaluation method of an actual vehicle control unit, which comprises the steps of constructing a vehicle dynamic model, calibrating the constructed vehicle dynamic model to generate an actual vehicle control unit, outputting planning data, ideal track data and ideal motion state data by an ideal decision planning control module when the actual vehicle control unit is subjected to performance evaluation, inputting the planning data into the actual vehicle control unit to obtain the actual track data and the actual motion state data, and carrying out performance evaluation on the actual vehicle control unit together with the ideal track data and the ideal motion state data. The control accuracy of the actual control unit can be guaranteed as far as possible when the actual control unit is generated, then the actual control unit is subjected to simulation test based on data output by the ideal decision planning control module aiming at different paths, the evaluation efficiency of the actual control unit of the vehicle is improved, and the running safety of the automatic driving vehicle is further improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a performance evaluation device of a vehicle actual control unit according to a third embodiment of the present invention, which is capable of executing a performance evaluation method of a vehicle actual control unit according to any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method, and can be configured in an autonomous vehicle. As shown in fig. 3, the apparatus includes:
the driving control module 301 is configured to plan a target path based on a high-precision map, and control an ideal decision planning control module to perform ideal simulation driving according to the target path;
an ideal data acquisition module 302, configured to acquire planning data output by a decision planning unit in the ideal decision planning control module and ideal trajectory data and ideal motion state data output by an ideal control unit in an ideal simulation driving process;
an actual data acquisition module 303, configured to use planning data output by the decision planning unit in a first time period as an input of an actual control unit to be tested, control the actual control unit to work, and acquire actual trajectory data and actual motion state data output by the actual control unit in a second time period, where the first time period is before the second time period;
and a performance determining module 304, configured to determine performance of the actual control unit according to the ideal trajectory data and the ideal motion state data output by the ideal control unit in the second time period, and the actual trajectory data and the actual motion state data output by the actual control unit in the second time period.
The embodiment provides a performance evaluation device of a vehicle actual control unit, wherein an ideal decision planning control module outputs planning data, ideal track data and ideal motion state data in the process of driving according to a target path planned by a high-precision map, inputs the planning data into the actual control unit to obtain the actual track data and the actual motion state data, and carries out performance evaluation on the actual control unit together with the ideal track data and the ideal motion state data. The simulation test of the actual control unit is realized on the basis of the data output by the ideal decision planning control module aiming at different paths, and the evaluation efficiency of the actual control unit of the automatic driving vehicle is improved.
Further, the performance determining module 304 is specifically configured to:
drawing a first track graph according to ideal track data output by the ideal control unit in the second time period;
drawing a second track graph according to actual track data output by the actual control unit in the second time period;
and determining the performance of the actual control unit according to the consistency rate between the first track map and the second track map.
Further, the performance determining module 304 is specifically configured to:
determining the performance of the actual control unit according to the consistency ratio between the ideal motion state data output by the ideal control unit in the second time period and the actual motion state data output by the actual control unit in the second time period; wherein the ideal motion state data and the actual motion state data comprise speed and/or rotational angle.
Further, the above apparatus further comprises an actual unit forming module for:
constructing a vehicle dynamic model according to the static attribute parameters of the vehicle;
calibrating the vehicle dynamic model according to the relation between the vehicle actual running parameters collected in the actual running process of the vehicle on the road to form the actual control unit
Example four
Fig. 4 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention. Fig. 4 shows a block diagram of an exemplary device 40 suitable for use in implementing embodiments of the present invention. The device 40 shown in fig. 4 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present invention. As shown in fig. 4, the device 40 is in the form of a general purpose computing device. The components of the apparatus 40 may include, but are not limited to: one or more processors or processing units 401, a system memory 402, and a bus 403 that couples the various system components (including the system memory 402 and the processing unit 401).
The system memory 402 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)404 and/or cache memory 405. Device 40 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 406 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, 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 the bus 403 by one or more data media interfaces. System memory 402 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 408 having a set (at least one) of program modules 407 may be stored, for example, in system memory 402, such program modules 407 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. Program modules 407 generally perform the functions and/or methods of the described embodiments of the invention.
The processing unit 401 executes various functional applications and data processing by running a program stored in the system memory 402, for example, to implement a performance evaluation method of a vehicle actual control unit provided by an embodiment of the present invention.
EXAMPLE five
Fifth embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, can implement the method for evaluating the performance of the vehicle actual control unit described in the above-described embodiment.
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. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. 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, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects 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).
The above example numbers are for description only and do not represent the merits of the examples.
It will be appreciated by those of ordinary skill in the art that the modules or operations of the embodiments of the invention described above may be implemented using a general purpose computing device, which may be centralized on a single computing device or distributed across a network of computing devices, and that they may alternatively be implemented using program code executable by a computing device, such that the program code is stored in a memory device and executed by a computing device, and separately fabricated into integrated circuit modules, or fabricated into a single integrated circuit module from a plurality of modules or operations thereof. Thus, the present invention is not limited to any specific combination of hardware and software.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of evaluating performance of a vehicle physical control unit, characterized by comprising:
planning a target path based on a high-precision map, controlling an ideal decision planning control module to perform ideal simulation driving according to the target path, and acquiring planning data output by a decision planning unit in the ideal decision planning control module and ideal trajectory data and ideal motion state data output by the ideal control unit in an ideal simulation driving process;
taking planning data output by the decision planning unit in a first time period as input of an actual control unit to be tested, controlling the actual control unit to work, and collecting actual trajectory data and actual motion state data output by the actual control unit in a second time period, wherein the first time period is before the second time period;
determining the performance of the actual control unit according to the ideal track data and the ideal motion state data output by the ideal control unit in the second time period and the actual track data and the actual motion state data output by the actual control unit in the second time period;
wherein the ideal motion state data is the speed and/or rotation angle obtained by the ideal execution planning data.
2. The method of claim 1, wherein determining the performance of the actual control unit based on the ideal trajectory data output by the ideal control unit during the second time period and the actual trajectory data output by the actual control unit during the second time period comprises:
drawing a first track graph according to ideal track data output by the ideal control unit in the second time period;
drawing a second track graph according to actual track data output by the actual control unit in the second time period;
and determining the performance of the actual control unit according to the consistency rate between the first track map and the second track map.
3. The method of claim 1, wherein determining the performance of the actual control unit based on the ideal motion state data output by the ideal control unit during the second time period and the actual motion state data output by the actual control unit during the second time period comprises:
determining the performance of the actual control unit according to the consistency ratio between the ideal motion state data output by the ideal control unit in the second time period and the actual motion state data output by the actual control unit in the second time period; wherein the ideal motion state data and the actual motion state data comprise speed and/or rotational angle.
4. The method of claim 1, wherein the method uses the motion state data output by the decision planning unit in the first time period as input to the actual control unit to be tested, and further comprises:
constructing a vehicle dynamic model according to the static attribute parameters of the vehicle;
and calibrating the vehicle dynamic model according to the relation between the vehicle actual running parameters acquired in the actual running process of the vehicle on the road to form the actual control unit.
5. A performance evaluation device of a vehicle actual control unit, characterized by comprising:
the driving control module is used for planning a target path based on the high-precision map and controlling the ideal decision planning control module to perform ideal simulation driving according to the target path;
the ideal data acquisition module is used for acquiring planning data output by a decision planning unit in the ideal decision planning control module and ideal track data and ideal motion state data output by an ideal control unit in an ideal simulation driving process;
the actual data acquisition module is used for taking planning data output by the decision planning unit in a first time period as input of an actual control unit to be tested, controlling the actual control unit to work, and acquiring actual trajectory data and actual motion state data output by the actual control unit in a second time period, wherein the first time period is before the second time period;
the performance determining module is used for determining the performance of the actual control unit according to the ideal track data and the ideal motion state data output by the ideal control unit in the second time period and the actual track data and the actual motion state data output by the actual control unit in the second time period;
wherein the ideal motion state data is the speed and/or rotation angle obtained by the ideal execution planning data.
6. The apparatus of claim 5, wherein the performance determination module is specifically configured to:
drawing a first track graph according to ideal track data output by the ideal control unit in the second time period;
drawing a second track graph according to actual track data output by the actual control unit in the second time period;
and determining the performance of the actual control unit according to the consistency rate between the first track map and the second track map.
7. The apparatus of claim 5, wherein the performance determination module is specifically configured to:
determining the performance of the actual control unit according to the consistency ratio between the ideal motion state data output by the ideal control unit in the second time period and the actual motion state data output by the actual control unit in the second time period; wherein the ideal motion state data and the actual motion state data comprise speed and/or rotational angle.
8. The apparatus of claim 5, further comprising a real cell forming module to:
constructing a vehicle dynamic model according to the static attribute parameters of the vehicle;
and calibrating the vehicle dynamic model according to the relation between the vehicle actual running parameters acquired in the actual running process of the vehicle on the road to form the actual control unit.
9. An apparatus, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of evaluating performance of a vehicle physical control unit according to any one of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of evaluating the performance of a vehicle physical control unit according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811479522.9A CN109491369B (en) | 2018-12-05 | 2018-12-05 | Method, device, equipment and medium for evaluating performance of vehicle actual control unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811479522.9A CN109491369B (en) | 2018-12-05 | 2018-12-05 | Method, device, equipment and medium for evaluating performance of vehicle actual control unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109491369A CN109491369A (en) | 2019-03-19 |
| CN109491369B true CN109491369B (en) | 2020-11-17 |
Family
ID=65699328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811479522.9A Active CN109491369B (en) | 2018-12-05 | 2018-12-05 | Method, device, equipment and medium for evaluating performance of vehicle actual control unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109491369B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109883448B (en) * | 2019-03-28 | 2021-10-15 | 北京经纬恒润科技股份有限公司 | Map box testing method and system |
| CN110210058B (en) * | 2019-04-26 | 2024-04-26 | 纵目科技（上海）股份有限公司 | Reference line generation method, system, terminal and medium conforming to vehicle dynamics |
| CN110544375A (en) * | 2019-06-10 | 2019-12-06 | 河南北斗卫星导航平台有限公司 | Vehicle supervision method and device and computer readable storage medium |
| CN110162023A (en) * | 2019-06-24 | 2019-08-23 | 北京智行者科技有限公司 | A kind of test method of control module |
| CN113112643A (en) * | 2020-01-13 | 2021-07-13 | 北京地平线机器人技术研发有限公司 | Evaluation method and device for predicted trajectory, electronic device and storage medium |
| CN113761701B (en) * | 2020-09-11 | 2024-09-20 | 北京京东乾石科技有限公司 | Target simulation control method and device |
| CN114019975B (en) * | 2021-11-05 | 2024-06-11 | 广州极飞科技股份有限公司 | Agricultural tool track control method and device and agricultural machine |
| CN117217422B (en) * | 2023-11-07 | 2024-03-22 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle motion control capability assessment method, system, device and medium thereof |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4211594B2 (en) * | 2003-12-18 | 2009-01-21 | 日産自動車株式会社 | Three-dimensional road surface environment model and evaluation device for vehicle behavior control system equipped with the model |
| CN102323761B (en) * | 2011-07-18 | 2013-03-27 | 铁道部运输局 | Semi-physical simulation testing platform of train control network |
| CN105223832B (en) * | 2014-06-25 | 2018-11-30 | 南车株洲电力机车研究所有限公司 | Locomotive hardware-in-the-loop simulation device, system and method |
| CN104460349B (en) * | 2014-11-28 | 2017-01-18 | 北京经纬恒润科技有限公司 | Real automobile in-the-loop simulation testing method, real-time simulation machine and system |
| CN104536434A (en) * | 2014-12-15 | 2015-04-22 | 华晨汽车集团控股有限公司 | Vehicle network bus simulation and testing method |
| CN105807750B (en) * | 2014-12-30 | 2018-12-18 | 株洲南车时代电气股份有限公司 | A kind of the semi-hardware type simulation test device and test method of city rail vehicle motion control unit |
| CN104932268A (en) * | 2015-06-08 | 2015-09-23 | 武汉理工大学 | Fuzzy PID based automobile cruise control system |
| CN105573296B (en) * | 2016-01-15 | 2017-12-15 | 上海汽车变速器有限公司 | Vehicle diagnosis automatization test system and method based on hardware in loop |
| CN107992016A (en) * | 2016-10-26 | 2018-05-04 | 法乐第(北京)网络科技有限公司 | A kind of automatic driving vehicle analog detection method |
| US20180239342A1 (en) * | 2017-02-22 | 2018-08-23 | Electronics And Telecommunications Research Institute | Method and apparatus for registering virtual equipment for virtual production system |
| CN108829087B (en) * | 2018-07-19 | 2019-09-10 | 山东省科学院自动化研究所 | A kind of intelligent test system of autonomous driving vehicle |
-
2018
- 2018-12-05 CN CN201811479522.9A patent/CN109491369B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109491369A (en) | 2019-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109491369B (en) | Method, device, equipment and medium for evaluating performance of vehicle actual control unit | |
| CN109522673B (en) | Test method, device, equipment and storage medium | |
| US11783590B2 (en) | Method, apparatus, device and medium for classifying driving scenario data | |
| US11400928B2 (en) | Driverless vehicle testing method and apparatus, device and storage medium | |
| CN113032285B (en) | High-precision map testing method and device, electronic equipment and storage medium | |
| CN109215372B (en) | Road network information updating method, device and equipment | |
| CN108508881B (en) | Automatic driving control strategy adjusting method, device, equipment and storage medium | |
| CN110609290B (en) | Laser radar matching positioning method and device | |
| CN109435955B (en) | Performance evaluation method, device and equipment for automatic driving system and storage medium | |
| WO2022056770A1 (en) | Path planning method and path planning apparatus | |
| CN109866752A (en) | Double mode parallel vehicles track following driving system and method based on PREDICTIVE CONTROL | |
| CN108995657A (en) | Operate the method and data processing system of automatic driving vehicle | |
| CN109870698B (en) | Ultrasonic array obstacle detection result processing method and system | |
| CN111665738A (en) | In-loop simulation system and information processing method and device thereof | |
| CN109444932A (en) | A kind of vehicle positioning method, device, electronic equipment and storage medium | |
| CN111983936A (en) | Semi-physical simulation system and evaluation method for unmanned aerial vehicle | |
| CN112834249B (en) | Steering parameter detection method, device, equipment and storage medium | |
| CN107697155A (en) | Control method and device for wheel steering angle and wheel steering angle controller | |
| CN113126624B (en) | Automatic driving simulation test method, device, electronic equipment and medium | |
| CN113324542B (en) | Positioning method, device, equipment and storage medium | |
| CN112651456A (en) | Unmanned vehicle control method based on RBF neural network | |
| WO2022226477A1 (en) | Systems and methods for simulation supported map quality assurance in an autonomous vehicle context | |
| KR20230137439A (en) | A computer-implemented method for assessing the accuracy of swarm trajectory locations. | |
| CN111368409A (en) | Vehicle flow simulation processing method, device, equipment and storage medium | |
| CN113119999B (en) | Method, device, equipment, medium and program product for determining automatic driving characteristics |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211021 Address after: 105 / F, building 1, No. 10, Shangdi 10th Street, Haidian District, Beijing 100085 Patentee after: Apollo Intelligent Technology (Beijing) Co.,Ltd. Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Patentee before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. |