CN111591306A - Driving track planning method of automatic driving vehicle, related equipment and storage medium - Google Patents

Driving track planning method of automatic driving vehicle, related equipment and storage medium Download PDF

Info

Publication number
CN111591306A
CN111591306A CN202010237723.9A CN202010237723A CN111591306A CN 111591306 A CN111591306 A CN 111591306A CN 202010237723 A CN202010237723 A CN 202010237723A CN 111591306 A CN111591306 A CN 111591306A
Authority
CN
China
Prior art keywords
vehicle
time
effective
driving
track
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010237723.9A
Other languages
Chinese (zh)
Other versions
CN111591306B (en
Inventor
张子期
邓堃
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Geely Holding Group Co Ltd
Zhejiang Geely Automobile Research Institute Co Ltd
Original Assignee
Zhejiang Geely Holding Group Co Ltd
Zhejiang Geely Automobile Research Institute Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Geely Holding Group Co Ltd, Zhejiang Geely Automobile Research Institute Co Ltd filed Critical Zhejiang Geely Holding Group Co Ltd
Priority to CN202010237723.9A priority Critical patent/CN111591306B/en
Publication of CN111591306A publication Critical patent/CN111591306A/en
Application granted granted Critical
Publication of CN111591306B publication Critical patent/CN111591306B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
    • 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
    • B60W60/0013—Planning or execution of driving tasks specially adapted for occupant comfort
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
    • Y02T10/84—Data processing systems or methods, management, administration

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a driving track planning method of an automatic driving vehicle, related equipment and a storage medium, wherein the driving track planning method comprises the following steps: when a vehicle needs to pass through an intersection provided with a traffic light, acquiring an initial vehicle state of the vehicle at the current moment, a light state of the traffic light, the remaining duration of the light state, a first preset ending vehicle state and a second preset ending vehicle state of the vehicle within a planning time range; determining the effective time of the equivalent barrier corresponding to the traffic light according to the light state and the residual duration of the traffic light; determining effective candidate running tracks corresponding to a first preset ending vehicle state and a second preset ending vehicle state according to the initial vehicle state and the effective time of the equivalent barrier; and selecting the target effective running track with the minimum track cost value from the effective candidate running track set as a planned running track passing through the intersection. The automatic driving vehicle has high driving efficiency and high driving smoothness during driving.

Description

Driving track planning method of automatic driving vehicle, related equipment and storage medium
Technical Field
The present invention relates to the field of automatic driving technologies, and in particular, to a method for planning a driving trajectory of an automatic driving vehicle, a related device, and a storage medium.
Background
With the improvement of the automatic driving function and the safety level, the automatic driving vehicle is required to complete the driving task in a specific scene, and the decision of the automatic driving vehicle is required to be efficient and the driving is smooth. Taking a traffic light (i.e., traffic light) intersection scene as an example, when an automatically-driven vehicle needs to pass through a traffic light intersection, the driving track of the automatically-driven vehicle needs to be planned, in the related technology, when the automatically-driven vehicle plans the driving track of the automatically-driven vehicle passing through the traffic light intersection, the strategy is single, the speed of the automatically-driven vehicle can be roughly reduced by red light and yellow light, and the green light passes through the automatically-driven vehicle at a constant speed.
Disclosure of Invention
In order to solve the problems in the prior art, embodiments of the present invention provide a method for planning a driving trajectory of an autonomous vehicle, a related device, and a storage medium. The technical scheme is as follows:
in one aspect, a method for planning a driving trajectory of an autonomous vehicle is provided, the method comprising:
when an automatic driving vehicle needs to pass through an intersection provided with a traffic light, acquiring an initial vehicle state of the automatic driving vehicle at the current moment, a light state of the traffic light and a remaining duration corresponding to the light state;
acquiring a first preset ending vehicle state and a second preset ending vehicle state of the automatic driving vehicle within a planning time range; the first preset end vehicle state represents a vehicle state when the autonomous vehicle passes through the intersection at the reference passing speed of the intersection, and the second preset end vehicle state represents a vehicle state when the autonomous vehicle stops at a stop line of the intersection;
determining the effective time of the equivalent barrier corresponding to the traffic light according to the light state of the traffic light and the remaining duration corresponding to the light state;
determining a first effective candidate running track corresponding to a first preset ending vehicle state and a second effective candidate running track corresponding to a second preset ending vehicle state in the planning time range according to the initial vehicle state and the effective time of the equivalent obstacle, and obtaining an effective candidate running track set of the automatic driving vehicle;
and selecting a target effective running track with the minimum track cost value from the effective candidate running track set, wherein the target effective running track is used as a planned running track of the automatic driving vehicle passing through the intersection.
In another aspect, there is provided a driving trajectory planning apparatus of an autonomous vehicle, the apparatus including:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring an initial vehicle state of an automatic driving vehicle at the current moment, a lamp state of a traffic lamp and a residual duration corresponding to the lamp state when the automatic driving vehicle needs to pass through an intersection provided with the traffic lamp;
the second acquisition module is used for acquiring a first preset ending vehicle state and a second preset ending vehicle state of the automatic driving vehicle within a planning time range; the first preset end vehicle state represents a vehicle state when the autonomous vehicle passes through the intersection at the reference passing speed of the intersection, and the second preset end vehicle state represents a vehicle state when the autonomous vehicle stops at a stop line of the intersection;
the first determination module is used for determining the effective time of the equivalent barrier corresponding to the traffic light according to the light state of the traffic light and the remaining duration corresponding to the light state;
the second determination module is used for determining a first effective candidate running track corresponding to a first preset ending vehicle state and a second effective candidate running track corresponding to a second preset ending vehicle state in the planning time range according to the initial vehicle state and the effective time of the equivalent obstacle, so as to obtain an effective candidate running track set of the automatic driving vehicle;
and the selection module is used for selecting a target effective running track with the minimum track cost value from the effective candidate running track set, and taking the target effective running track as a planned running track of the automatic driving vehicle passing through the intersection.
Optionally, the first determining module includes:
a first determination submodule for taking the remaining duration as an equivalent obstacle valid time of the traffic light when a light state of the traffic light is a red light;
the second determining submodule is used for determining the effective time of the equivalent barrier of the traffic light according to the remaining duration and the planning termination time corresponding to the planning time when the light state of the traffic light is yellow light;
a third determining submodule for determining a time and a value of the remaining duration and the preset duration of the yellow light when the lamp status of the traffic light is green; and determining the effective time of the equivalent barrier of the traffic light according to the time sum value and the planning termination time corresponding to the planning time.
Optionally, the second determining module includes:
the first generation module is used for generating a fourth-order polynomial function in the planning time range according to the initial vehicle state and a first preset ending vehicle state; the fourth-order polynomial function is a function of displacement and time;
the second generation module is used for generating a plurality of sampling points within the planning time range at preset sampling time intervals according to the fourth-order polynomial function;
the first fitting module is used for fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a first candidate driving track;
a third determining module, configured to determine, according to the first candidate driving trajectory, a first candidate displacement corresponding to a time point within the planned time range;
the third acquisition module is used for acquiring the distance between the automatic driving vehicle and the stop line of the intersection at the current moment;
a fourth determining module, configured to determine a first effective candidate driving trajectory of the first candidate driving trajectories according to a lamp state of the traffic light, an effective time of an equivalent obstacle in the lamp state, the distance, and the first candidate displacement.
Optionally, the second determining module further includes:
the third generation module is used for generating a fifth-order polynomial function in the planning time range according to the initial vehicle state and a second preset ending vehicle state; the quintic polynomial function is a function of displacement and time;
the fourth generation module is used for generating a plurality of sampling points within the effective time of the equivalent barrier at preset sampling time intervals according to the fifth-order polynomial function;
the second fitting module is used for fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a second candidate driving track; the second candidate travel track is taken as the second valid candidate travel track.
Optionally, the apparatus further comprises:
a fifth determining module, configured to determine a driving distance cost value, a longitudinal jerk cost value, and a driving speed deviation cost value corresponding to each effective candidate driving trajectory in the effective candidate driving trajectory set;
a sixth determining module, configured to determine weight coefficients corresponding to the driving distance cost value, the longitudinal jerk cost value, and the driving speed deviation cost value;
a seventh determining module, configured to determine a product of the driving distance cost value, the longitudinal jerk cost value, and the driving speed deviation cost value with a corresponding weight coefficient; and taking the sum of the products as the track cost value of the effective candidate running track.
Optionally, the fifth determining module includes:
a fourth determining submodule, configured to determine, according to each effective candidate driving trajectory, a planned driving displacement and a planned driving speed of the effective candidate driving trajectory at a planning termination time corresponding to the planning time;
a fifth determining submodule, configured to determine a travel distance cost value of the effective candidate travel track according to an inverse of the planned travel displacement;
a sixth determining submodule, configured to determine a driving speed deviation cost value of the effective candidate driving trajectory according to a difference between the planned driving speed and an expected driving speed corresponding to the terminal planning time;
a seventh determining submodule, configured to determine jerks corresponding to the multiple time points in each effective candidate travel track according to each effective candidate travel track;
and the eighth determining submodule is used for determining the mean value of the jerks corresponding to the multiple time points, and taking the mean value of the jerks corresponding to the multiple time points as the longitudinal jerk cost value.
Optionally, the eighth determining sub-module includes:
a first calculation module, configured to calculate a sum of squares of jerks corresponding to the plurality of time points;
the second calculation module is used for calculating the sum of the effective values of the jerk corresponding to the multiple time points;
and the third calculation module is used for dividing the sum of the squares by the sum of the effective values to obtain the average value of the jerks corresponding to the multiple time points.
In another aspect, a driving path planning device for an autonomous vehicle is provided, which includes a processor and a memory, where the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the driving path planning method for the autonomous vehicle.
In another aspect, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the method for planning a driving trajectory of an autonomous vehicle as described above.
When an automatically-driven vehicle needs to pass through an intersection provided with a traffic light, the embodiment of the invention obtains the initial vehicle state, the light state of the traffic light, the remaining duration corresponding to the light state, and the first preset ending vehicle state and the second preset ending vehicle state within the planning time range of the automatically-driven vehicle at the current moment, determines the effective time of an equivalent obstacle corresponding to the traffic light based on the light state of the traffic light and the corresponding remaining duration, further determines an effective candidate driving track set corresponding to the first preset ending vehicle state and the second preset ending vehicle state according to the initial vehicle state and the effective time of the equivalent obstacle, and obtains the effective candidate driving track with the minimum track cost value as the planning driving track of the automatically-driven vehicle passing through the traffic light intersection, so that when the automatically-driven vehicle needs to pass through the traffic light intersection, the vehicle has high driving efficiency, greatly improves the driving smoothness and has higher riding comfort.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for planning a driving track of an autonomous vehicle according to an embodiment of the present invention;
FIG. 2a is a schematic diagram of a Cartesian coordinate system and a Frenet coordinate system according to an embodiment of the present invention; FIG. 2b is another schematic diagram of a Cartesian coordinate system and a Frenet coordinate system according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart diagram illustrating a method for determining a first valid candidate travel track corresponding to a first default ending vehicle state within a planned time range based on an initial vehicle state and an equivalent obstacle validity time according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart diagram illustrating a method for determining a second valid candidate travel track corresponding to a second predetermined end vehicle state within the planned time range based on the initial vehicle state and the equivalent obstacle valid time according to an embodiment of the present invention;
fig. 5 is a schematic view of a part of effective candidate driving trajectories in an effective candidate driving trajectory set planned when a traffic light at the current time is a red light according to an embodiment of the present invention;
fig. 6 is a schematic view of a part of effective candidate driving trajectories in an effective candidate driving trajectory set planned when a traffic light at the current time is a green light/yellow light according to an embodiment of the present invention;
fig. 7a, 7b, 8a, 8b, 9a and 9b are simulation result diagrams for simulation by using the method for planning the driving trajectory of the autonomous vehicle according to the embodiment of the present invention;
fig. 10 is a schematic structural diagram of a travel track planning apparatus for an autonomous vehicle according to an embodiment of the present invention;
fig. 11 is a block diagram of a hardware structure of a travel track planning apparatus for an autonomous vehicle according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, which is a schematic flow chart illustrating a method for planning a driving trajectory of an autonomous vehicle according to an embodiment of the present invention, it should be noted that the present specification provides the method operation steps as described in the embodiment or the flow chart, but more or less operation steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In actual system or product execution, sequential execution or parallel execution (e.g., parallel processor or multi-threaded environment) may be possible according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 1, the method may include:
s101, when an automatic driving vehicle needs to pass through an intersection provided with a traffic light, acquiring an initial vehicle state of the automatic driving vehicle at the current moment, a light state of the traffic light and a remaining duration corresponding to the light state.
In the embodiment of the present specification, when it is detected that the autonomous vehicle is driven into the intersection monitoring range, it is possible to communicate with the detected autonomous vehicle by the V2X technique.
V2X is intended to mean vehicle to evolution, i.e. including vehicle-to-vehicle information interaction, and also including information interaction outside the fleet. The Internet of vehicles establishes a new automobile technology development direction by integrating a Global Positioning System (GPS) navigation technology, an automobile-to-automobile communication technology, a wireless communication technology and a remote sensing technology, and realizes the compatibility of manual driving and automatic driving.
In practical application, the V2X communication system adopting the V2X technology is divided into two parts, namely hardware and software. The hardware aspect comprises road side devices (including road side sensing devices and road side V2X communication devices) arranged at various positions of the intersection, and the automatic driving vehicle is also provided with an on-board V2X communication device. In the aspect of software, the cloud computing server establishes communication with the automatic driving vehicles within the range of the intersection.
In this embodiment, the light state of the traffic light and the remaining duration corresponding to the light state may be obtained by the roadside sensing device, and the distance between the autonomous vehicle and the stop line of the intersection may also be obtained by the roadside sensing device, where the light state of the traffic light may include a green light, a yellow light, and a red light, and the traffic light is transformed into a green light-yellow light-red light-green light-yellow light-red light … …, each light state has a preset duration, for example, the preset duration of the green light is 10 seconds, the preset duration of the yellow light is 3 seconds, the duration of the red light is 8 seconds, and the remaining duration is the remaining duration of the traffic light in a certain light state at the current time.
In the embodiment of the present specification, the vehicle state at the present time, that is, the initial vehicle state may be acquired by a plurality of sensors provided in the autonomous vehicle. The vehicle state can be characterized by three parameters of displacement, speed and acceleration, and therefore, the initial vehicle state can be characterized by the displacement at the current moment, the speed at the current moment and the acceleration at the current moment.
It should be noted that the planned driving track in the embodiment of the present specification is a longitudinal driving track of the autonomous vehicle in a Frenet coordinate system, that is, a curve in which a longitudinal displacement s changes with time t is planned, so that when the autonomous vehicle drives along the curve, not only can the traffic rules be met, but also the driving efficiency and the driving smoothness can be improved. Therefore, in the embodiments of the present description, the displacement characterizing the vehicle state is the longitudinal displacement, the speed is the longitudinal speed, and the acceleration is the longitudinal acceleration, that is, the vehicle state is represented by
Figure BDA0002431555960000081
Composition, where s denotes the longitudinal displacement,
Figure BDA0002431555960000082
the speed in the longitudinal direction is indicated,
Figure BDA0002431555960000083
indicating the longitudinal acceleration.
The Frenet coordinate system is a more intuitive way of representing road locations than the traditional Cartesian coordinates (x, y). In the Frenet coordinate system, the position of the vehicle on the road is described using the variables s and d. The s-coordinate represents the distance along the road (reference line) (also referred to as longitudinal displacement) and the d-coordinate represents the left and right position on the road (also referred to as lateral displacement), as shown in fig. 2 a. Under the Frenet coordinate system, the two-dimensional motion problem of the vehicle can be decoupled into two one-dimensional motion problems. A curved road (reference line) in cartesian coordinate system is a straight line in Frenet coordinate system, as shown in fig. 2 b.
An autonomous vehicle refers to a vehicle that may be configured to be in an autonomous driving mode in which the vehicle navigates through the environment with little or no input from the driver. Such autonomous vehicles may include a sensor system having one or more sensors, such as speed sensors, acceleration sensors, etc., configured to detect information related to the environment in which the vehicle is traveling.
S103, acquiring a first preset ending vehicle state and a second preset ending vehicle state of the automatic driving vehicle within a planning time range.
Wherein the first preset ending vehicle state represents a vehicle state when the autonomous vehicle passes the intersection at the reference passing speed of the intersection, and the second preset ending vehicle state represents a vehicle state when the autonomous vehicle stops at a stop line of the intersection.
In the embodiment of the description, when the automatic driving vehicle needs to pass through the intersection of the traffic light, two decisions exist, namely, stopping the vehicle at the intersection and stopping the vehicle at the intersection, so that the longitudinal driving tracks corresponding to the two decisions, namely the longitudinal driving track passing through the intersection and the longitudinal driving track stopping at the intersection, are considered simultaneously when the driving track planning is carried out. Wherein the first predetermined end vehicle state corresponds to a final vehicle state of the autonomous vehicle within a planned time range when planning a longitudinal travel trajectory through the intersection. The second predetermined end vehicle state corresponds to a final vehicle state of the autonomous vehicle within the planned time frame when the longitudinal travel trajectory is planned to stop at the intersection.
In particular implementations, the first predetermined end vehicle state can be determined based on the autonomous vehicle passing through the intersection at a uniform speed at a reference passing speed of the intersection, and can be characterized as being
Figure BDA0002431555960000091
Wherein, statefinalIndicating a first preset end vehicle state; underdefined means that there is no limit to the longitudinal displacement of the final state of the autonomous vehicle within the planned time frame;
Figure BDA0002431555960000092
represents the longitudinal speed of the final state of the autonomous vehicle within the planned time frame, and
Figure BDA0002431555960000093
vrefthe reference passing speed, which indicates the intersection, can be, for example, 5m/s cruise speed,
Figure BDA0002431555960000094
the maximum passing speed of the intersection is the maximum passing speed of the intersection,
Figure BDA0002431555960000095
the minimum passing speed of the intersection, and the delta v is the speed step length; 0 means that the acceleration of the final state of the autonomous vehicle is 0 in the planned time frame.
The second predetermined end vehicle state represents a vehicle state when the autonomous vehicle stops at the stop line of the intersection, i.e., the traffic light is in the red light state at the time when the autonomous vehicle reaches the stop line, and thus the second predetermined end vehicle state can be characterized as a statefinal＝[sstopline,0,0]Wherein, statefinalIndicating the end of the second presetA vehicle state; sstoplineRepresenting a distance between the autonomous vehicle and a stop-line of the intersection; the longitudinal speed of the autonomous vehicle in the second preset end vehicle state is 0 and the longitudinal acceleration is 0.
The planned time refers to a future time period taking the current time as the starting time, namely the planned driving track is a longitudinal driving track of the automatic driving vehicle in the future time period. In practical applications, the planning time may be set as required, for example, 8 seconds.
S105, determining the effective time of the equivalent barrier corresponding to the traffic light according to the lamp state of the traffic light and the remaining duration corresponding to the lamp state.
In practical applications, the intersection does not allow passage when the lamp status of the traffic light is red, so the traffic light at red can be equivalent to an obstacle. If the lamp state of the traffic light at the current moment is red, the remaining duration time of the red light can be directly used as the effective time of the equivalent barrier of the traffic light, namely the effective time of the equivalent barrier
Figure BDA0002431555960000101
Wherein the content of the first and second substances,
Figure BDA0002431555960000102
the remaining duration of the red light.
When the traffic light is in a green light state and a yellow light state, the intersection is allowed to pass through, equivalent obstacles do not exist in the duration time of the green light and the yellow light, in order to ensure continuity, in the embodiment of the description, the remaining duration corresponding to the green light is the sum of the actual remaining duration of the green light and the preset duration of the yellow light, the remaining duration corresponding to the yellow light is the actual remaining duration of the yellow light, and the traffic light enters the red light state after the yellow light is finished, and the obstacles are not allowed to pass through and are equivalent. Therefore, if the lamp state of the traffic light at the current moment is yellow, the effective time of the equivalent barrier of the traffic light, namely the effective time of the equivalent barrier can be determined according to the remaining duration and the end planning moment corresponding to the planning time
Figure BDA0002431555960000103
Wherein the content of the first and second substances,
Figure BDA0002431555960000104
the remaining duration of the yellow light, tmaxFor the end of the planning time, tmaxWhich can be understood as the longest time for planning the trajectory. If the lamp state of the traffic light at the current moment is green, the time and the value of the residual duration of the green lamp and the preset duration of the yellow lamp can be determined firstly, and then the effective time of the equivalent barrier of the traffic light, namely the effective time of the equivalent barrier, is determined according to the ending planning moment corresponding to the time and the value and the planning time
Figure BDA0002431555960000105
Figure BDA0002431555960000111
Wherein the content of the first and second substances,
Figure BDA0002431555960000112
the remaining duration of the green light, tYA preset duration of yellow light.
S107, according to the initial vehicle state and the effective time of the equivalent obstacle, determining a first effective candidate running track corresponding to a first preset ending vehicle state and a second effective candidate running track corresponding to a second preset ending vehicle state in the planning time range, and obtaining an effective candidate running track set of the automatic driving vehicle.
The embodiment of the specification passes through a group of [ state ]init,statefinal,T]To determine an effective candidate trajectory. Wherein, stateinitIndicating an initial vehicle state, of the autonomous vehiclefinalA first preset ending vehicle state and a second preset ending vehicle state included in the foregoing of the embodiments of the present specification; t represents the slave state of the automatic driving vehicleinitGo to statefinalTime spent, when statefinalAt the first preset end vehicle state, T ∈{tmin+n·Δt|n＝0,1,2,…,N}∩[tmin,tmax]When statefinalAt a second predetermined end vehicle state, T ∈ { Tmin+n·Δt|n＝0,1,2,…,N}∩TvalidWherein, tminRepresenting the shortest time for planning the trajectory.
As an alternative embodiment, the method in fig. 3 may be adopted to determine a first valid candidate driving trajectory corresponding to a first preset ending vehicle state within the planning time range according to the initial vehicle state and the effective time of the equivalent obstacle, and includes:
s301, generating a fourth-order polynomial function in the planning time range according to the initial vehicle state and the first preset ending vehicle state.
Wherein the fourth order polynomial function is a function of displacement (longitudinal displacement) and time. For example, the fourth order polynomial function is generated as s (t) ═ a0+a1t1+a2t2+a3t3+a4t4Wherein a is0,a1,a2,a3,a4Is a polynomial coefficient, and t represents time. How to determine the polynomial coefficient a from the initial vehicle state and the first predetermined end vehicle state is explained below0,a1,a2,a3,a4. The expressions of the first derivative (velocity) and the second derivative (acceleration) corresponding to the fourth-order polynomial are respectively:
Figure BDA0002431555960000114
Figure BDA0002431555960000113
assuming that the time T corresponding to the initial vehicle state is 0, and the time T corresponding to the first preset ending vehicle state is T, it can be obtained that:
Figure BDA0002431555960000121
Figure BDA0002431555960000122
wherein the content of the first and second substances,
Figure BDA0002431555960000123
the initial vehicle state is known and the first predetermined end vehicle state is described previously in this specification, wherein,
Figure BDA0002431555960000124
T∈{tmin+n·Δt|n＝0,1,2,…,N}∩[tmin,tmax]so that the polynomial coefficient a can be solved from the above 5 independent equations0,a1,a2,a3,a4And further obtaining a fourth-order polynomial function in the planning time range.
And S303, generating a plurality of sampling points in the planning time range at preset sampling time intervals according to the fourth-order polynomial function.
The preset sampling time interval may be a minimum time step, the minimum time step may be set according to actual needs, for example, 0.1 second, and then a plurality of sampling points may be determined within the effective time of the equivalent obstacle according to a fourth-order polynomial function s (t), and each sampling point may include a sampling time within the effective time of the equivalent obstacle and a longitudinal displacement corresponding to each sampling time.
S305, fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a first candidate running track.
It will be appreciated that the final speed of the vehicle is in the interval since in the first preset end vehicle state
Figure BDA0002431555960000125
Internal values, so the first preset end vehicle state is actually a set
Figure BDA0002431555960000126
And T is also a set{T1,T2,…,TmAnd obtaining a plurality of candidate running tracks by the first driving unit.
S307, determining a first candidate displacement corresponding to the time point in the planning time range according to the first candidate driving track.
S309, obtaining the distance between the automatic driving vehicle and the stop line of the intersection at the current moment.
The current time can be understood as the initial time of the planning.
S311, determining a first effective candidate running track in the first candidate running tracks according to the lamp state of the traffic lamp, the effective time of the equivalent obstacle in the lamp state, the distance and the first candidate displacement.
In the embodiment of the present specification, for safety reasons, after the first candidate driving trajectory is determined, the first candidate driving trajectory needs to be screened to exclude the driving trajectory passing through the intersection during the red light period, the specific screening method is the above steps S307 to S311, and the remaining first candidate driving trajectory is the first valid candidate driving trajectory that can pass through the intersection legally.
Specifically, step S311 may include, when executed:
when the lamp state of the traffic light is red, the effective time of the equivalent barrier is
Figure BDA0002431555960000131
Then judge
Figure BDA0002431555960000132
And if the judgment result is negative, the corresponding first candidate running track can be considered as a first effective candidate running track.
When the lamp state of the traffic light is green light or yellow light, the effective time of the equivalent barrier is
Figure BDA0002431555960000133
Figure BDA0002431555960000134
tmax]Then first of all judge
Figure BDA0002431555960000135
Whether the first candidate displacement corresponding to the time point in the range is smaller than the distance between the automatic driving vehicle and the stop line of the intersection at the initial moment or not can be judged, when the judgment result is negative, the first candidate driving track corresponding to the first candidate displacement can be determined to be an effective candidate driving track, and when the judgment result is positive, the judgment is further carried out
Figure BDA0002431555960000136
And if the judgment result is negative, the first candidate running track corresponding to the first candidate displacement can be determined to be an effective candidate running track.
As an optional implementation, determining a second valid candidate driving trajectory corresponding to a second preset ending vehicle state within the planning time range according to the initial vehicle state and the equivalent obstacle valid time may adopt the method in fig. 4, including:
s401, generating a fifth-order polynomial function in the planning time range according to the initial vehicle state and a second preset ending vehicle state.
Wherein the fifth order polynomial function is a function of displacement (i.e., longitudinal displacement) and time.
In the embodiment of the present specification, in order to make the planned driving trajectory have good smoothness, a fifth-order polynomial is used to describe the driving trajectory in the second predetermined end vehicle state.
Specifically, the generated fifth-order polynomial function may be s (t) ═ a0+a1t1+a2t2+a3t3+a4t4+a5t5Wherein a is0,a1,a2,a3,a4,a5Is a polynomial coefficient, and t represents time. How to determine the polynomial coefficient a from the initial vehicle state and the second predetermined end vehicle state is explained below0,a1,a2,a3,a4,a5. The expressions of the first derivative (velocity) and the second derivative (acceleration) corresponding to the fifth-order polynomial are respectively:
Figure BDA0002431555960000145
Figure BDA0002431555960000146
assuming that the time T corresponding to the initial vehicle state is 0, and the time T corresponding to the second preset ending vehicle state is T, it can be obtained that:
Figure BDA0002431555960000141
Figure BDA0002431555960000142
wherein the content of the first and second substances,
Figure BDA0002431555960000143
the initial vehicle state is known and the second predetermined end vehicle state is described previously in this specification, where s isfinal＝sstopline，
Figure BDA0002431555960000144
T∈{tmin+n·Δt|n＝0,1,2,…,N}∩TvalidSo that the polynomial coefficient a can be solved from the above 6 independent equations0,a1,a2,a3,a4,a5And further obtaining a fifth-order polynomial function in the planning time range.
And S403, generating a plurality of sampling points within the effective time of the equivalent obstacle at preset sampling time intervals according to the fifth-order polynomial function.
The preset sampling time interval may be a minimum time step, the minimum time step may be set according to actual needs, for example, 0.1 second, and then a plurality of sampling points may be determined within the effective time of the equivalent obstacle according to a fourth-order polynomial function s (t), and each sampling point may include a sampling time within the effective time of the equivalent obstacle and a longitudinal displacement corresponding to each sampling time.
S405, fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a second candidate running track; the second candidate travel track is taken as the second valid candidate travel track.
In the embodiment of the present specification, the first valid candidate travel track and the second valid candidate travel track described above constitute a valid candidate travel track set within a planned time range.
Referring to fig. 5 and 6, fig. 5 shows a part of the effective candidate driving trajectories in the set of effective candidate driving trajectories planned when the traffic light at the current time is red light, and fig. 6 shows a part of the effective candidate driving trajectories in the set of effective candidate driving trajectories planned when the traffic light at the current time is green light/yellow light.
S109, selecting a target effective running track with the minimum track cost value from the effective candidate running track set, wherein the target effective running track is used as a planned running track of the automatic driving vehicle passing through the intersection.
In practical applications, a step of calculating a track cost value of each effective candidate traveling track in the effective candidate traveling track set may be further included before step S109. In the embodiment of the present description, the cost of each effective candidate driving track is comprehensively evaluated from three aspects of driving efficiency, smoothness and legality, specifically, a driving distance cost value is used for characterizing driving efficiency, a longitudinal jerk cost value is used for characterizing driving smoothness, and a driving speed deviation cost value is used for characterizing driving legality, and then calculating the track cost values of the effective candidate driving tracks may include:
(1) and determining a driving distance cost value, a longitudinal acceleration cost value and a driving speed deviation cost value corresponding to each effective candidate driving track in the effective candidate driving track set.
Specifically, according to each effective candidate running track, a planned running displacement s and a planned running speed v of the effective candidate running track at a planning termination time (i.e., a maximum planning time) corresponding to the planning time can be determined; wherein the planned driving displacement s is a longitudinal displacement, and the planned driving speed v is a longitudinal speed.
Determining a travel distance cost value of the effective candidate travel track according to the reciprocal of the planned travel displacement; in particular, the travel distance cost value CsThe following formula can be used for calculation:
Figure BDA0002431555960000151
it can be seen that the farther the planned travel displacement s is, the travel distance cost value CsThe smaller the distance, the more the vehicle is encouraged to travel in the same time, and the travel efficiency is improved.
According to the planned driving speed v and the expected driving speed v corresponding to the end planning timerefDetermining a travel speed deviation cost value of the effective candidate travel track; in particular, the running speed deviation cost value CvThe following formula can be used for calculation:
Cv＝(v-vref)2
v represents the final state speed of the planned driving trajectory, vrefThe final state speed, v, representing the desired driving trajectoryrefGenerally, the recommended speed of the automatically driven vehicle passing through the intersection is obtained, and the final state speed of the planned driving track should be as close as possible to the recommended speed in terms of safety and legality.
Since jerk may be used as an indicator of ride comfort, the average jerk in the embodiments of the present disclosure is used to equate the cost of longitudinal jerk, i.e., based on each available candidate railDetermining jerks corresponding to a plurality of time points in the effective candidate driving track; and determining the average value of the jerks corresponding to the multiple time points, and taking the average value of the jerks corresponding to the multiple time points as the longitudinal jerk cost value. When determining the average value of the jerks corresponding to the multiple time points, the sum of the squares of the jerks corresponding to the multiple time points may be calculated, then the sum of the effective values of the jerks corresponding to the multiple time points may be calculated, and finally the sum of the squares may be divided by the sum of the effective values, thereby obtaining the average value of the jerks corresponding to the multiple times. In particular, longitudinal jerk cost value CjThe following formula can be used for calculation:
Figure BDA0002431555960000161
wherein the content of the first and second substances,
Figure BDA0002431555960000162
is the jerk at which the autonomous vehicle travels along the valid candidate travel trajectory,
Figure BDA0002431555960000163
is the effective value of jerk.
(2) And determining weight coefficients corresponding to the driving distance cost value, the longitudinal acceleration cost value and the driving speed deviation cost value.
In particular, the travel distance cost value CsLongitudinal jerk cost value CjAnd running speed deviation cost value CvCorresponding weighting system Ks,Kj,KvCan be set and adjusted according to actual needs, for example, K can be sets＝10,Kj＝0.1,Kv＝1。
(3) And determining the product of the driving distance cost value, the longitudinal acceleration cost value and the driving speed deviation cost value with the corresponding weight coefficient.
(4) And taking the sum of the products as the track cost value of the effective candidate running track.
That is to sayTrajectory cost value C of effective candidate travel trajectorytotalThe following formula can be used for calculation:
Ctotal＝KsCs+KjCj+KvCv
after the track cost values of the effective candidate running tracks in the effective candidate running track set are obtained, the effective candidate running track with the minimum track cost value, namely the target effective running track, can be selected, and the target effective running track is used as a planned running track of the automatic driving vehicle passing through the traffic light intersection.
Considering that the actual road has a limitation on the vehicle speed, and the acceleration or deceleration and the turning curvature of the autonomous vehicle are limited by the mechanical performance of the autonomous vehicle and the road condition, as an optional implementation manner, before step S109 is executed, a preliminary screening may be performed on the valid candidate driving trajectory set, specifically, when the valid candidate driving trajectory satisfies any one of the preliminary screening conditions, the valid candidate driving trajectory is deleted from the valid candidate driving trajectory set. Wherein, the preliminary screening conditions may include: the running speed determined according to the effective candidate running track is greater than a preset speed threshold (for example, 50 km/h); the absolute value of the acceleration/deceleration determined from the valid candidate travel path is greater than a preset acceleration/deceleration threshold (e.g., 4 m/s)2) (ii) a The turning curvature determined from the valid candidate travel path is greater than a preset curvature threshold (e.g., 1 m)-1). Subsequently, when step S109 is executed, a target effective travel track with the smallest track cost value is selected from the set of effective candidate travel tracks after the preliminary screening. It can be understood that, in order to improve the decision efficiency, only the effective candidate driving track set after the preliminary screening may be calculated when calculating the track cost value.
According to the technical scheme of the embodiment of the invention, when the driving track of the automatic driving vehicle is planned, the lamp state of the traffic light and the corresponding residual duration are considered, and the effective time of the equivalent barrier corresponding to the traffic light is determined based on the residual duration, so that the obtained planned driving track is a track which accords with traffic rules, is efficient to drive and has high smoothness, and the automatic driving vehicle has high driving efficiency, greatly improves the smoothness of driving and has high riding comfort when passing through a traffic light intersection according to the planned driving track.
In addition, the embodiment of the invention considers the cost of the driving efficiency, the cost of the smoothness and the cost of the legality when determining the track cost value, further improves the legality, the driving efficiency and the smoothness of the planned driving track, and further improves the driving efficiency and the smoothness of the automatic driving vehicle.
Referring to fig. 7a, fig. 7b, fig. 8a, fig. 8b, fig. 9a and fig. 9b, a simulation result diagram of a simulation performed by the method for planning a driving trajectory of an autonomous vehicle according to an embodiment of the present invention is shown. Wherein, the simulation scenario corresponding to the simulation result diagram of fig. 7a is g5v1d 50; the simulation scenario corresponding to the simulation result diagram of fig. 7b is g10v10d 50; the simulation scenario corresponding to the simulation result diagram of fig. 8a is y3v1d 50; the simulation scenario corresponding to the simulation result diagram of fig. 8b is y3v10d 50; the simulation scenario corresponding to the simulation result diagram of fig. 9a is r5v1d 50; the simulation scenario corresponding to the simulation result diagram of fig. 9b is r15v10d 50.
The naming mode of the simulation scene is r/g/yXvXdX, and the r/g/yX respectively indicates that the remaining time of the red light, the green light and the yellow light at the initial moment is X seconds; vX represents that the speed of the automatic driving vehicle at the current moment is X meters per second; dX represents the distance between the autonomous vehicle and the stop line of the intersection at the present time. And t in the simulationmaxThe setting is 8 seconds, the cruising speed is set as the recommended speed of the intersection of 5m/s, and the distance between the stop line of the intersection and the traffic light of the intersection is set as 5.5 meters.
Fig. 7a and 7b include a lamp state diagram of a traffic light, a speed diagram of an autonomous vehicle, and a distance diagram between the autonomous vehicle and the traffic light at an intersection in order from top to bottom. In fig. 7a, the speed of the autonomous vehicle at the current time is smaller than 1m/s, the remaining duration of the green light is 5 seconds, and the autonomous vehicle first accelerates and then decelerates to a stop line when traveling according to the planned travel trajectory; in fig. 7b, the speed of the autonomous vehicle at the current moment is 10m/s, the remaining duration of the green light is 10 seconds, and the autonomous vehicle passes through the intersection at the recommended speed (5m/s) of the intersection when traveling according to the planned travel track.
Wherein, fig. 8a and 8b include a traffic light state diagram, an autonomous vehicle speed diagram, and a distance diagram between an autonomous vehicle and a traffic light at an intersection in order from top to bottom. In fig. 8a, the speed of the autonomous vehicle at the current time is smaller than 1m/s, the remaining duration of the yellow light is 3 seconds, and the autonomous vehicle first accelerates and then decelerates to a stop line when traveling according to the planned travel trajectory; in fig. 8b the speed of the autonomous vehicle at the present moment is 10m/s and the remaining duration of the yellow light is 3 seconds, the autonomous vehicle decelerates to a stop-line while driving according to the planned driving trajectory.
Fig. 9a and 9b include a traffic light state diagram, an autonomous vehicle speed diagram, and an autonomous vehicle-to-traffic light distance diagram in this order from top to bottom. In fig. 9a, the speed of the autonomous vehicle at the current time is smaller than 1m/s, the remaining duration of the red light is 5 seconds, and the autonomous vehicle accelerates to the recommended speed of the intersection before passing through the intersection when traveling according to the planned travel track; in fig. 9b, the speed of the autonomous vehicle at the current time is 10m/s, the remaining duration of the red light is 10 seconds, the autonomous vehicle decelerates to stop to the stop line when traveling according to the planned travel trajectory, and accelerates again through the intersection when the light is green.
Corresponding to the travel track planning methods of the autonomous vehicles provided in the above embodiments, embodiments of the present invention further provide a travel track planning apparatus of an autonomous vehicle, and since the travel track planning apparatus of an autonomous vehicle provided in embodiments of the present invention corresponds to the travel track planning methods of the autonomous vehicles provided in the above embodiments, embodiments of the travel track planning method of an autonomous vehicle described above are also applicable to the travel track planning apparatus of an autonomous vehicle provided in this embodiment, and are not described in detail in this embodiment.
Referring to fig. 10, a schematic structural diagram of a driving trajectory planning apparatus for an autonomous vehicle according to an embodiment of the present invention is shown, and as shown in fig. 10, the apparatus may include:
a first obtaining module 1010, configured to obtain an initial vehicle state of an autonomous vehicle at a current time, a light state of a traffic light, and a remaining duration corresponding to the light state when the autonomous vehicle needs to pass through an intersection provided with the traffic light;
a second obtaining module 1020, configured to obtain a first preset ending vehicle state and a second preset ending vehicle state of the autonomous vehicle within a planned time range; the first preset end vehicle state represents a vehicle state when the autonomous vehicle passes through the intersection at the reference passing speed of the intersection, and the second preset end vehicle state represents a vehicle state when the autonomous vehicle stops at a stop line of the intersection;
a first determining module 1030, configured to determine an effective time of an equivalent obstacle corresponding to the traffic light according to a light state of the traffic light and a remaining duration corresponding to the light state;
a second determining module 1040, configured to determine, according to the initial vehicle state and the effective time of the equivalent obstacle, a first effective candidate driving trajectory corresponding to a first preset ending vehicle state and a second effective candidate driving trajectory corresponding to a second preset ending vehicle state within the planning time range, so as to obtain an effective candidate driving trajectory set of the autonomous vehicle;
a selecting module 1050, configured to select a target effective driving track with a smallest track cost value from the effective candidate driving track set, and use the target effective driving track as a planned driving track of the autonomous vehicle passing through the intersection.
As an optional implementation, the first determining module 1030 may include:
a first determination submodule for taking the remaining duration as an equivalent obstacle valid time of the traffic light when a light state of the traffic light is a red light;
the second determining submodule is used for determining the effective time of the equivalent barrier of the traffic light according to the remaining duration and the planning termination time corresponding to the planning time when the light state of the traffic light is yellow light;
a third determining submodule for determining a time and a value of the remaining duration and the preset duration of the yellow light when the lamp status of the traffic light is green; and determining the effective time of the equivalent barrier of the traffic light according to the time sum value and the planning termination time corresponding to the planning time.
As an optional implementation, the second determining module 1040 may include:
the first generation module is used for generating a fourth-order polynomial function in the planning time range according to the initial vehicle state and a first preset ending vehicle state; the fourth-order polynomial function is a function of displacement and time;
the second generation module is used for generating a plurality of sampling points within the planning time range at preset sampling time intervals according to the fourth-order polynomial function;
the first fitting module is used for fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a first candidate driving track;
a third determining module, configured to determine, according to the first candidate driving trajectory, a first candidate displacement corresponding to a time point within the planned time range;
the third acquisition module is used for acquiring the distance between the automatic driving vehicle and the stop line of the intersection at the current moment;
a fourth determining module, configured to determine a first effective candidate driving trajectory of the first candidate driving trajectories according to a lamp state of the traffic light, an effective time of an equivalent obstacle in the lamp state, the distance, and the first candidate displacement.
As an optional implementation, the second determining module 1040 may further include:
the third generation module is used for generating a fifth-order polynomial function in the planning time range according to the initial vehicle state and a second preset ending vehicle state; the quintic polynomial function is a function of displacement and time;
the fourth generation module is used for generating a plurality of sampling points within the effective time of the equivalent barrier at preset sampling time intervals according to the fifth-order polynomial function;
the second fitting module is used for fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a second candidate driving track; the second candidate travel track is taken as the second valid candidate travel track.
As an optional embodiment, the driving path planning apparatus of the autonomous vehicle may further include:
a fifth determining module, configured to determine a driving distance cost value, a longitudinal jerk cost value, and a driving speed deviation cost value corresponding to each effective candidate driving trajectory in the effective candidate driving trajectory set;
a sixth determining module, configured to determine weight coefficients corresponding to the driving distance cost value, the longitudinal jerk cost value, and the driving speed deviation cost value;
a seventh determining module, configured to determine a product of the driving distance cost value, the longitudinal jerk cost value, and the driving speed deviation cost value with a corresponding weight coefficient; and taking the sum of the products as the track cost value of the effective candidate running track.
As an optional implementation, the fifth determining module may include:
a fourth determining submodule, configured to determine, according to each effective candidate driving trajectory, a planned driving displacement and a planned driving speed of the effective candidate driving trajectory at a planning termination time corresponding to the planning time;
a fifth determining submodule, configured to determine a travel distance cost value of the effective candidate travel track according to an inverse of the planned travel displacement;
a sixth determining submodule, configured to determine a driving speed deviation cost value of the effective candidate driving trajectory according to a difference between the planned driving speed and an expected driving speed corresponding to the terminal planning time;
a seventh determining submodule, configured to determine jerks corresponding to the multiple time points in each effective candidate travel track according to each effective candidate travel track;
and the eighth determining submodule is used for determining the mean value of the jerks corresponding to the multiple time points, and taking the mean value of the jerks corresponding to the multiple time points as the longitudinal jerk cost value.
As an optional implementation, the eighth determining sub-module may include:
a first calculation module, configured to calculate a sum of squares of jerks corresponding to the plurality of time points;
the second calculation module is used for calculating the sum of the effective values of the jerk corresponding to the multiple time points;
and the third calculation module is used for dividing the sum of the squares by the sum of the effective values to obtain the average value of the jerks corresponding to the multiple time points.
It should be noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.
The travel track planning device of the automatic acceleration vehicle in the embodiment of the invention considers the lamp state of the traffic light and the corresponding remaining duration time when planning the travel track of the automatic driving vehicle, and determines the effective time of the equivalent barrier corresponding to the traffic light based on the remaining duration time, so that the obtained planned travel track is a track which accords with traffic rules, is high in travel efficiency and smoothness, and the automatic driving vehicle has high travel efficiency, greatly improves the travel smoothness and has high riding comfort when passing through a traffic light intersection according to the planned travel track.
In addition, the embodiment of the invention considers the cost of the driving efficiency, the cost of the smoothness and the cost of the legality when determining the track cost value, further improves the legality, the driving efficiency and the smoothness of the planned driving track, and further improves the driving efficiency and the smoothness of the automatic driving vehicle. .
The embodiment of the invention provides a driving track planning device of an automatic driving vehicle, which comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to realize the driving track planning method of the automatic driving vehicle provided by the embodiment of the method.
The memory may be used to store software programs and modules, and the processor may execute various functional applications and travel path planning by executing the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.
The method provided by the embodiment of the invention can be executed in a computer terminal, a vehicle-mounted terminal, a server or a similar operation device. Fig. 11 is a block diagram of a hardware structure of a travel track planning apparatus for an autonomous vehicle according to an embodiment of the present invention. As shown in fig. 11, the apparatus 1100 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 1110 (the processors 1110 may include but are not limited to Processing devices such as a microprocessor MCU or a programmable logic device FPGA), a memory 1130 for storing data, and one or more storage media 1120 (e.g., one or more mass storage devices) for storing applications 1123 or data 1122. The memory 1130 and the storage medium 1120 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 1120 may include one or more modules, each of which may include a sequence of instructions operating on a device. Still further, the central processor 1110 may be arranged to communicate with the storage medium 1120, to execute a series of instruction operations in the storage medium 1120 on the device 1100. The apparatus 1100 may also include one or more power supplies 1160, one or more wired or wireless network interfaces 1150, one or more input-output interfaces 1140, and/or one or more operating systems 1121, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
The input output interface 1140 may be used to receive or transmit data via a network. Specific examples of such networks can include wireless networks provided by a communications provider of the device 1100. In one example, i/o Interface 1140 includes a Network adapter (NIC) that may be coupled to other Network devices via a base station to communicate with the internet. In one example, the input/output interface 1140 can be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
It will be understood by those skilled in the art that the structure shown in fig. 11 is merely illustrative and is not intended to limit the structure of the above-described apparatus. For example, device 1100 may also include more or fewer components than shown in FIG. 11, or have a different configuration than shown in FIG. 11.
Embodiments of the present invention further provide a computer-readable storage medium, which may be disposed in a driving trajectory planning device of an autonomous vehicle to store at least one instruction or at least one program for implementing a driving trajectory planning method of an autonomous vehicle in the method embodiments, where the at least one instruction or the at least one program is loaded and executed by a processor to implement the driving trajectory planning method of an autonomous vehicle provided in the method embodiments.
Alternatively, in this embodiment, the storage medium may be located in at least one network server of a plurality of network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A method of planning a travel path of an autonomous vehicle, the method comprising:
when an automatic driving vehicle needs to pass through an intersection provided with a traffic light, acquiring an initial vehicle state of the automatic driving vehicle at the current moment, a light state of the traffic light and a remaining duration corresponding to the light state;
acquiring a first preset ending vehicle state and a second preset ending vehicle state of the automatic driving vehicle within a planning time range; the first preset end vehicle state represents a vehicle state when the autonomous vehicle passes through the intersection at the reference passing speed of the intersection, and the second preset end vehicle state represents a vehicle state when the autonomous vehicle stops at a stop line of the intersection;
determining the effective time of the equivalent barrier corresponding to the traffic light according to the light state of the traffic light and the remaining duration corresponding to the light state;
determining a first effective candidate running track corresponding to a first preset ending vehicle state and a second effective candidate running track corresponding to a second preset ending vehicle state in the planning time range according to the initial vehicle state and the effective time of the equivalent obstacle, and obtaining an effective candidate running track set of the automatic driving vehicle;
and selecting a target effective running track with the minimum track cost value from the effective candidate running track set, wherein the target effective running track is used as a planned running track of the automatic driving vehicle passing through the intersection.
2. The method of claim 1, wherein determining the equivalent obstacle valid time for the traffic light according to the light status of the traffic light and the remaining duration corresponding to the light status comprises:
when the lamp state of the traffic light is red, taking the residual duration as the effective time of the equivalent obstacle of the traffic light;
when the lamp state of the traffic lamp is yellow, determining the effective time of the equivalent barrier of the traffic lamp according to the residual duration and the end planning time corresponding to the planning time;
determining time and value of the remaining duration and the preset duration of the yellow light when the lamp status of the traffic light is green;
and determining the effective time of the equivalent barrier of the traffic light according to the time sum value and the planning termination time corresponding to the planning time.
3. The method of claim 2, wherein determining a first valid candidate travel trajectory within the planned time range corresponding to a first preset end vehicle state based on the initial vehicle state and the equivalent obstacle validity time comprises:
generating a fourth-order polynomial function within the planning time range according to the initial vehicle state and a first preset ending vehicle state; the fourth-order polynomial function is a function of displacement and time;
generating a plurality of sampling points in the planning time range at preset sampling time intervals according to the fourth-order polynomial function;
fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a first candidate driving track;
determining a first candidate displacement corresponding to a time point in the planning time range according to the first candidate driving track;
obtaining the distance between the automatic driving vehicle and a stop line of the intersection at the current moment;
and determining a first effective candidate driving track in the first candidate driving tracks according to the lamp state of the traffic lamp, the effective time of the equivalent barrier in the lamp state, the distance and the first candidate displacement.
4. The method of claim 2, wherein determining a second valid candidate travel trajectory within the planned time range corresponding to a second predetermined ending vehicle state based on the initial vehicle state and the equivalent obstacle validity time comprises:
generating a fifth-order polynomial function within the planning time range according to the initial vehicle state and a second preset ending vehicle state; the quintic polynomial function is a function of displacement and time;
generating a plurality of sampling points within the effective time of the equivalent barrier at preset sampling time intervals according to the quintic polynomial function;
fitting the plurality of sampling points by taking the initial vehicle state as a starting point to obtain a second candidate driving track; the second candidate travel track is taken as the second valid candidate travel track.
5. The method of claim 1, wherein before the selecting the target effective driving track from the set of effective candidate driving tracks with the smallest track cost value, the method further comprises:
determining a driving distance cost value, a longitudinal acceleration cost value and a driving speed deviation cost value corresponding to each effective candidate driving track in the effective candidate driving track set;
determining weight coefficients corresponding to the driving distance cost value, the longitudinal acceleration cost value and the driving speed deviation cost value;
determining the product of the driving distance cost value, the longitudinal acceleration cost value and the driving speed deviation cost value with the corresponding weight coefficient;
and taking the sum of the products as the track cost value of the effective candidate running track.
6. The method of claim 5, wherein determining a travel distance cost value, a longitudinal jerk cost value, and a travel speed deviation cost value for each active candidate travel trajectory in the set of active candidate travel trajectories comprises:
according to each effective candidate running track, determining the planned running displacement and the planned running speed of the effective candidate running track at the planning termination moment corresponding to the planning time;
determining the driving distance cost value of the effective candidate driving track according to the reciprocal of the planned driving displacement;
determining the running speed deviation cost value of the effective candidate running track according to the difference value of the planned running speed and the expected running speed corresponding to the planning termination time;
determining jerks corresponding to a plurality of time points in each effective candidate running track according to each effective candidate running track;
and determining the average value of the jerks corresponding to the multiple time points, and taking the average value of the jerks corresponding to the multiple time points as the longitudinal jerk cost value.
7. The method of claim 6, wherein the determining the mean of the jerks for the plurality of time points comprises:
calculating a sum of squares of jerks corresponding to the plurality of time points;
calculating the sum of the effective values of the jerk corresponding to the plurality of time points;
and dividing the sum of the squares by the sum of the effective values to obtain the average value of the jerks corresponding to the multiple time points.
8. A travel path planning apparatus for an autonomous vehicle, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring an initial vehicle state of an automatic driving vehicle at the current moment, a lamp state of a traffic lamp and a residual duration corresponding to the lamp state when the automatic driving vehicle needs to pass through an intersection provided with the traffic lamp;
the second acquisition module is used for acquiring a first preset ending vehicle state and a second preset ending vehicle state of the automatic driving vehicle within a planning time range; the first preset end vehicle state represents a vehicle state when the autonomous vehicle passes through the intersection at the reference passing speed of the intersection, and the second preset end vehicle state represents a vehicle state when the autonomous vehicle stops at a stop line of the intersection;
the first determination module is used for determining the effective time of the equivalent barrier corresponding to the traffic light according to the light state of the traffic light and the remaining duration corresponding to the light state;
the second determination module is used for determining a first effective candidate running track corresponding to a first preset ending vehicle state and a second effective candidate running track corresponding to a second preset ending vehicle state in the planning time range according to the initial vehicle state and the effective time of the equivalent obstacle, so as to obtain an effective candidate running track set of the automatic driving vehicle;
and the selection module is used for selecting a target effective running track with the minimum track cost value from the effective candidate running track set, and taking the target effective running track as a planned running track of the automatic driving vehicle passing through the intersection.
9. A driving track planning device of an automatic driving vehicle is characterized by comprising a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to realize the driving track planning method of the automatic driving vehicle.
10. A computer readable storage medium having stored therein at least one instruction or at least one program set, which is loaded and executed by a processor to implement a method of travel trajectory planning for an autonomous vehicle as described above.
CN202010237723.9A 2020-03-30 2020-03-30 Driving track planning method of automatic driving vehicle, related equipment and storage medium Active CN111591306B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010237723.9A CN111591306B (en) 2020-03-30 2020-03-30 Driving track planning method of automatic driving vehicle, related equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010237723.9A CN111591306B (en) 2020-03-30 2020-03-30 Driving track planning method of automatic driving vehicle, related equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111591306A true CN111591306A (en) 2020-08-28
CN111591306B CN111591306B (en) 2022-07-12

Family

ID=72180059

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010237723.9A Active CN111591306B (en) 2020-03-30 2020-03-30 Driving track planning method of automatic driving vehicle, related equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111591306B (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112810630A (en) * 2021-02-05 2021-05-18 山东大学 Method and system for planning track of automatic driving vehicle
CN113050621A (en) * 2020-12-22 2021-06-29 北京百度网讯科技有限公司 Trajectory planning method and device, electronic equipment and storage medium
CN113129625A (en) * 2021-04-16 2021-07-16 阿波罗智联(北京)科技有限公司 Vehicle control method and device, electronic equipment and vehicle
CN113238565A (en) * 2021-06-16 2021-08-10 京东鲲鹏(江苏)科技有限公司 Vehicle path planning method and device, vehicle and storage medium
CN113239986A (en) * 2021-04-25 2021-08-10 浙江吉利控股集团有限公司 Training method and device for vehicle track evaluation network model and storage medium
CN113561992A (en) * 2021-07-30 2021-10-29 广州文远知行科技有限公司 Method, device, terminal device and medium for generating trajectory of automatic driving vehicle
CN114103938A (en) * 2021-03-23 2022-03-01 京东鲲鹏(江苏)科技有限公司 Method, device and storage medium for controlling longitudinal movement of vehicle
CN114167906A (en) * 2021-12-08 2022-03-11 安徽江淮汽车集团股份有限公司 Acceleration control method for automatic driving
CN114637283A (en) * 2020-12-16 2022-06-17 郑州宇通客车股份有限公司 Vehicle path planning method and device based on dynamic obstacle avoidance
CN115320636A (en) * 2022-08-31 2022-11-11 中汽创智科技有限公司 Automatic driving method, device and storage medium
WO2023273067A1 (en) * 2021-06-30 2023-01-05 上海商汤临港智能科技有限公司 Driving planning method and apparatus, computer device, and storage medium
WO2023165205A1 (en) * 2022-03-01 2023-09-07 魔门塔(苏州)科技有限公司 Intersection passing decision-making method and apparatus, medium, device, and vehicle

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10213450A (en) * 1997-01-28 1998-08-11 Alpine Electron Inc Vehicle mounted navigator
DE102015004605A1 (en) * 2015-04-08 2016-10-13 Audi Ag A method of operating a mobile unit and mobile unit control system
CN108196535A (en) * 2017-12-12 2018-06-22 清华大学苏州汽车研究院（吴江） Automated driving system based on enhancing study and Multi-sensor Fusion
CN108665716A (en) * 2018-05-28 2018-10-16 于挺进 A kind of method that the automatic anticipation red light crossing of automobile auxiliary is passed through
CN109003448A (en) * 2018-08-02 2018-12-14 北京图森未来科技有限公司 A kind of air navigation aid of intersection, equipment and system
DE102019206092A1 (en) * 2018-05-01 2019-11-07 Honda Motor Co., Ltd. SYSTEMS AND METHOD FOR PRODUCING INSTRUCTIONS FOR ACCESSING CROSSROADS WITH AUTONOMOUS VEHICLES

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10213450A (en) * 1997-01-28 1998-08-11 Alpine Electron Inc Vehicle mounted navigator
DE102015004605A1 (en) * 2015-04-08 2016-10-13 Audi Ag A method of operating a mobile unit and mobile unit control system
CN108196535A (en) * 2017-12-12 2018-06-22 清华大学苏州汽车研究院（吴江） Automated driving system based on enhancing study and Multi-sensor Fusion
DE102019206092A1 (en) * 2018-05-01 2019-11-07 Honda Motor Co., Ltd. SYSTEMS AND METHOD FOR PRODUCING INSTRUCTIONS FOR ACCESSING CROSSROADS WITH AUTONOMOUS VEHICLES
CN108665716A (en) * 2018-05-28 2018-10-16 于挺进 A kind of method that the automatic anticipation red light crossing of automobile auxiliary is passed through
CN109003448A (en) * 2018-08-02 2018-12-14 北京图森未来科技有限公司 A kind of air navigation aid of intersection, equipment and system

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114637283A (en) * 2020-12-16 2022-06-17 郑州宇通客车股份有限公司 Vehicle path planning method and device based on dynamic obstacle avoidance
CN113050621A (en) * 2020-12-22 2021-06-29 北京百度网讯科技有限公司 Trajectory planning method and device, electronic equipment and storage medium
CN113050621B (en) * 2020-12-22 2023-04-28 北京百度网讯科技有限公司 Track planning method, track planning device, electronic equipment and storage medium
CN112810630A (en) * 2021-02-05 2021-05-18 山东大学 Method and system for planning track of automatic driving vehicle
CN112810630B (en) * 2021-02-05 2022-03-04 山东大学 Method and system for planning track of automatic driving vehicle
CN114103938A (en) * 2021-03-23 2022-03-01 京东鲲鹏(江苏)科技有限公司 Method, device and storage medium for controlling longitudinal movement of vehicle
CN113129625A (en) * 2021-04-16 2021-07-16 阿波罗智联(北京)科技有限公司 Vehicle control method and device, electronic equipment and vehicle
CN113129625B (en) * 2021-04-16 2023-01-24 阿波罗智联(北京)科技有限公司 Vehicle control method and device, electronic equipment and vehicle
CN113239986A (en) * 2021-04-25 2021-08-10 浙江吉利控股集团有限公司 Training method and device for vehicle track evaluation network model and storage medium
CN113238565A (en) * 2021-06-16 2021-08-10 京东鲲鹏(江苏)科技有限公司 Vehicle path planning method and device, vehicle and storage medium
WO2023273067A1 (en) * 2021-06-30 2023-01-05 上海商汤临港智能科技有限公司 Driving planning method and apparatus, computer device, and storage medium
CN113561992A (en) * 2021-07-30 2021-10-29 广州文远知行科技有限公司 Method, device, terminal device and medium for generating trajectory of automatic driving vehicle
CN113561992B (en) * 2021-07-30 2023-10-20 广州文远知行科技有限公司 Automatic driving vehicle track generation method, device, terminal equipment and medium
CN114167906A (en) * 2021-12-08 2022-03-11 安徽江淮汽车集团股份有限公司 Acceleration control method for automatic driving
WO2023165205A1 (en) * 2022-03-01 2023-09-07 魔门塔(苏州)科技有限公司 Intersection passing decision-making method and apparatus, medium, device, and vehicle
CN115320636A (en) * 2022-08-31 2022-11-11 中汽创智科技有限公司 Automatic driving method, device and storage medium

Also Published As

Publication number Publication date
CN111591306B (en) 2022-07-12

Similar Documents

Publication Publication Date Title
CN111591306B (en) Driving track planning method of automatic driving vehicle, related equipment and storage medium
CN110861650B (en) Vehicle path planning method and device, vehicle-mounted equipment and storage medium
CN110562258B (en) Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium
US11614962B2 (en) Scheduling vehicle task offloading and triggering a backoff period
US20210009119A1 (en) Method and control device for a system for the control of a motor vehicle
US11586209B2 (en) Differential dynamic programming (DDP) based planning architecture for autonomous driving vehicles
US11567506B2 (en) Speed planning guidance line for mild slow down
US11584248B2 (en) Method of parking an autonomous driving vehicle for autonomous charging
CN113071487B (en) Automatic driving vehicle control method and device and cloud equipment
CN111344725A (en) System and method for determining whether an autonomous vehicle can provide a requested service to an occupant
US11628858B2 (en) Hybrid planning system for autonomous vehicles
CN113795801B (en) Obstacle avoidance trajectory planning for autonomous vehicles
CN113619597B (en) Planning system for speed limit change of automatic driving vehicle
CN114644016A (en) Vehicle automatic driving decision-making method and device, vehicle-mounted terminal and storage medium
CN113954858A (en) Method for planning vehicle driving route and intelligent automobile
US11300955B2 (en) Method for determining ride stability of an autonomous driving system controlling an autonomous driving vehicle
JP2020075561A (en) Travel range acquisition system, vehicle control system and travel range acquisition program
US20230391356A1 (en) Dynamic scenario parameters for an autonomous driving vehicle
CN112461251A (en) Method, device and system for transmitting waypoint information of automatic driving motorcade
EP3838697A1 (en) Speed planning using a speed planning guideline for idle speed of autonomous driving vehicles
US11724717B2 (en) Implementation of dynamic cost function of self-driving vehicles
CN117944684B (en) Track changing planning method and device, storage medium and electronic equipment
US20240034353A1 (en) Automatic generation of corner scenarios data for tuning autonomous vehicles
US20240092358A1 (en) Systems and methods for scene understanding
US20240101106A1 (en) Systems and methods for scene understanding

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