CN115556748A - Method, apparatus, device and storage medium for limiting speed of curve of autonomous vehicle - Google Patents
Method, apparatus, device and storage medium for limiting speed of curve of autonomous vehicle Download PDFInfo
- Publication number
- CN115556748A CN115556748A CN202211288424.3A CN202211288424A CN115556748A CN 115556748 A CN115556748 A CN 115556748A CN 202211288424 A CN202211288424 A CN 202211288424A CN 115556748 A CN115556748 A CN 115556748A
- Authority
- CN
- China
- Prior art keywords
- speed
- bending
- curve
- speed limit
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000000670 limiting effect Effects 0.000 title claims abstract description 37
- 238000005452 bending Methods 0.000 claims abstract description 62
- 230000001133 acceleration Effects 0.000 claims abstract description 48
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 230000009471 action Effects 0.000 claims abstract description 34
- 230000007704 transition Effects 0.000 claims abstract description 29
- 238000011217 control strategy Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 52
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 7
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 9
- 230000000007 visual effect Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000002829 reductive effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 208000031427 Foetal heart rate deceleration Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/14—Adaptive cruise control
- B60W30/143—Speed control
- B60W30/146—Speed limiting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18145—Cornering
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The application relates to a curve speed limiting method, a curve speed limiting device, curve speed limiting equipment and a storage medium for an automatic driving vehicle, wherein the method comprises the following steps: acquiring the longitudinal accumulated distance and the scatter curvature radius of each path point of a reference path to obtain the curvature radius of each path point, and acquiring a target speed limit value through a comfort over-bending speed calibration table of the current curve speed limit scene; calculating the predicted position of the vehicle in a preset time length based on a preset kinematic model, solving a speed sequence obtained by a target speed limit value, and judging the current intention of the automatic driving vehicle; the method comprises the steps of matching corresponding bending advance aiming time or bending advance aiming time according to current intention, determining bending advance deceleration action or bending advance acceleration action, and performing linear transition on a speed sequence through a quadratic programming algorithm to generate a bending speed limit control strategy of the automatic driving vehicle.
Description
Technical Field
The application relates to the technical field of curve speed limiting speed planning, in particular to a curve speed limiting method, a curve speed limiting device, curve speed limiting equipment and a storage medium for an automatic driving vehicle.
Background
The automatic driving technology can be divided into six modules of perception, positioning, prediction, decision, planning and control from the technical flow direction, wherein the planning module plays a key role in starting and stopping, and the vehicle is divided into path planning and speed planning according to longitudinal and transverse motion. In the driving process of the intelligent driving automobile, a reference line of a reference path can be generated, so that guidance and basis are provided for path planning or speed planning, the reference path can be divided into a global reference path and a local reference path in the space-time dimension, the intelligent driving levels are different, the meaning and the obtaining mode of the reference path are also different, and for example, in the L2 level, the lane central line obtained in the visual mode and the like can be used as the reference path; when the map is in the L4 level, generally, a reference path needs to be acquired by using global prior information of a high-precision map, so as to ensure the effects of path planning and speed planning.
In the automatic driving technology, the purpose of speed planning is to plan a smooth speed sequence meeting the control requirement of the vehicle for the vehicle, the smooth speed sequence is complementary with path planning, the smooth speed sequence plays a key role in controlling the transverse direction and the longitudinal direction of the vehicle at the rear end, the mutual support of the two technologies can greatly improve the intelligent level of the vehicle, and the commercial landing process is accelerated. The speed planning has different algorithm ideas aiming at different scenes, wherein the curve speed limit is a functional requirement necessary for automatically driving the automobile in scenes of turning on and off ramps of a highway, turning at an urban intersection and the like, the excellent curve speed limit function can gradually decelerate to a specified speed limit value before the curve enters, then adaptively adjust the speed limit value in the curve according to the curvature radius, and finally slowly accelerate to a reasonable target speed in advance when the curve exits.
Currently, the related art may obtain N upper limit speeds corresponding to curvatures according to curvatures respectively corresponding to N positions in a preset curve section in a vehicle advancing direction, then evaluate the N upper limit speeds according to current driving information of the vehicle, obtain a target upper limit speed, and obtain an acceleration curve corresponding to the target upper limit speed. In addition, the related art can also calculate the curvature of the curve according to visual perception to calculate the speed limit value, or carry out lane line visual identification on both high-quality roads and non-high-quality roads by using a camera to realize the speed limit of the curve.
However, the related art cannot adapt to various scenes, and lacks necessary acceleration smooth theory support, so that the acceleration is easily too large, the accuracy of curve curvature identification is low, the driving experience of a user is greatly influenced, and urgent solution is needed.
Disclosure of Invention
The application provides a curve speed limiting method, a curve speed limiting device, curve speed limiting equipment and a storage medium for an automatic driving vehicle, and aims to solve the problems that the related technology cannot adapt to various scenes, is lack of necessary acceleration smooth theoretical support, easily causes overlarge acceleration, and is low in curve curvature identification accuracy.
An embodiment of a first aspect of the application provides a method for limiting the speed of a curve of an automatically driven vehicle, which comprises the following steps: acquiring a longitudinal accumulated distance of each path point of a reference path, calculating a scatter curvature radius of the reference path to obtain a curvature radius of each path point, and acquiring a target speed limit value through a comfort overbending speed calibration table of a current curve speed limit scene; calculating the predicted position of the automatic driving vehicle in a preset time length based on a preset kinematic model, solving a target speed limit value according to the predicted position to obtain a speed sequence, and judging the current intention of the automatic driving vehicle; and matching corresponding bending advance aiming time or bending exit aiming time according to the current intention, determining bending advance deceleration action or bending exit acceleration action according to the bending advance aiming time or the bending exit aiming time, performing linear transition on the speed sequence by utilizing a target speed cost function of a pre-constructed quadratic programming algorithm, and generating a curve speed limit control strategy of the automatic driving vehicle based on the bending advance deceleration action or the bending exit acceleration action and the speed sequence after the linear transition.
According to the technical means, the curvature radius and the speed limit value of the reference path point and the position of the reference path point within a certain time of the vehicle are calculated, then the target speed limit value is obtained through interpolation, the preview time is introduced, and the speed limit sequence is combined with the quadratic programming algorithm to carry out smooth transition processing, so that the method and the device are suitable for various scenes, the reasonability of curve speed limit planning is improved, and the driving experience of a user is greatly improved while the safety of the vehicle is guaranteed.
Optionally, in an embodiment of the present application, the linearly transitioning the speed sequence by using a target speed cost function of a pre-constructed quadratic programming algorithm includes: and linearly descending all the speed limit values of the speed sequence and continuing to use the speed limit value at the preset moment.
According to the technical means, the embodiment of the application avoids the frequent acceleration and deceleration of the vehicle in a very short time through a reasonable linear transition strategy, so that the running speed of the vehicle at the curve is more stable, the rationality and superiority of curve speed limit planning are improved, and the driving experience of a user is greatly improved.
Optionally, in an embodiment of the present application, the target speed cost function is:
wherein f and x are vectors; h is a matrix; omega i A weight representing each cost function;
is an acceleration cost function;
is an acceleration cost function;
is the target speed deviation term.
According to the technical means, the speed sequence is subjected to linear transition through constructing the target speed cost function of the appropriate quadratic programming algorithm, so that the smooth speed sequence meeting the vehicle control requirement is planned for the vehicle curve speed limit, the scene universality of the curve speed limit algorithm is improved, the vehicle safety is guaranteed, and meanwhile, the intelligent level of the vehicle is greatly improved.
Optionally, in an embodiment of the present application, the determining the current intent of the autonomous vehicle includes: when the minimum speed serial number of the speed sequence is greater than or equal to a first preset serial number, the current intention is an intention of bending; and when the minimum speed serial number of the speed sequence is equal to a second preset serial number, the current intention is a bending intention.
According to the technical means, the embodiment of the application judges the current intention of the automatic driving vehicle by comparing the index position of the minimum speed in the speed sequence, so that the reliability and the intelligent level of the vehicle are effectively improved, and an important basis is provided for the follow-up generation of the curve speed-limiting control strategy of the automatic driving vehicle.
Optionally, in an embodiment of the present application, the first preset serial number is greater than the second preset serial number.
According to the technical means, the size between the preset serial numbers is reasonably set, and the accuracy of judging the current driving intention of the vehicle is powerfully guaranteed.
Optionally, in an embodiment of the present application, before the obtaining the longitudinal cumulative distance of each waypoint of the reference path, the method further includes: acquiring lane line data by using a lane level navigation system, and smoothing the lane line data to obtain the reference path; or acquiring a lane line image by using a vehicle-mounted camera, and fitting the lane line image to obtain the reference path.
According to the technical means, the embodiment of the application can utilize high-precision map prior information or visual equipment, the environmental adaptability and robustness of the vehicle for acquiring the reference path are improved, and the curvature of the path and the corresponding speed limit value can be calculated in advance through the reference path acquired in advance within a certain distance in front, so that the curve speed limit experience of the automatic driving vehicle is effectively guaranteed.
The embodiment of the second aspect of the application provides a curve speed limiting device of an automatic driving vehicle, which comprises: the calculation module is used for acquiring the longitudinal accumulated distance of each path point of a reference path, calculating the scatter curvature radius of the reference path to obtain the curvature radius of each path point, and obtaining a target speed limit value through a comfort overbending speed calibration table of the current curve speed limit scene; the judging module is used for calculating the predicted position of the automatic driving vehicle in the preset time length based on a preset kinematic model, solving a target speed limit value according to the predicted position to obtain a speed sequence and judging the current intention of the automatic driving vehicle; and the generation module is used for matching corresponding bending advance aiming time or bending exit aiming time according to the current intention, determining bending advance deceleration action or bending exit acceleration action according to the bending advance aiming time or the bending exit aiming time, performing linear transition on the speed sequence by utilizing a target speed cost function of a pre-constructed quadratic programming algorithm, and generating a curve speed limit control strategy of the automatic driving vehicle based on the bending advance deceleration action or the bending exit acceleration action and the speed sequence after the linear transition.
Optionally, in an embodiment of the present application, the generating module includes: and the smoothing unit is used for linearly descending all the speed limit values of the speed sequence and continuing to use the speed limit values at the preset moment.
Optionally, in an embodiment of the present application, the target speed cost function is:
wherein f and x are vectors; h is a matrix; omega i Weights representing each cost function；
Is an acceleration cost function;
is an acceleration cost function;
is the target speed deviation term.
Optionally, in an embodiment of the present application, the determining module includes: the bending entering unit is used for determining the current intention as a bending entering intention when the minimum speed serial number of the speed sequence is greater than or equal to a first preset serial number; and the bending-out unit is used for judging that the current intention is a bending-out intention when the minimum speed serial number of the speed sequence is equal to a second preset serial number.
Optionally, in an embodiment of the present application, the first preset serial number is greater than the second preset serial number.
Optionally, in an embodiment of the present application, the method further includes: a first obtaining module, configured to obtain lane line data by using a lane-level navigation system before obtaining the longitudinal accumulated distance of each path point of the reference path, and perform smoothing processing on the lane line data to obtain the reference path; or the second acquisition module is used for acquiring lane line images by using a vehicle-mounted camera and fitting the lane line images to obtain the reference path.
An embodiment of a third aspect of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and operable on the processor, the processor executing the program to implement the method of curve speed limiting for an autonomous vehicle as described in the above embodiments.
A fourth aspect of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the curve speed limiting method of an autonomous vehicle as above.
Thus, the embodiments of the present application have the following advantageous effects:
(1) According to the method and the device, the curvature radius and the speed limit value of the reference path point and the position of the reference path point within a certain time of the vehicle are calculated, then the target speed limit value is obtained through interpolation, the preview time is introduced, and the speed limit sequence of the quadratic programming algorithm is combined for smooth transition processing, so that the method and the device are suitable for various scenes, the reasonability of curve speed limit planning is improved, and the driving experience of a user is greatly improved while the safety of the vehicle is guaranteed.
(2) The embodiment of the application avoids frequent acceleration and deceleration of the vehicle in a very short time through a reasonable linear transition strategy, so that the running speed of the vehicle at the curve is more stable, the reasonability and the superiority of curve speed limit planning are improved, and the driving experience of a user is greatly improved.
(3) According to the method and the device, the speed sequence is subjected to linear transition through the target speed cost function of the proper quadratic programming algorithm, so that the smooth speed sequence meeting the vehicle control requirement is planned for the vehicle curve speed limit, the scene universality of the curve speed limit algorithm is improved, and the intelligent level of the vehicle is greatly improved while the vehicle safety is guaranteed.
(4) According to the embodiment of the application, the current intention of the automatic driving vehicle is judged by comparing the index position of the minimum speed in the speed sequence, so that the reliability and the intelligent level of the vehicle are effectively improved, and an important basis is provided for the follow-up generation of the curve speed-limiting control strategy of the automatic driving vehicle.
(5) According to the embodiment of the application, the size between the preset serial numbers is reasonably set, so that the accuracy of judgment of the current driving intention of the vehicle is powerfully guaranteed.
(6) According to the embodiment of the application, high-precision map prior information or visual equipment can be utilized, the environmental adaptability and robustness of the vehicle for acquiring the reference path are improved, and the curvature of the path and the corresponding speed limit value can be calculated in advance through the reference path acquired in a certain distance in front, so that the curve speed limit experience of the automatic driving vehicle is effectively guaranteed.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method for limiting a speed of a curve of an autonomous vehicle according to an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating a method for calculating cumulative distance of reference waypoints according to an embodiment of the present application;
FIG. 3 is a schematic diagram of calculating a reference waypoint radius of curvature according to an embodiment of the present application;
FIG. 4 is a curve speed limit calibration graph provided in accordance with an embodiment of the present application;
FIG. 5 is a schematic diagram of a method for calculating a future 8s reference speed limit according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating a staggered occurrence of peaks and valleys of a speed limit according to an embodiment of the present application;
FIG. 7 is a logic diagram illustrating an implementation of a curve speed limit method for an autonomous vehicle according to an embodiment of the present application;
FIG. 8 is an exemplary diagram of a curve speed limiter arrangement of an autonomous vehicle in accordance with an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
The device comprises a curve speed limiting device of an automatic driving vehicle, a 100-calculation module, a 200-judgment module, a 300-generation module, a 901-memory, a 902-processor and a 903-communication interface, wherein the curve speed limiting device comprises the following components of 10-an automatic driving vehicle.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
A curve speed limiting method, apparatus, device, and storage medium of an autonomous vehicle according to an embodiment of the present application are described below with reference to the accompanying drawings. In order to solve the problems mentioned in the background art, the application provides a curve speed-limiting method of an automatic driving vehicle, in the method, the curvature radius of each path point is obtained by obtaining the longitudinal accumulated distance and the scattered point curvature radius of each path point of a reference path, and a target speed-limiting value is obtained through a comfort over-bending speed calibration table of a current curve speed-limiting scene; calculating the predicted position of the vehicle in a preset time length based on a preset kinematic model, solving a target speed limit value to obtain a speed sequence, and judging the current intention of the automatic driving vehicle; the method comprises the steps of matching corresponding bend-in preview time or bend-out preview time according to current intentions, determining bend-in deceleration action or bend-out acceleration action, and performing linear transition on a speed sequence through a quadratic programming algorithm to generate a bend speed-limiting control strategy of the automatic driving vehicle. Therefore, the problems that the related technology cannot be adapted to various scenes, the necessary acceleration smooth theoretical support is lacked, the acceleration is too large easily, the curve curvature identification accuracy is low and the like are solved.
Specifically, fig. 1 is a flowchart of a curve speed limiting method for an autonomous vehicle according to an embodiment of the present disclosure.
As shown in fig. 1, the curve speed limiting method of the autonomous vehicle includes the steps of:
in step S101, a longitudinal accumulated distance of each path point of the reference path is obtained, a scatter curvature radius of the reference path is calculated, a curvature radius of each path point is obtained, and a target speed limit value is obtained through a comfort overbending speed calibration table of the current curve speed limit scene.
It should be noted that, when the embodiment of the present application performs curve speed limitation on an autonomous vehicle, a longitudinal accumulated distance of each point of a reference trajectory of the autonomous vehicle may be calculated first, and then a scatter curvature radius of the reference path may be calculated to obtain a curvature radius of each path point. And then, a target speed limit value is obtained by combining a comfortable over-bending speed calibration table of the current curve speed limit scene, so that reliable data support is provided for subsequent vehicle speed limit operation.
Optionally, in an embodiment of the present application, before acquiring the longitudinal cumulative distance of each waypoint of the reference path, the method further includes: acquiring lane line data by using a lane level navigation system, and smoothing the lane line data to obtain a reference path; or acquiring a lane line image by using a vehicle-mounted camera, and fitting the lane line image to obtain a reference path.
Specifically, the embodiments of the present application may obtain the above-mentioned reference path by:
1. a lane-level navigation system based on a high-precision map acquires a reference path;
the embodiment of the application can acquire specific lane line information through a high-precision map, however, the acquired lane lines cannot be guaranteed to be smooth enough in the map measurement and drawing process, and a broken line condition may exist, so that the embodiment of the application can smooth the lane lines by using a smoothing algorithm through a decision module to output a smooth reference path.
2. A reference path is obtained based on a visual method.
In the embodiment of the application, in the auxiliary driving based on the L2 level, the lane image in front of the vehicle can be collected through the camera so as to extract and fit lane line information, and therefore the reference path is obtained.
It should be noted that due to the influence of the camera pixels and the curve environment, the method can only correctly fit the lane line not far ahead of the lane where the vehicle is located, for example, in a small-radius road such as a ramp, the vehicle can correctly fit lane line data about 20 meters by using a visual method, and the fitting accuracy is higher as the radius is larger, so that the embodiment of the application can still obtain a reference path by using the visual method for a scene which cannot be covered by a high-precision map such as an expressway, and the vehicle can decelerate in time when the curvature of the curve changes.
It should be noted that, in the embodiment of the present application, when the navigation signal strength allows in the current driving environment of the vehicle, the above reference route may be preferentially acquired by the lane-level navigation system of the high-precision map. In the specific implementation process, a person skilled in the art may also adopt other technical methods and apparatuses to obtain the reference path according to the actual situation, which is not specifically limited herein.
Therefore, the embodiment of the application can utilize high-precision map prior information or visual equipment, the environmental adaptability and robustness of the vehicle for acquiring the reference path are improved, and the path curvature and the corresponding speed limit value can be calculated in advance through the reference path acquired in advance within a certain distance in front, so that the curve speed limit experience of the automatic driving vehicle is effectively guaranteed.
After the reference path is obtained in the above manner, embodiments of the present application may further obtain a longitudinal cumulative distance of each path point of the reference path.
Specifically, the embodiment of the present application may first calculate the distance between each two adjacent path scatters, and record as: l1, L2, L3, \8230 \ 8230;, L448, L449 and L500; let S1= L1, then, starting from the second path point, add the distances of the previous adjacent scatter points, respectively noted: s2= S1+ L2, S3= S2+ L3, sn = Sn-1+ Ln-1, S500= S499+ L500, and the calculated longitudinal cumulative distance value of each path scatter just corresponds to that index value. Through the above calculation, the longitudinal accumulated distance of each path point of the reference trajectory can be obtained, as shown in fig. 2.
After the longitudinal accumulated distance of each path point of the reference trajectory is obtained, further, the embodiment of the application may calculate the curvature radius of the reference path point. Fig. 3 is a schematic diagram of calculating the radius of curvature of the reference path discrete point, as shown in fig. 3, where a, B, and C are three consecutive discrete points of the reference line, and a, B, and C are opposite sides thereof. According to the relevant properties of the circumscribed circle of the triangle, the center O of the circumscribed circle of the triangle can be obtained by making the intersection point of the perpendicular bisectors of the three sides.
In Δ ABC, it can be known from the cosine theorem:
connecting CO and extending the intersection circle to a point D, and obtaining the following result according to the opposite angle complementary property of the quadrilateral circumscribed circle because the circle O is the circumscribed circle of the quadrilateral ABCD:
in order to conclude the above formula, the curvature can be expressed as:
therefore, the curvatures of three continuous discrete points A, B and C can be obtained by combining formula (1) and formula (3).
It can be understood by those skilled in the art that after the longitudinal accumulated distance of each waypoint of the reference trajectory and the curvature radius of the reference waypoint are obtained, in order to perform reasonable speed planning, the embodiment of the application can also calibrate the comfort overbending reference speedometer to obtain a reasonable target speed limit value.
It should be noted that there are generally two types of calibration for the bending speed of an autonomous vehicle, one is the bending speed based on safety, and the other is the bending speed that gives consideration to safety and comfort. The over-bending speed based on safety is relatively conservative, so that the over-bending speed calibration considering safety and comfort can be adopted in the embodiment of the application.
As a way to implement, the embodiment of the present application may perform multiple rounds of actual tests on different driving speeds in multiple different curve scenes, such as curves and ramps on a highway, intersections in an urban area, and the like, and comprehensively consider the driving styles and subjective feelings of different drivers and passengers, so as to finally obtain a comfortable over-bending speed calibration table, as shown in table 1:
TABLE 1
| Turning radius (m) | Comfortable vehicle speed (km/h) | Comfortable vehicle speed (m/s) | Transverse acceleration (m/s) 2 ) |
| 6 | 14 | 3.89 | 2.52 |
| 10 | 18 | 5.00 | 2.50 |
| 15 | 20 | 5.56 | 2.06 |
| 25 | 32 | 8.89 | 3.16 |
| 35 | 37 | 10.28 | 3.02 |
| 45 | 41 | 11.39 | 2.88 |
| 55 | 44 | 12.22 | 2.72 |
| 65 | 50 | 13.89 | 2.97 |
| 75 | 52 | 14.44 | 2.78 |
| 85 | 55 | 15.28 | 2.75 |
| 95 | 56 | 15.56 | 2.55 |
| 105 | 61 | 16.94 | 2.73 |
| 115 | 62 | 17.22 | 2.58 |
| 125 | 64 | 17.78 | 2.53 |
| 135 | 68 | 18.89 | 2.64 |
| 175 | 73 | 20.28 | 2.35 |
| 285 | 80 | 22.22 | 1.73 |
| 352 | 84 | 23.33 | 1.55 |
| 530 | 94 | 26.11 | 1.29 |
| 787 | 108 | 30.00 | 1.14 |
| 1030 | 120 | 33.33 | 1.08 |
It should be noted that table 1 details the comfortable vehicle speed and lateral acceleration corresponding to the turning radius with non-equal spacing between 6m and 1030m, and the missing turning radius data can be obtained by linear interpolation. Embodiments of the present application may plot the data of table 1 into a comfort overbending reference speed curve, as shown in fig. 4.
It is worth noting that the calculated lateral acceleration has no strict mathematical law, that is, the curve speed limit is greatly dependent on the subjective feeling of people, and is difficult to be regularly expressed by an objective mathematical model. Therefore, according to the embodiment of the application, the curvature radius of each path point is obtained according to the reference path points, and then the reasonable target speed limit value is obtained through interpolation of the comfortable turning reference speedometer, so that the accuracy of curvature calculation and the reasonability of the speed limit value are improved, and reliable data support is provided for subsequent vehicle speed limit operation.
In step S102, a predicted position of the autonomous vehicle in a preset time period is calculated based on a preset kinematic model, a target speed limit value is solved according to the predicted position to obtain a speed sequence, and a current intention of the autonomous vehicle is determined.
After the longitudinal accumulated distance, the scatter curvature radius and the target speed limit value of each path point of the reference path are obtained, the embodiment of the application can calculate the predicted position of the vehicle within a specified time length according to a kinematic model, and perform difference operation according to the predicted position to solve the target speed limit value to obtain a speed sequence and judge the current intention of the automatic driving vehicle.
In practical implementation, the embodiment of the application can calculate the future 8s position of the vehicle based on the kinematic model, and perform interpolation operation to solve the target speed limit value.
Specifically, fig. 5 is a schematic diagram illustrating calculation of a target speed limit value of a reference path in the future for 8s, and as shown in fig. 5, the embodiment of the present application may use a curve target speed limit as a reference speed of 8s in the ST diagram in each period, and at the same time, use the curve target speed limit as one of the cost functions of the quadratic programming algorithm to program a speed sequence approaching the target speed limit value.
Therefore, the embodiment of the present application can calculate the reference velocity of 8s in the ST map by using the uniform acceleration model, as shown in the following formula:
in the formula, v 0 And a 0 Respectively representing the current actual speed and acceleration of the vehicle.
It should be noted that, when the current actual acceleration of the vehicle is negative, in order to avoid the situation that the vehicle runs in reverse, the calculated vehicle speed needs to be determined, so as to ensure that the vehicle speed is not less than 0.
After the estimated position of the vehicle on the reference line in the future 8s is obtained through calculation, because the position is generally not coincident with the discrete point of the reference path, the curvature radius and the target speed limit value need to be obtained through interpolation based on the front discrete point and the rear discrete point according to a linear interpolation method adopted in the process of calculating the curvature radius and the speed limit value of the reference path point.
Therefore, the embodiment of the application calculates the position of the future 8s of the vehicle based on the kinematic model, and the speed sequence is obtained by solving the target speed limit value through interpolation, so that the reliability of the obtained speed sequence is guaranteed, and meanwhile, a basis is provided for judging the current intention of the automatic driving vehicle.
Optionally, in one embodiment of the present application, determining a current intent of the autonomous vehicle includes: when the minimum speed serial number of the speed sequence is greater than or equal to a first preset serial number, the current intention is an intention of entering a bend; and when the minimum speed serial number of the speed sequence is equal to a second preset serial number, the current intention is a bending-out intention.
It should be noted that, as shown in fig. 4, the comfort overbending speed limit is in positive correlation with the curvature radius of the curve, i.e., the larger the curvature radius of the curve is, the larger the speed limit is. The size of the target speed limit value of the future 8s obtained by the method is generally different. Therefore, the embodiment of the application can indirectly judge whether the automobile enters the curve or exits the curve by comparing the index position of the minimum speed in the 8s speed sequence.
Specifically, the embodiments of the present application judge the current intention of an autonomous vehicle, and are mainly classified into the following two cases:
1) As can be seen from fig. 4, the curve curvature radius corresponding to the lower speed is smaller, and if the minimum speed serial number of the 8s speed-limiting sequence is greater than or equal to 2, the speed-limiting value of the entire speed sequence tends to decrease first and then increase, i.e., it indicates that the place with the largest curve curvature is 2s or more in the future. In other words, the current position of the vehicle is somewhere before the minimum turning radius, i.e., is turning. For example, the minimum speed serial number is set to be 4, which indicates that the minimum speed limit value of 8s in the future appears in the 4 th s, and the current position with the maximum curvature from the 4 th s has a period of about 4s, so that the curve is currently in the curve advancing stage;
2) If the minimum speed serial number of the 8s speed limit sequence is equal to 1, the position which is very close to the position with the maximum curve curvature is indicated, and the speed limit values from the 2s to the 8s are all larger than the 1s, so that the situation can be regarded as the curve going out for the convenience of understanding and subsequent processing.
It can be understood that the embodiment of the application judges the current intention of the automatic driving vehicle by comparing the index position of the minimum speed in the speed sequence, thereby effectively improving the reliability and the intelligent level of the vehicle and providing an important basis for the subsequent generation of the curve speed limit control strategy of the automatic driving vehicle.
Optionally, in an embodiment of the present application, the first preset serial number is greater than the second preset serial number.
It should be noted that, in the process of determining the current intention of the autonomous vehicle, the embodiment of the present application needs to make the first preset serial number greater than the second preset serial number, for example, when the first preset serial number is 2, that is, the minimum speed serial number of the 8s speed limit sequence is greater than or equal to 2, to determine whether the vehicle is turning; the second preset serial number can be set to 1, namely the minimum speed serial number of the 8s speed-limiting sequence is equal to 1, and whether the vehicle is turning out is judged, so that the accuracy of judging the current driving intention of the vehicle is powerfully guaranteed by reasonably setting the sizes among the preset serial numbers.
In step S103, the corresponding bend entry preview time or bend exit preview time is matched according to the current intention, a bend entry deceleration action or bend exit acceleration action is determined according to the bend entry preview time or bend exit preview time, a linear transition is performed on the speed sequence by using a target speed cost function of a pre-constructed quadratic programming algorithm, and a curve speed limit control strategy for the autonomous vehicle is generated based on the bend entry deceleration action or bend exit acceleration action and the speed sequence after the linear transition.
It should be noted that after the speed sequence is obtained by solving the target speed limit value and the current intention of the autonomous vehicle is judged, the embodiment of the present application may introduce the preview time, determine the curve-entering deceleration action or the curve-exiting acceleration action, and perform linear transition on the speed sequence by using the target speed cost function of the pre-constructed quadratic programming algorithm to generate the curve speed limit control strategy of the autonomous vehicle, thereby improving the rationality of curve speed limit planning of the vehicle, improving the intelligence level of the vehicle, and accelerating the commercial landing process.
It will be appreciated by those skilled in the art that there are a number of hysteresis effects in an autonomous vehicle in a curve speed limit due primarily to the following reasons:
1) Generally, the quadratic programming algorithm does not directly use the curve speed limit as an inequality constraint condition, otherwise, the response overshoot of the automobile may be caused but the constraint condition is not satisfied, and then the solving error of the quadratic programming algorithm is enabled, so that the sum of squares of the difference between the automobile programming speed and the speed limit value is generally solved and is used as one of the performance indexes of the cost function, the programming speed is enabled to satisfy the speed limit value as far as possible by minimizing the cost function, and therefore, the hysteresis phenomenon exists in the process of adjusting the current speed to the target speed;
2) The control module level generally includes a PID (Proportional-Integral-Differential) control algorithm, wherein the Integral term has a delay, so that the programmed speed sequence also has a hysteresis phenomenon in the control algorithm level;
3) The control algorithm module outputs a deceleration command and the brake does not respond immediately to sufficient deceleration, so there is also a partial lag in this process.
In summary, in consideration of the timeliness of the curve speed limit, the problem of speed limit delay caused by system delay should be compensated at a planning layer, and therefore, the embodiment of the application introduces a preview time compensation concept.
It should be noted that, as shown in fig. 5, it is assumed that the automobile runs at a constant speed at a certain position of the curve, and 8 discrete points in the graph are calculated according to the automobile kinematics model. The bend-entering preview time t1 and the bend-exiting preview time t2 are introduced, the product of the current actual speed of the vehicle and the preview time is used as a preview distance, and the two values are used as calibration quantities in the actual debugging process to be determined. For example, assuming that the curve preview time t1=2s, since the host vehicle is set to travel at a constant speed, a new 1 st discrete point considering the preview distance should be the 3 rd position calculated previously, as shown in fig. 5. Since the curvature of the 3 rd discrete point is larger than that of the 1 st discrete point, the speed limit value of the 3 rd discrete point is necessarily smaller, so that the vehicle gradually generates smaller deceleration at the moment and slowly starts to decelerate. Thus, the embodiments of the present application can appropriately increase the deceleration distance to reduce the deceleration, thereby improving the ride comfort before the approach bend.
Similarly, assuming that the vehicle is currently located at t =5s and the time of the curve-out preview is 1s, the new discrete point of the 5 th s considering the preview distance should be the previously calculated 6 th position, as shown in fig. 5. Since the curvature of the discrete point at the 6 th s is larger than that of the discrete point at the 5 th s, the speed limit value at the 6 th s is necessarily larger, and the vehicle gradually generates a certain acceleration at this time and starts to accelerate slowly.
Thus, in embodiments of the present application, the vehicle may also accelerate before making a bend to avoid excessive response delays of the system, thereby improving the ride experience for the user.
Optionally, in an embodiment of the present application, the preset linear transition strategy is to linearly decrease all speed limit values of the speed sequence and follow the speed limit value at the preset time.
After the preview time compensation is introduced and the operations of early deceleration and acceleration are carried out, further, the embodiment of the application can carry out linear transition processing on the speed-limiting sequence.
It should be noted that, in general, in the bending stage, the speed limit value of the future 8s is firstly decreased and then increased, and the speed limit sequence only shows a single trough curve trend. Because the coverage scenes of the automatic driving vehicles are complicated, in some continuous turning scenes, the situation that wave crests and wave troughs appear alternately in the speed limiting sequence of 8s in the future may exist. Fig. 6 shows a typical continuous turning scene, in which the speed limit is [40,38,36,60,35,38,40,60], the minimum speed limit is shown at the 5 th s and the maximum speed is shown at the 4 th s and the 8 th s, considering that the vehicle should not be accelerated or decelerated frequently in a very short time, otherwise the acceleration is large, and the comfort is reduced.
The embodiment of the application can adopt the following measures to avoid the situation that the vehicle is frequently accelerated and decelerated in a very short time:
1) Setting the minimum speed limit value at the t second, neglecting the change condition of any wave crest and wave trough between the 1s to the ts, and completely performing linear reduction;
2) In order to ensure that the speed limit value has enough performance index value in the quadratic programming performance index matrix, the speed limit value of the ts is used no matter how the speed limit from the ts to the 8s is changed, wherein the detailed process of quadratic programming will be described in detail below, and will not be described herein again.
Through the above processing, the speed limit value in fig. 6 is changed to: [40,38,36,35.5,35,35,35,35].
Therefore, the embodiment of the application avoids the frequent acceleration and deceleration of the vehicle in a very short time through a reasonable linear transition strategy, so that the running speed of the vehicle at the curve is more stable, the reasonability and superiority of curve speed limit planning are improved, and the driving experience of a user is greatly improved.
Optionally, in an embodiment of the present application, the target speed cost function is:
wherein f and x are vectors; h is a matrix; omega i A weight representing each cost function;
is an acceleration cost function;
is an acceleration cost function;
is the target speed deviation term.
It should be noted that, in the embodiment of the present application, the quadratic programming algorithm may generate a multi-segment fifth-order polynomial curve with smooth end-to-end transition by solving coefficients of the multi-segment fifth-order polynomial curve to smooth the rough speed sequence generated by dynamic programming, where a general expression of the quadratic programming algorithm is as follows:
in the formula, f, x, b eq Lb and ub are vectors, H, A and A eq Is a matrix.
If a total of 8 sections of the quintic polynomial curves are set, the quadratic programming algorithm needs to solve a solution meeting the lowest condition of the cost function under the condition of meeting the constraint condition, that is, 6 × 8 coefficients need to be solved in total. For the speed planning application scenario, the cost function can be quantitatively expressed from various comfort and smoothness mathematical models, and then the above formula is converted into:
in the formula, ω i The weight of each cost function is expressed, the first term in the middle brackets represents the acceleration cost function, and the second term represents the additionA speed cost function.
It can be understood that in a curve speed limit scene, because the curve speed limit needs to be decelerated in advance, the target speed limit value is not suitable to be used as a constraint condition in the process of deceleration in advance, and if the actual speed of the vehicle is not reduced, the constraint condition is not met, so that the calculation of the quadratic programming algorithm fails. In addition, the current actual speed of the vehicle may exceed the target speed limit, and if the target speed limit is directly used as the constraint condition of the quadratic programming algorithm, the algorithm may cause a drastic increase in the calculation amount of the iteration times due to the fact that the constraint condition is not satisfied, which may lead to problems such as calculation timeout.
Therefore, embodiments of the present application introduce a target speed deviation based on equation (6), as shown below, to reduce the deviation between the planned speed curve and the target speed by taking the curve speed limit as part of the cost function of the quadratic programming algorithm.
The third term cost function is a target speed deviation term, and the specific expression is as follows:
it should be noted that, when the difference between the current actual speed of the vehicle and the target speed limit value is large, the speed deviation term in equation (7) has a large proportion, so that the quadratic programming algorithm is influenced by the speed error term when performing speed sequence smoothing, so that the planned speed sequence satisfies the speed limit value as much as possible, and the vehicle speed is reduced in a relatively flat manner to gradually approach the target speed limit value.
Therefore, the embodiment of the application carries out linear transition on the speed sequence by constructing the target speed cost function of the proper quadratic programming algorithm, so that the smooth speed sequence meeting the vehicle control requirement is planned for the vehicle curve speed limit, the scene universality of the curve speed limit algorithm is improved, and the intelligent level of the vehicle is greatly improved while the vehicle safety is ensured.
The curve speed limiting method of the autonomous vehicle of the present application will be described below with reference to the accompanying drawings.
FIG. 7 is a logic diagram illustrating the implementation of a curve speed limit method for an autonomous vehicle. As shown in fig. 7, the specific steps of executing the curve speed limit of the autonomous vehicle according to the embodiment of the present application are as follows:
s1: calibrating a comfort over-bending reference speedometer;
s2: calculating the curvature radius and the speed limit value of the reference path point;
s3: calculating the position of the future 8s moment based on the uniform acceleration model, and interpolating to obtain a target speed limit value;
s4: comparing the future 8s speed limit value, and judging whether the curve is in or out;
s5: introducing preview time compensation, and decelerating and accelerating in advance;
s6: and performing linear transition processing on the target speed limit sequence.
According to the curve speed-limiting method of the automatic driving vehicle, the curvature radius of each path point is obtained by obtaining the longitudinal accumulated distance and the scattered point curvature radius of each path point of a reference path, and a target speed-limiting value is obtained through a comfort over-bending speed calibration table of the current curve speed-limiting scene; calculating the predicted position of the vehicle in a preset time length based on a preset kinematic model, solving a speed sequence obtained by a target speed limit value, and judging the current intention of the automatic driving vehicle; the method comprises the steps of matching corresponding bend-in preview time or bend-out preview time according to current intentions, determining bend-in deceleration action or bend-out acceleration action, and performing linear transition on a speed sequence through a quadratic programming algorithm to generate a bend speed-limiting control strategy of the automatic driving vehicle.
Next, a curve speed limiting apparatus of an automatically driven vehicle according to an embodiment of the present application will be described with reference to the accompanying drawings.
FIG. 8 is a block schematic diagram of a curve speed limiter of an autonomous vehicle according to an embodiment of the application.
As shown in fig. 8, the curve speed limiter 10 of the autonomous vehicle includes: a calculation module 100, a judgment module 200 and a generation module 300.
The calculation module 100 is configured to obtain a longitudinal accumulated distance of each path point of the reference path, calculate a scatter curvature radius of the reference path, obtain a curvature radius of each path point, and obtain a target speed limit value through a comfort overbending speed calibration table of a current curve speed limit scene.
And the judging module 200 is used for calculating the predicted position of the automatic driving vehicle in the preset time length based on the preset kinematics model, solving the target speed limit value according to the predicted position to obtain a speed sequence, and judging the current intention of the automatic driving vehicle.
The generating module 300 is configured to match a corresponding bend-in preview time or bend-out preview time according to the current intention, determine a bend-in deceleration action or a bend-out acceleration action according to the bend-in preview time or the bend-out preview time, perform linear transition on a speed sequence by using a target speed cost function of a pre-constructed quadratic programming algorithm, and generate a curve speed-limiting control strategy for the autonomous vehicle based on the bend-in deceleration action or the bend-out acceleration action and the speed sequence after the linear transition.
Optionally, in an embodiment of the present application, the generating module 300 includes: and the smoothing unit is used for linearly decreasing all the speed limit values of the speed sequence and using the speed limit values at preset time.
Optionally, in an embodiment of the present application, the target speed cost function is:
wherein f and x are vectors; h is a matrix; omega i A weight representing each cost function;
at a cost of accelerationA function;
is an acceleration cost function;
is the target speed deviation term.
Optionally, in an embodiment of the present application, the determining module 200 includes: the bending device comprises a bending inlet unit and a bending outlet unit.
And the bending entering unit is used for indicating the current intention as the bending entering intention when the minimum speed serial number of the speed sequence is greater than or equal to a first preset serial number.
And the bending-out unit is used for judging that the current intention is a bending-out intention when the minimum speed serial number of the speed sequence is equal to a second preset serial number, wherein the first preset serial number is greater than the second preset serial number.
Optionally, in an embodiment of the present application, the first preset serial number is greater than the second preset serial number.
Optionally, in an embodiment of the present application, the curve speed limiting device 10 of the autonomous vehicle of the embodiment of the present application further includes: the device comprises a first acquisition module and a second acquisition module.
The first acquisition module is used for acquiring lane line data by using a lane-level navigation system before acquiring the longitudinal accumulated distance of each path point of the reference path, and smoothing the lane line data to obtain the reference path. Or,
and the second acquisition module is used for acquiring the lane line image by using the vehicle-mounted camera and fitting the lane line image to obtain a reference path.
It should be noted that the explanation of the embodiment of the curve speed limiting method for an automatically driven vehicle is also applicable to the curve speed limiting device for an automatically driven vehicle of the embodiment, and is not repeated herein.
According to the curve speed limiting device of the automatic driving vehicle, the curvature radius of each path point is obtained by obtaining the longitudinal accumulated distance and the scatter curvature radius of each path point of a reference path, and a target speed limiting value is obtained through a comfort over-bending speed calibration table of a current curve speed limiting scene; calculating the predicted position of the vehicle in a preset time length based on a preset kinematic model, solving a target speed limit value to obtain a speed sequence, and judging the current intention of the automatic driving vehicle; the method comprises the steps of matching corresponding bend-in preview time or bend-out preview time according to current intentions, determining bend-in deceleration action or bend-out acceleration action, and performing linear transition on a speed sequence through a quadratic programming algorithm to generate a bend speed-limiting control strategy of the automatic driving vehicle.
Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
The processor 902, when executing the program, implements the curve speed limit method of the autonomous vehicle provided in the above-described embodiments.
Further, the electronic device further includes:
a communication interface 903 for communication between the memory 901 and the processor 902.
A memory 901 for storing computer programs executable on the processor 902.
If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 9, but that does not indicate only one bus or one type of bus.
Alternatively, in specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated into one chip, the memory 901, the processor 902 and the communication interface 903 may complete mutual communication through an internal interface.
The processor 902 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the curve speed limiting method of an autonomous vehicle as above.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried out in the method of implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer-readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (14)
1. A curve speed limiting method of an automatic driving vehicle is characterized by comprising the following steps:
acquiring a longitudinal accumulated distance of each path point of a reference path, calculating a scatter curvature radius of the reference path to obtain a curvature radius of each path point, and acquiring a target speed limit value through a comfort overbending speed calibration table of a current curve speed limit scene;
calculating the predicted position of the automatic driving vehicle in a preset time length based on a preset kinematic model, solving a target speed limit value according to the predicted position to obtain a speed sequence, and judging the current intention of the automatic driving vehicle;
and matching corresponding bending advance aiming time or bending exit aiming time according to the current intention, determining bending advance deceleration action or bending exit acceleration action according to the bending advance aiming time or the bending exit aiming time, performing linear transition on the speed sequence by utilizing a target speed cost function of a pre-constructed quadratic programming algorithm, and generating a curve speed limit control strategy of the automatic driving vehicle based on the bending advance deceleration action or the bending exit acceleration action and the speed sequence after the linear transition.
2. The method of claim 1, wherein said linearly transitioning said velocity sequence with a target velocity cost function of a pre-constructed quadratic programming algorithm comprises:
and linearly descending all the speed limit values of the speed sequence and continuing to use the speed limit value at the preset moment.
3. The method of claim 1, wherein the target speed cost function is:
wherein f and x are vectors; h is a matrix; omega i A weight representing each cost function;
to accelerateA degree cost function;
is an acceleration cost function;
is the target speed deviation term.
4. The method of claim 1, wherein the determining the current intent of the autonomous vehicle comprises:
when the minimum speed serial number of the speed sequence is greater than or equal to a first preset serial number, the current intention is an intention of bending;
and when the minimum speed serial number of the speed sequence is equal to a second preset serial number, the current intention is an out-of-curve intention.
5. The method of claim 4, wherein the first predetermined sequence number is greater than the second predetermined sequence number.
6. The method of claim 1, further comprising, prior to said obtaining a longitudinal cumulative distance for each waypoint of the reference path:
acquiring lane line data by using a lane level navigation system, and smoothing the lane line data to obtain the reference path;
or acquiring a lane line image by using a vehicle-mounted camera, and fitting the lane line image to obtain the reference path.
7. A curve speed-limiting device of an automatic driving vehicle is characterized by comprising:
the calculation module is used for acquiring the longitudinal accumulated distance of each path point of the reference path, calculating the scatter curvature radius of the reference path to obtain the curvature radius of each path point, and obtaining a target speed limit value through a comfort overbending speed calibration table of the current curve speed limit scene;
the judging module is used for calculating the predicted position of the automatic driving vehicle in the preset time length based on a preset kinematic model, solving a target speed limit value according to the predicted position to obtain a speed sequence and judging the current intention of the automatic driving vehicle;
and the generation module is used for matching corresponding bending advance aiming time or bending advance aiming time according to the current intention, determining bending advance deceleration action or bending exit acceleration action according to the bending advance aiming time or the bending exit aiming time, performing linear transition on the speed sequence by utilizing a target speed cost function of a pre-constructed quadratic programming algorithm, and generating a curve speed limit control strategy of the automatic driving vehicle based on the bending advance deceleration action or the bending exit acceleration action and the speed sequence after the linear transition.
8. The apparatus of claim 7, wherein the generating module comprises:
and the smoothing unit is used for linearly decreasing all the speed limit values of the speed sequence and using the speed limit values at preset time.
9. The apparatus of claim 7, wherein the target speed cost function is:
wherein f and x are vectors; h is a matrix; omega i A weight representing each cost function;
is an acceleration cost function;
is an acceleration cost function;
is the target speed deviation term.
10. The apparatus of claim 7, wherein the determining module comprises:
the bending entering unit is used for determining the current intention as a bending entering intention when the minimum speed serial number of the speed sequence is greater than or equal to a first preset serial number;
and the bending-out unit is used for judging that the current intention is a bending-out intention when the minimum speed serial number of the speed sequence is equal to a second preset serial number.
11. The apparatus of claim 10, wherein the first predetermined sequence number is greater than the second predetermined sequence number.
12. The apparatus of claim 7, further comprising:
a first obtaining module, configured to obtain lane line data by using a lane-level navigation system before obtaining the longitudinal accumulated distance of each path point of the reference path, and perform smoothing processing on the lane line data to obtain the reference path; or,
and the second acquisition module is used for acquiring lane line images by using the vehicle-mounted camera and fitting the lane line images to obtain the reference path.
13. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of curve speed limiting for an autonomous vehicle of any of claims 1-6.
14. A computer-readable storage medium, on which a computer program is stored, the program being executed by a processor for implementing the curve speed limiting method of an autonomous vehicle as recited in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211288424.3A CN115556748A (en) | 2022-10-20 | 2022-10-20 | Method, apparatus, device and storage medium for limiting speed of curve of autonomous vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211288424.3A CN115556748A (en) | 2022-10-20 | 2022-10-20 | Method, apparatus, device and storage medium for limiting speed of curve of autonomous vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115556748A true CN115556748A (en) | 2023-01-03 |
Family
ID=84746804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211288424.3A Pending CN115556748A (en) | 2022-10-20 | 2022-10-20 | Method, apparatus, device and storage medium for limiting speed of curve of autonomous vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115556748A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116215584A (en) * | 2023-05-09 | 2023-06-06 | 智道网联科技(北京)有限公司 | Variable road diameter planning method, device, equipment and storage medium |
-
2022
- 2022-10-20 CN CN202211288424.3A patent/CN115556748A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116215584A (en) * | 2023-05-09 | 2023-06-06 | 智道网联科技(北京)有限公司 | Variable road diameter planning method, device, equipment and storage medium |
| CN116215584B (en) * | 2023-05-09 | 2023-07-21 | 智道网联科技(北京)有限公司 | Variable road diameter planning method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7069103B2 (en) | How to assist a driver, a driver assistance system, and a vehicle equipped with such a driver assistance system | |
| CN103209876B (en) | Vehicle travel controlling apparatus | |
| US9457807B2 (en) | Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver | |
| US9428187B2 (en) | Lane change path planning algorithm for autonomous driving vehicle | |
| CN102458944B (en) | Method and module for determining of velocity reference values for a vehicle control system | |
| CN110262509B (en) | Automatic vehicle driving method and device | |
| US20190367032A1 (en) | Travelling control apparatus | |
| EP4242998A1 (en) | Traffic stream information determination method and apparatus, electronic device and storage medium | |
| CN114987498B (en) | Anthropomorphic trajectory planning method and device for automatic driving vehicle, vehicle and medium | |
| CN109655076B (en) | Vehicle turning speed planning method and device and storage medium | |
| CN115556748A (en) | Method, apparatus, device and storage medium for limiting speed of curve of autonomous vehicle | |
| EP2470406A1 (en) | System and method for maintaining driving times | |
| CN113348121A (en) | Method and control unit for operating an adaptive speed regulator | |
| CN112937584A (en) | Automatic lane changing control method and device and automobile | |
| CN111824167B (en) | Vehicle speed limiting method and device, vehicle and electronic equipment | |
| CN114475607B (en) | Method and device for changing lanes for automatic driving vehicle, vehicle and storage medium | |
| CN115683140A (en) | Method, system, equipment and medium for planning curve passing speed of passenger-riding parking tracking | |
| CN110920622B (en) | Prediction method before vehicle changes lane to target lane in automatic driving | |
| CN114387805A (en) | Intersection passing method and device of vehicle, vehicle and storage medium | |
| CN114620060A (en) | Automatic driving mode selection method, automatic driving automobile and control method thereof | |
| CN114616156A (en) | Determining a discrete representation of a lane section ahead of a vehicle | |
| CN111469841B (en) | Curve target selection method, vehicle-mounted equipment and storage medium | |
| CN116588078B (en) | Vehicle control method, device, electronic equipment and computer readable storage medium | |
| CN113978462B (en) | Main target screening method, track planning method and system of self-adaptive cruise system | |
| JP7275406B1 (en) | Passing point generator |
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 |