CN115973162A - Method, apparatus, electronic device, and medium for determining vehicle travel track - Google Patents
Method, apparatus, electronic device, and medium for determining vehicle travel track Download PDFInfo
- Publication number
- CN115973162A CN115973162A CN202310113398.9A CN202310113398A CN115973162A CN 115973162 A CN115973162 A CN 115973162A CN 202310113398 A CN202310113398 A CN 202310113398A CN 115973162 A CN115973162 A CN 115973162A
- Authority
- CN
- China
- Prior art keywords
- radius
- hypothesis
- vehicle
- track
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 11
- 239000002245 particle Substances 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 2
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 2
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- 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
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The present disclosure relates to a method, apparatus, electronic device, and medium for determining a vehicle travel track. The method comprises the following steps: determining a set of historical travel trajectories corresponding to each of a plurality of leading vehicles, the set of historical travel trajectories including a plurality of historical track points; determining a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle, each radius hypothesis in the set of radius hypotheses corresponding to a respective radius hypothesis circular trajectory; selecting an optimal radius hypothesis from a set of radius hypotheses based on distance differences between adjacent points in the plurality of historical track points and the corresponding radius hypothesis circular tracks; and determining at least one of a locally optimal radius and a globally optimal radius associated with the target travel track according to the selected optimal radius hypothesis. In this way, the preceding vehicle information can be utilized, the dependence on the acquisition equipment is reduced, the noise can be fully eliminated, and the accurate optimal estimation of the vehicle track can be obtained.
Description
Technical Field
The present disclosure relates generally to the field of automated driving technology, and more particularly to methods, apparatus, electronic devices, and computer-readable storage media for determining a vehicle travel trajectory.
Background
In recent years, driving assistance functions such as an adaptive cruise control system (ACC) and an automatic emergency braking system (AEB) have rapidly penetrated the passenger vehicle market, and the ACC and AEB functions on a high-speed structured road have become mature.
Chinese patent application CN112665590a provides a method and apparatus for determining a trajectory of a vehicle, an electronic device, and a computer storage medium. The track determination method of the vehicle comprises the following steps: determining a target planning path based on the high-precision map and the driving destination; determining a vehicle driving mode of the target vehicle based on the target planned path and the current position of the target vehicle; acquiring a target historical traffic flow track corresponding to a vehicle running mode; matching a track with the highest correlation degree from the target historical traffic flow track as a first track of the target vehicle based on the curvature value, the distance and the azimuth; obtaining a second track of the target vehicle by using a vehicle dynamics model according to the motion state information of the target vehicle; and fusing the first track and the second track based on the fusion function to obtain the target track of the target vehicle.
In the process of determining the vehicle track in the patent, firstly, high-precision map input is needed, the front track kernel is weighted and fused with the vehicle motion track, the track determining method does not fully utilize the front traffic information, and only the vehicle motion track is simply fused, so that the track estimation accuracy is not enough, and the driving safety is even affected in serious cases.
Particularly, in the scenes of unstructured roads, congested road conditions and the like, the detection result of the camera on the lane line is greatly reduced, and the vehicle is difficult to select the target vehicles of ACC and AEB according to the lane line. Therefore, a method for calculating the driving track of the self vehicle is designed, and is important for the driving safety of the vehicle, especially for the performance of ACC and AEB.
Disclosure of Invention
According to an example embodiment of the present disclosure, a solution for determining a vehicle driving trajectory is provided to at least partially solve the problems in the prior art.
In a first aspect of the present disclosure, a method for determining a vehicle travel track is provided. The method comprises the following steps: determining a set of historical travel trajectories corresponding to each of a plurality of leading vehicles, wherein the set of historical travel trajectories includes a plurality of historical trajectory points; determining a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle, each radius hypothesis in the set of radius hypotheses corresponding to a respective radius hypothesis circular trajectory; selecting an optimal radius hypothesis from a group of radius hypotheses based on distance differences between adjacent points in the plurality of historical track points and corresponding radius hypothesis circular tracks; and determining at least one of a local optimal radius and a global optimal radius associated with the target travel track according to the selected optimal radius hypothesis.
In some embodiments, determining a set of historical travel trajectories corresponding to each of a plurality of leading vehicles may preferably comprise: and fitting the plurality of historical track points by using a least square method to obtain a group of historical driving tracks.
In some embodiments, determining a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle may include: determining a first radius hypothesis based on a lateral acceleration of the vehicle; determining a second radius hypothesis based on the kinematic trajectory of the vehicle; and determining a third radius hypothesis based on the target driving trajectory calculated in the previous period.
In some embodiments, selecting an optimal radius hypothesis from a set of radius hypotheses based on distance differences between neighboring points of the plurality of historical trajectory points to corresponding ones of the radius hypothesis circular trajectories may include: determining an initial global optimal radius based on the curvature of the running track of the vehicle in the previous period; calculating the distance from each point in a plurality of historical track points to a circular track corresponding to the initial global optimal radius based on the initial global optimal radius; acquiring a difference absolute value between adjacent points in the plurality of historical track points and a circumferential track distance corresponding to the initial global optimal radius; and calculating an average of the absolute values of the differences for determining whether the target travel path corresponding to a respective one of a set of the radius hypotheses is good or bad.
In some embodiments, selecting an optimal radius hypothesis from a set of radius hypotheses based on distance differences between adjacent points of the plurality of historical trajectory points and corresponding radius hypothesis circular trajectories comprises: sequentially calculating an average value of the absolute difference values of all track points in the plurality of historical track points to the radius hypothesis circular track corresponding to each radius hypothesis in the group of radius hypotheses; and determining the radius hypothesis corresponding to the minimum value of the average values as the optimal radius hypothesis.
In some embodiments, the method may comprise: and calculating the average value of the difference values of all the points in the plurality of historical track points to the circular track corresponding to the optimal radius hypothesis.
In some embodiments, determining at least one of a locally optimal radius and a globally optimal radius associated with the target travel trajectory based on the selected optimal radius hypothesis may include: determining at least one of a local optimal radius and a global optimal radius of the target travel track based on the difference average; and obtaining the target running track based on at least one of the local optimal radius and the global optimal radius.
In a second aspect of the present disclosure, an apparatus for determining a vehicle travel track is provided. The device includes: a preceding vehicle history travel track determination module configured to determine a set of history travel tracks corresponding to each of a plurality of preceding vehicles, wherein the set of history travel tracks includes a plurality of history track points; a radius hypothesis determination module configured to determine a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle, each radius hypothesis in the set of radius hypotheses corresponding to a respective radius hypothesis circular trajectory; an optimal hypothesis radius selection module configured to select an optimal radius hypothesis from a set of radius hypotheses based on distance differences between adjacent points of a plurality of historical trajectory points and corresponding radius hypothesis circular trajectories; and a target optimal radius determination module configured to determine at least one of a local optimal radius and a global optimal radius associated with the target travel trajectory according to the selected optimal radius hypothesis.
In some embodiments, the previous vehicle historical travel track determination module may be further configured to: and fitting the plurality of historical track points by using a least square method to obtain a group of historical driving tracks.
In some embodiments, the radius hypothesis determination module may be further configured to: determining a first radius hypothesis based on a lateral acceleration of the vehicle; determining a second radius hypothesis based on the kinematic trajectory of the vehicle; and determining a third radius hypothesis based on the target driving trajectory calculated in the previous period.
In some embodiments, the optimal hypothetical radius selection module may be further configured to: determining an initial global optimal radius based on the curvature of the running track of the vehicle in the previous period; calculating the distance from each point in a plurality of historical track points to a circular track corresponding to the initial global optimal radius based on the determined initial global optimal radius; acquiring the absolute value of the difference value between adjacent points in the plurality of historical track points and the circumferential track distance corresponding to the initial global optimal radius; and calculating an average of the absolute values of the differences for determining whether the target travel path corresponding to a respective one of a set of the radius hypotheses is good or bad.
In some embodiments, the optimal hypothesis radius selection module may be further configured to: sequentially calculating the average value of the absolute values of the differences between all the track points in the plurality of historical track points and the radius hypothesis circular track corresponding to each radius hypothesis in the group of radius hypotheses; and determining the radius hypothesis corresponding to the minimum value of the average values as the optimal radius hypothesis.
In some embodiments, the apparatus may be configured to: and calculating the average value of the difference values of all the points in the plurality of historical track points to the circular track corresponding to the optimal radius hypothesis.
In some embodiments, the target optimal radius determination module may be further configured to: determining at least one of a local optimal radius and a global optimal radius associated with the target travel track based on the difference average; and obtaining the target running track based on at least one of the local optimal radius and the global optimal radius.
In a third aspect of the present disclosure, an electronic device is provided. The apparatus comprises: one or more processors; and storage means for storing the one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the method according to the first aspect of the disclosure.
In a fourth aspect of the disclosure, a computer-readable storage medium is provided. The medium has stored thereon a computer program which, when executed by a processor, implements a method according to the first aspect of the present disclosure.
In a fifth aspect of the present disclosure, a computer program product is provided. The product comprises computer programs/instructions which, when executed by a processor, implement the method according to the first aspect of the disclosure.
It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, the same or similar reference numerals denote the same or similar elements. The accompanying drawings are included to provide a further understanding of the present disclosure, and are not intended to limit the disclosure in any way, wherein:
FIG. 1 illustrates a schematic diagram of an example environment in which various embodiments of the present disclosure can be implemented;
FIG. 2 shows a schematic flow diagram of a method for determining a vehicle travel track, in accordance with some embodiments of the present disclosure;
FIG. 3 shows a schematic flow diagram of a particle swarm algorithm in accordance with some embodiments of the present disclosure;
FIG. 4 shows a schematic block diagram of an apparatus for determining a vehicle travel trajectory according to some embodiments of the present disclosure; and
FIG. 5 illustrates a block diagram of a computing device capable of implementing various embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
In describing embodiments of the present disclosure, the terms "include" and "comprise," and similar language, are to be construed as open-ended, i.e., "including but not limited to. The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first," "second," and the like may refer to different or the same objects. Other explicit and implicit definitions are also possible below.
As described above, the current technology does not fully utilize the forward traffic information, and only performs simple fusion on the motion trajectory of the vehicle, thereby resulting in insufficient accuracy of the trajectory estimation. In addition, the calculation of the driving track of the self-vehicle at present mostly depends on the detection of the lane line by the camera, and the calculation effect is poor under the condition of the unstructured road or the road condition with the blocked detection of other lane lines.
In view of the above problems, the present disclosure provides a scheme for determining a vehicle driving track, which can make full use of front vehicle information, fit a plurality of front vehicle tracks, then make a radius assumption for a rear vehicle based on driving parameters of the vehicle, and calculate distances from particle swarms composed of track points of the front vehicle tracks to track curves corresponding to the radius assumptions, thereby selecting an optimal radius assumption, and determining a target driving path based on the distances from the track points to the optimal radius assumption. The mode can obviously reduce the dependence on the camera, and can be widely applied to scenes such as unstructured roads, congested road conditions and the like. Moreover, the method can effectively eliminate noise and increase the robustness of the system. The scheme can obtain the optimal estimation of the target running track.
Exemplary embodiments of the present disclosure will be described below in conjunction with fig. 1 to 5.
Fig. 1 illustrates a schematic diagram of an example environment 100 in which various embodiments of the present disclosure can be implemented.
As shown in fig. 1, in the example of environment 100, vehicle 110 (i.e., "own vehicle") is traveling on a road, with one or more other vehicles present in its surroundings. The vehicle 110 is, for example, in a congested environment, and the sensing unit (e.g., a camera) cannot accurately detect the lane line information. Alternatively, the road on which the vehicle 110 travels belongs to an unstructured road, and the surrounding lane lines are not clear enough. The vehicle 110 needs to accurately detect the track of the vehicle ahead, and then plan an optimal target driving track in combination with the track of the vehicle ahead, so as to ensure driving comfort and safety.
It should be understood that the environment 100 shown in FIG. 1 is only one example environment in which a vehicle 110 may be traveling. In addition to traveling on outdoor roads, the vehicle 110 is likely to be traveling in various environments such as tunnels, outdoor parking lots, building interiors (e.g., indoor parking lots), communities, parks, and so forth.
In the example of FIG. 1, vehicle 110 may be any type of vehicle that may carry people and/or things and that is moved by a powered system such as an engine, including but not limited to a car, truck, bus, electric vehicle, motorcycle, recreational vehicle, train, and the like. In some embodiments, the vehicle 110 in the environment 100 may be a vehicle with certain autonomous driving capabilities, such a vehicle also being referred to as an unmanned vehicle or autonomous vehicle. In some embodiments, vehicle 110 may also be a vehicle with semi-autonomous driving capabilities.
As shown in fig. 1, vehicle 110 may also include a computing device 120. In some embodiments, computing device 120 may be communicatively coupled to vehicle 110. Although shown as a separate entity, computing device 120 may be embedded in vehicle 110. Computing device 120 may also be an entity external to vehicle 110 and may communicate with vehicle 110 via a wireless network. Computing device 120 may be any device with computing capabilities.
As shown in fig. 1, as non-limiting examples, computing device 120 may be any type of fixed, mobile, or portable computing device, including but not limited to a desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, multimedia computer, mobile phone, or the like; all or a portion of the components of computing device 120 may be distributed in the cloud. Computing device 120 contains at least a processor, memory, and other components typically found in a general purpose computer to implement computing, storage, communication, control, and the like functions.
In some embodiments, the computing device 120 may include a system for autonomous vehicle speed planning. The system architecture may include, for example, modules for system input, information processing, system execution, and the like. The system input module may include at least a sensing unit and a body unit. The sensing unit may include a radar, a camera, etc. for acquiring the preceding vehicle motion information. The body unit can be used for acquiring the kinematic parameters of the self-vehicle. The information processing module can be used for processing the motion information of the front vehicle, obtaining the position lighting information of the front vehicle in the self-vehicle coordinate system, and calculating the motion state of the self-vehicle. The information processing module can also comprise an ADAS domain controller which is used for realizing a vehicle auxiliary driving algorithm and outputting a vehicle control command. The system execution module is used for executing the request instruction. The parameter transmission among the units includes but is not limited to the transmission of CAN bus and Ethernet. Various embodiments for determining a vehicle travel trajectory according to the present disclosure may be incorporated in an ADAS domain controller, for example.
With continued reference to fig. 1, when the vehicle 100 travels in a complex environment as mentioned above and the sensing unit cannot accurately provide lane line information and surrounding vehicle information, the vehicle 100 needs to plan a set of optimal travel paths by relying on the trajectories of a plurality of preceding vehicles to ensure driving safety and driving comfort in a special scene.
Fig. 2 shows a schematic flow diagram of a method 200 for determining a vehicle driving trajectory, according to some embodiments of the present disclosure. The method 200 may be implemented, for example, by the computing device 120 shown in FIG. 1.
At block 201, a set of historical travel trajectories corresponding to each of a plurality of leading vehicles is determined, wherein the set of historical travel trajectories includes a plurality of historical trajectory points. The historical trajectory of the preceding vehicle may be determined by the sensing unit of the vehicle 110. For example, there are a target vehicle a in front, there are X history points of a, and fitting the X history points is a track that a has traveled in the past, that is, a history travel track. When there are a plurality of vehicles ahead, the historical travel locus equal to the number of vehicles ahead is obtained.
In some embodiments, a least squares fit may be used to fit a plurality of historical trajectory points to obtain a set of historical travel trajectories. In one embodiment, specifically, after obtaining the historical track points of each vehicle from the sensing unit, the curve equation of the historical track of the front vehicle to be fitted is assumed to be a quadratic equation:
f(x)＝C 0 +C 1 *x+C 2 *x 2
the least squares method aims to solve:
wherein x is the longitudinal coordinate of the track point and y is the transverse coordinate of the track point.
Where y is the true value and f (x) is the value calculated from the fitted curve, the minimum value is required, and it is necessary to match C to the above formula 0 、C 1 、C 2 Calculating a partial derivative:
and n is the number of points on the curve, and can be determined according to effects or experience, and the number of n can be used for accurately calculating the historical track equation of the front vehicle. Thus, the conversion is in matrix form:
thereby obtaining C of each curve of the front vehicle track with smaller performance and less labor consumption 0 、C 1 、C 2 。
It should be noted that the calculation method and the embodiment of the least square method are only exemplary, and any other suitable method may be adopted to fit each trajectory of the leading vehicle, which is not limited by the present disclosure.
At block 203, a set of radius hypotheses associated with a target travel trajectory of vehicle 110 is determined based on one or more travel parameters associated with the travel trajectory of vehicle 110, each radius hypothesis in the set of radius hypotheses corresponding to a respective radius hypothesis circular trajectory.
In some embodiments, the above and subsequent operations may be implemented using a particle swarm algorithm as shown in FIG. 3, to combine all the front vehicle trajectories into one optimal trajectory that the vehicle 110 may travel. The algorithm utilizes a fitness function to calculate the average value of the difference between the distances from two adjacent track points on all effective tracks to the current circle radius. The smaller the value, the closer the particle swarm algorithm is to converging. The working principle of the algorithm will be described below with reference to fig. 3.
Fig. 3 illustrates a schematic flow diagram 300 of a particle swarm algorithm in accordance with some embodiments of the present disclosure. The flow diagram 300 may be used to implement one or more of blocks 203, 205, and 207.
At block 301, the particles are initialized so that the particles are in a state that enables further calculations. At block 303, the fitness of each particle is then calculated. The fitness refers to a value of a fitness function in an algorithm, on the basis of observing the activity behaviors of animal clusters, the algorithm utilizes sharing of information by individuals in the clusters to enable the motion of the whole clusters to generate a process of evolution from disorder to order in a problem solving space, and an optimal solution is searched through iteration, so that the quality of the solution is evaluated through the fitness.
Further, at block 305, the global optimum is updated based on the fitness calculated at block 303, and the speed of particle update and the values of the particles are further updated at block 307. When the maximum iteration speed or global optimum is reached, then the final output is obtained at block 309. If the maximum iteration speed or global optimum is not reached, return to block 301 to re-iterate the process until an optimum solution is found.
In one embodiment, the first radius assumption may be based on a maximum lateral acceleration 3m/s 2 acceptable to the host vehicle. I.e., radiuHyp [0] = | Vego | ^2/3. Wherein Vego is the speed of the bicycle. In other embodiments, the acceptable speed of the vehicle may be set empirically. The lateral direction may be a direction perpendicular to the path traveled by the vehicle 110, i.e., a direction normal to the trajectory traveled by the vehicle 110.
In one embodiment, the second radius assumption may be based on the kinematic trajectory of the vehicle 110. Namely: radiausHyp [1] =1.0/VDY _ c0. Wherein VDY _ c0 is the track curvature calculated by the kinematic track module of the vehicle 110.
In one embodiment, the third radius assumes RadiUSHyp [2] may be the final own vehicle trajectory calculated for the previous cycle.
Initializing local optimality of each hypothesis and the update speed of the particle swarm based on the 3 radius hypotheses: localBestFit [ i ] = InitFit;
LocalBestRadius[i]＝RadiusHyp[i]；
VelHyp[i]＝10；
it should be understood that since there are three assumed initial radii, there are three fitness functions, localBestFit [1] LocalBestFit [2] LocalBestFit [3], where InitFit is the last three fitness function initial values, which can be given a maximum value empirically, and VelHyp [ i ] is the update speed for each local optimum radius, say by considering the value of the local radius for each cycle to shift by 10m.
It should be noted that the above radius assumptions and values are illustrative, and any suitable radius assumptions and values may be used, which are not limited in this disclosure.
At block 205, an optimal radius hypothesis is selected among a set of radius hypotheses based on differences in distances from neighboring points of the plurality of historical track points to the corresponding radius hypothesis circular tracks.
In some embodiments, the starting global optimum radius may be determined based on a curvature of a travel trajectory of the vehicle in a previous cycle. Then, based on the determined starting global optimal radius, a distance from each point of the plurality of historical track points to a circular track corresponding to the starting global optimal radius is calculated. Further, a difference absolute value of distances from adjacent points in the plurality of historical track points to a circumferential track corresponding to the initial global optimal radius is obtained. Finally, an average of the absolute values of the differences is calculated for use in determining whether the target travel path corresponds to a respective one of a set of radius hypotheses.
In one embodiment, the starting global optimum radius may be determined based on the last cycle of the vehicle trajectory curvature TraceCurve. Namely: globalBestRadius =1/TraceCurve. Next, the global optimum radius GlobalBestRadius determined according to the above operations may be determined as follows:
s1: calculating the distance from the track point of the front vehicle to the global optimal radius circular track;
s2: calculating the absolute value of the difference value between the distance from two adjacent track points on the track of the front vehicle to the distance from the track of the circumference; and
s3: and calculating the average value Curve2TraceDevAverage of the circular track distance difference value, wherein the value is used for judging the quality of the fusion Curve.
Therefore, the starting global optimal radius fitness value GlobalBestFit is equal to Curve2 TraceDevAvage.
In some embodiments, an average of absolute values of differences of all of the plurality of historical track points to the radius hypothesis circular tracks corresponding to each radius hypothesis in the set of radius hypotheses may be sequentially calculated, and the radius hypothesis corresponding to the smallest value in the average may be determined as the optimal radius hypothesis.
The global optimal radius GlobalBestRadius is the final output of the previous period, and the optimal radius hypothesis with the minimum fitness function can be found from the three assumed radii output in the previous period and used as the initial optimal radius hypothesis of the period. In one implementation, the average of the distance differences from all the trace points to each assumed radius circle is computed sequentially, and the above process is repeated, replacing only the GlobalBestRadius with the corresponding radius hyp [ i ]. The corresponding local optimum is then:
LocalBestFit[i]；
if(LocalBestFit[i]<GlobalBestFit)
{
GlobalBestFit＝LocalBestFit[i]；
GlobalBestRadius＝RadiusHyp[i]；
}
it should be noted that the above manner of finding the optimal radius assumption is only exemplary, and any other appropriate manner may be adopted to find the optimal radius assumption, which is not limited by the present disclosure.
At block 207, at least one of a locally optimal radius and a globally optimal radius of the target travel trajectory is determined based on the selected optimal radius hypothesis.
In some embodiments, an average of differences from all of the plurality of historical track points to a circular track corresponding to the optimal radius hypothesis may be calculated, and then at least one of a local optimal radius and a global optimal radius of the target travel track may be determined based on the average of differences, and the target travel track may be obtained based on the at least one of the local optimal radius and the global optimal radius.
In one embodiment, the local optimal radius and the global optimal radius of the target travel trajectory may be determined by performing an iterative loop:
RadiusHyp[i]＝RadiusHyp[i]+VelHyp[i]；
and calculating the average value of the distance difference between all track points and the assumed circular track of the radius to obtain Curve2TraceDevAverage.
The local optimum radius can then be found by:
if Curve2 TraceDevAvage is smaller than LocalBestFit [ i ] of the previous cycle, indicating that the error of RadiUsHyp [ i ] is smaller at this time, replacing LocalBestRadus [ i ] with the current RadiUsHyp [ i ]:
if(LocalBestFit[i]>Curve2TraceDevAverage)
{
LocalBestFit[i]＝Curve2TraceDevAverage；
LocalBestRadius[i]＝RadiusHyp[i]；
}
further, the global optimum may be found by:
if(GlobalBestFit[i]>Curve2TraceDevAverage)
{
GlobalBestFit[i]＝Curve2TraceDevAverage；
GlobalBestRadius＝RadiusHyp[i]；
}
the iteration times of the algorithm can be set according to different requirements, and the more the iteration times are, the closer the final result is to the true value. After the algorithm reaches the iteration times, the radius GlobalBestradius of the target driving track can be obtained.
It should be noted that the above embodiments may be implemented by the calculation method shown in fig. 3, and may also be implemented by other suitable calculation methods, which is not limited by the present disclosure.
Therefore, according to the embodiments of the present disclosure, historical track information of a vehicle ahead can be fully utilized, the optimal estimation of the target driving track of the vehicle can be obtained by fitting a single track of the vehicle ahead and utilizing a preset algorithm according to the track information of the vehicle ahead, the robustness and the calculation efficiency of the system can be significantly improved, and the driving safety of the vehicle under a complex environment can be ensured.
Fig. 4 shows a schematic block diagram of an apparatus 400 for determining a vehicle driving trajectory, in accordance with some embodiments of the present disclosure.
As shown in fig. 4, the apparatus 400 includes a previous vehicle historical travel track determining module 401, a radius hypothesis determining module 403, an optimal hypothesis radius extracting module 405, and a target optimal radius determining module 407.
In the apparatus 400, a preceding vehicle history travel track determination module 401 is configured to determine a set of history travel tracks corresponding to each of a plurality of preceding vehicles, wherein the set of history travel tracks includes a plurality of history track points. The radius hypothesis determination module 403 is configured to determine a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle, each radius hypothesis in the set of radius hypotheses corresponding to a respective radius hypothesis circular trajectory; the optimal hypothesis radius extraction module 405 is configured to extract an optimal radius hypothesis from a set of radius hypotheses based on differences in distances between neighboring points of the plurality of historical trajectory points to corresponding radius hypothesis circular trajectories. The target optimal radius determination module 407 is configured to determine at least one of a local optimal radius and a global optimal radius associated with the target travel trajectory according to the selected optimal radius hypothesis.
In some embodiments, the previous vehicle historical driving track determination module 401 may be further configured to: and fitting the plurality of historical track points by using a least square method to obtain a group of historical driving tracks.
In some embodiments, the radius assumption determination module 403 may be further configured to determine a first radius assumption based on a lateral acceleration of the vehicle; determining a second radius hypothesis based on the kinematic trajectory of the vehicle; and determining a third radius hypothesis based on the target driving trajectory calculated in the previous period.
In some embodiments, the optimal hypothetical radius selection module 405 may be further configured to: determining an initial global optimal radius based on the curvature of the running track of the vehicle in the previous period; calculating the distance from each point in the plurality of historical track points to a circular track corresponding to the initial global optimal radius based on the determined initial global optimal radius; acquiring a difference absolute value between adjacent points in the plurality of historical track points and a circumferential track distance corresponding to the initial global optimal radius; and calculating an average of the absolute values of the differences for determining whether the target travel path corresponding to a respective one of the set of radius hypotheses is good or bad.
In some embodiments, the optimal hypothetical radius selection module 405 may be further configured to: sequentially calculating the average value of the difference absolute values of all track points in the plurality of historical track points to the radius hypothesis circular track corresponding to each radius hypothesis in the group of radius hypotheses; and determining a radius hypothesis corresponding to a minimum value of the average values as an optimal radius hypothesis.
In some embodiments, the apparatus 400 may be configured to: and calculating the difference average value of all the points in the plurality of historical track points to the circular track corresponding to the optimal radius hypothesis.
In some embodiments, the target optimal radius determination module 407 may be further configured to: determining at least one of a local optimal radius and a global optimal radius associated with the target travel track based on the difference average; and obtaining a target running track based on at least one of the local optimal radius and the global optimal radius.
Fig. 5 illustrates a block diagram of a computing device 500 capable of implementing multiple embodiments of the present disclosure. Device 500 may be used, for example, to implement computing device 120 of fig. 1.
As shown in fig. 5, device 500 includes a computing unit 501 that may perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM) 502 or loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 501 performs the various methods and processes described above, such as the method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM503 and executed by the computing unit 501, one or more steps of the method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the method 200 by any other suitable means (e.g., by means of firmware).
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a load programmable logic device (CPLD), and the like.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (10)
1. A method for determining a trajectory of a vehicle, comprising:
determining a set of historical travel trajectories corresponding to each of a plurality of leading vehicles, wherein the set of historical travel trajectories includes a plurality of historical trajectory points;
determining a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle, each radius hypothesis in the set of radius hypotheses corresponding to a respective radius hypothesis circular trajectory;
selecting an optimal radius hypothesis from a group of radius hypotheses based on distance differences between adjacent points in the plurality of historical track points and corresponding radius hypothesis circular tracks; and
determining at least one of a locally optimal radius and a globally optimal radius associated with the target travel trajectory based on the selected optimal radius hypothesis.
2. The method of claim 1, wherein determining a set of historical travel trajectories corresponding to each of a plurality of leading vehicles preferably comprises:
and fitting the plurality of historical track points by using a least square method to obtain a group of historical driving tracks.
3. The method of claim 1, wherein determining a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle comprises:
determining a first radius hypothesis based on a lateral acceleration of the vehicle;
determining a second radius hypothesis based on the kinematic trajectory of the vehicle; and
determining a third radius hypothesis based on the target driving trajectory calculated in the previous period.
4. The method of any one of claims 1 to 3, wherein selecting an optimal radius hypothesis from the set of radius hypotheses based on differences in distances between adjacent points of the plurality of historical trajectory points and corresponding ones of the radius hypothesis circular trajectories comprises:
determining an initial global optimal radius based on the curvature of the driving track of the vehicle in the previous period;
calculating the distance from each point in a plurality of historical track points to a circular track corresponding to the initial global optimal radius based on the initial global optimal radius;
acquiring a difference absolute value between adjacent points in the plurality of historical track points and a circumferential track distance corresponding to the initial global optimal radius; and
and calculating the average value of the absolute values of the difference values, and judging whether the target running track corresponding to the corresponding radius hypothesis in the group of radius hypotheses is good or bad.
5. The method of claim 4, wherein selecting an optimal radius hypothesis from the set of radius hypotheses based on differences in distances between adjacent points of the plurality of historical trajectory points and corresponding circular trajectories of the radius hypotheses comprises:
sequentially calculating an average value of the absolute difference values of all track points in the plurality of historical track points to the radius hypothesis circular track corresponding to each radius hypothesis in the group of radius hypotheses; and
determining the radius hypothesis corresponding to the minimum of the averages as the optimal radius hypothesis.
6. The method of claim 5, wherein the method comprises:
and calculating the average value of the difference values of all the points in the plurality of historical track points to the circular track corresponding to the optimal radius hypothesis.
7. The method of claim 6, wherein determining at least one of a locally optimal radius and a globally optimal radius associated with the target travel trajectory based on the selected optimal radius hypothesis comprises:
determining at least one of a local optimal radius and a global optimal radius associated with the target travel track based on the difference average; and
and obtaining the target running track based on at least one of the local optimal radius and the global optimal radius.
8. An apparatus for determining a vehicle travel track, comprising:
a preceding vehicle history travel track determination module configured to determine a set of history travel tracks corresponding to each of a plurality of preceding vehicles, wherein the set of history travel tracks includes a plurality of history track points;
a radius hypothesis determination module configured to determine a set of radius hypotheses associated with a target travel trajectory of the vehicle based on one or more travel parameters associated with the travel trajectory of the vehicle, each radius hypothesis of the set of radius hypotheses corresponding to a respective radius hypothesis circular trajectory;
an optimal hypothesis radius selection module configured to select an optimal radius hypothesis from a set of radius hypotheses based on distance differences between adjacent points of a plurality of historical trajectory points and corresponding radius hypothesis circular trajectories; and
a target optimal radius determination module configured to determine at least one of a locally optimal radius and a globally optimal radius associated with the target travel trajectory based on the selected optimal radius hypothesis.
9. An electronic device, the device comprising:
one or more processors; and
storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310113398.9A CN115973162A (en) | 2023-02-14 | 2023-02-14 | Method, apparatus, electronic device, and medium for determining vehicle travel track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310113398.9A CN115973162A (en) | 2023-02-14 | 2023-02-14 | Method, apparatus, electronic device, and medium for determining vehicle travel track |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115973162A true CN115973162A (en) | 2023-04-18 |
Family
ID=85970368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310113398.9A Pending CN115973162A (en) | 2023-02-14 | 2023-02-14 | Method, apparatus, electronic device, and medium for determining vehicle travel track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115973162A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108919802A (en) * | 2018-07-04 | 2018-11-30 | 百度在线网络技术（北京）有限公司 | Unmanned vehicle traveling and device |
| CN112665590A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle track determination method and device, electronic equipment and computer storage medium |
| CN113022580A (en) * | 2021-03-17 | 2021-06-25 | 地平线(上海)人工智能技术有限公司 | Trajectory prediction method, trajectory prediction device, storage medium and electronic equipment |
| CN113353078A (en) * | 2021-06-24 | 2021-09-07 | 中汽创智科技有限公司 | Method and device for determining automatic following track without lane line |
| CN113978462A (en) * | 2021-11-12 | 2022-01-28 | 北京易航远智科技有限公司 | Main target screening method, track planning method and system of adaptive cruise system |
| CN114735002A (en) * | 2022-03-16 | 2022-07-12 | 广州小鹏自动驾驶科技有限公司 | Steering control method and device for vehicle, vehicle and storage medium |
| CN114758502A (en) * | 2022-04-29 | 2022-07-15 | 北京百度网讯科技有限公司 | Double-vehicle combined track prediction method and device, electronic equipment and automatic driving vehicle |
| WO2023010928A1 (en) * | 2021-08-06 | 2023-02-09 | 上汽通用五菱汽车股份有限公司 | Vehicle following method, vehicle, and computer-readable storage medium |
-
2023
- 2023-02-14 CN CN202310113398.9A patent/CN115973162A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108919802A (en) * | 2018-07-04 | 2018-11-30 | 百度在线网络技术（北京）有限公司 | Unmanned vehicle traveling and device |
| CN112665590A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle track determination method and device, electronic equipment and computer storage medium |
| CN113022580A (en) * | 2021-03-17 | 2021-06-25 | 地平线(上海)人工智能技术有限公司 | Trajectory prediction method, trajectory prediction device, storage medium and electronic equipment |
| CN113353078A (en) * | 2021-06-24 | 2021-09-07 | 中汽创智科技有限公司 | Method and device for determining automatic following track without lane line |
| WO2023010928A1 (en) * | 2021-08-06 | 2023-02-09 | 上汽通用五菱汽车股份有限公司 | Vehicle following method, vehicle, and computer-readable storage medium |
| CN113978462A (en) * | 2021-11-12 | 2022-01-28 | 北京易航远智科技有限公司 | Main target screening method, track planning method and system of adaptive cruise system |
| CN114735002A (en) * | 2022-03-16 | 2022-07-12 | 广州小鹏自动驾驶科技有限公司 | Steering control method and device for vehicle, vehicle and storage medium |
| CN114758502A (en) * | 2022-04-29 | 2022-07-15 | 北京百度网讯科技有限公司 | Double-vehicle combined track prediction method and device, electronic equipment and automatic driving vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11042157B2 (en) | Lane/object detection and tracking perception system for autonomous vehicles | |
| CN111771141B (en) | LIDAR positioning for solution inference using 3D CNN network in autonomous vehicles | |
| CN111771135B (en) | LIDAR positioning using RNN and LSTM for time smoothing in autonomous vehicles | |
| CN113168708B (en) | Lane line tracking method and device | |
| WO2020154970A1 (en) | Deep learning–based feature extraction for lidar localization of autonomous driving vehicles | |
| CN109278752B (en) | Energy optimization control method for plug-in hybrid electric vehicle based on cooperative sensing | |
| CN113267199B (en) | Method and device for planning driving track | |
| US11697412B2 (en) | Collision monitoring using statistic models | |
| US11648939B2 (en) | Collision monitoring using system data | |
| CN113916246A (en) | Unmanned obstacle avoidance path planning method and system | |
| CN112534483A (en) | Method and device for predicting vehicle exit | |
| CN114882457A (en) | Model training method, lane line detection method and equipment | |
| Liu et al. | Hercules: An autonomous logistic vehicle for contact-less goods transportation during the COVID-19 outbreak | |
| US20200097005A1 (en) | Object detection device, object detection method, and vehicle controller | |
| CN116523970B (en) | Dynamic three-dimensional target tracking method and device based on secondary implicit matching | |
| CN115546781A (en) | Point cloud data clustering method and device | |
| CN113515111B (en) | Vehicle obstacle avoidance path planning method and device | |
| CN112699575A (en) | Method and system for measuring and calculating relative position in virtual vehicle test platform | |
| US11328596B2 (en) | Parking prediction | |
| EP4148599A1 (en) | Systems and methods for providing and using confidence estimations for semantic labeling | |
| CN115973162A (en) | Method, apparatus, electronic device, and medium for determining vehicle travel track | |
| Ren et al. | Intelligent path planning and obstacle avoidance algorithms for autonomous vehicles based on enhanced rrt algorithm | |
| CN113753038A (en) | Trajectory prediction method and apparatus, electronic device and storage medium | |
| CN114730521A (en) | Collision monitoring using statistical models | |
| Shetty et al. | Road slope prediction and vehicle dynamics control for autonomous vehicles |
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 |