CN109910880A - Method, apparatus, storage medium and the terminal device of vehicle behavior planning - Google Patents

Method, apparatus, storage medium and the terminal device of vehicle behavior planning Download PDF

Info

Publication number
CN109910880A
CN109910880A CN201910172670.4A CN201910172670A CN109910880A CN 109910880 A CN109910880 A CN 109910880A CN 201910172670 A CN201910172670 A CN 201910172670A CN 109910880 A CN109910880 A CN 109910880A
Authority
CN
China
Prior art keywords
obstacle target
candidate
vehicular behavior
main vehicle
behavior
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
CN201910172670.4A
Other languages
Chinese (zh)
Other versions
CN109910880B (en
Inventor
潘屹峰
杨旭光
詹锟
夏中谱
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.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201910172670.4A priority Critical patent/CN109910880B/en
Publication of CN109910880A publication Critical patent/CN109910880A/en
Application granted granted Critical
Publication of CN109910880B publication Critical patent/CN109910880B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The present invention proposes method, apparatus, storage medium and the terminal device of a kind of vehicle behavior planning, wherein, the described method includes: according to the current state of main vehicle, it is determined to influence at least one first obstacle target of the main vehicle, and the first prediction is carried out to the motion profile of at least one first obstacle target;According to first prediction as a result, the candidate vehicular behavior that the planning main vehicle is able to carry out;Current state based on the candidate vehicular behavior and at least one first obstacle target, it is determined to influence at least one second obstacle target of the main vehicle, and the second prediction is carried out to the motion profile of at least one second obstacle target based on the candidate vehicular behavior;And according to second prediction as a result, determining the pending vehicular behavior of the main vehicle from the candidate vehicular behavior.Using the present invention, the efficiency and order of accuarcy of prediction can effectively improve.

Description

Method, apparatus, storage medium and the terminal device of vehicle behavior planning
Technical field
The present invention relates to field of computer technology more particularly to a kind of method, apparatus of vehicle behavior planning, storage medium And terminal device.
Background technique
When vehicle launch automatic driving mode is driven, driver is generally woth no need to the input operated, automatically The sensor that vehicle can be loaded by vehicle itself is driven, the position of other vehicles and barrier in running environment is obtained It sets, come the vehicular behavior planning wheelpath of the automatic driving vehicle in following one section or taking.For example, accelerating, slowing down, becoming Road, turn etc..In existing automatic driving vehicle, predicting unit for being predicted track of vehicle with for automatic The planning unit that the traveling of driving vehicle is planned is two units independent of each other, in the optimum prediction that predicting unit provides As a result after, planning unit can be planned the driving behavior of vehicle based on the optimal result.
But the vehicular behavior of the planning of automatic driving vehicle, it is generally based on other in automatic Pilot running environment The actual travel behavior of vehicle is planned.In actual scene, the behavior of vehicle and track necessarily will affect other vehicles Vehicular behavior or wheelpath.That is, the variation of motion profile can also occur with the variation of running environment for other vehicles.It is existing The path planning of technology is carried out based on the virtual condition of vehicle each in environment, pedestrian etc., is obtained based on the optimal of actual road conditions Path.However, in the prior art, there is no the influences for considering that the behavior of automatic driving vehicle generates other vehicles, and only It is only the agenda and route of road participant to be monitored from actual state, and then carry out to the behavior of automatic driving vehicle Planning.Therefore, the scheme of the prior art may due to not accounting for influence of the behavior of automatic driving vehicle to other vehicles and The vehicular behavior for leading to the problem of planning is unreasonable.
Summary of the invention
The embodiment of the present invention provides method, apparatus, storage medium and the terminal device of a kind of vehicle behavior planning, to solve Or alleviate above one or more technical problems in the prior art.
In a first aspect, the embodiment of the invention provides a kind of methods of vehicle behavior planning, comprising:
According to the current state of main vehicle, it is determined to influence at least one first obstacle target of the main vehicle, and right The motion profile of at least one first obstacle target carries out the first prediction;
According to first prediction as a result, the candidate vehicular behavior that the planning main vehicle is able to carry out;
Based on the current state of the candidate vehicular behavior and at least one first obstacle target, it is determined to influence At least one second obstacle target of the main vehicle, and based on the candidate vehicular behavior at least one described second obstacle The motion profile of target carries out the second prediction;And
According to second prediction as a result, determining the pending driving row of the main vehicle from the candidate vehicular behavior For.
In one embodiment, at least one described first obstacle target and at least one described second obstacle target energy It is enough identical.
In one embodiment, it is described first prediction and it is described second prediction include:
Obtain history travelling data;
According to the history travelling data, each practical vehicular behavior is assessed;
According to the assessment as a result, determining the vehicular behavior of obstacle target;And
According to the vehicular behavior and current state of the obstacle target, the motion profile of the obstacle target is predicted,
Wherein, the obstacle target includes at least one described first obstacle target and at least one described second obstacle mesh Mark.
In one embodiment, the history travelling data include: the main vehicle and obstacle target have with it is current The practical vehicular behavior of in the case of state same state, the described obstacle target.
In one embodiment, described according to second prediction as a result, being determined from the candidate vehicular behavior The pending vehicular behavior of main vehicle, comprising:
Based on each of described candidate vehicular behavior and its corresponding second prediction result, respectively described in assessment The performance indicator of main vehicle;
Based on the performance indicator of each main vehicle, select one in the candidate vehicular behavior so that the main vehicle is held Row.
In one embodiment, the performance indicator based on each main vehicle selects one in the candidate vehicular behavior It is a for the main Che Zhihang, comprising:
It is given a mark based on the performance indicator of each main vehicle to corresponding candidate vehicular behavior;And
According to the marking to each candidate vehicular behavior, select one in the candidate vehicular behavior for the master Vehicle executes.
Second aspect, the embodiment of the present invention provide a kind of device of vehicle behavior planning, comprising:
First prediction module, for the current state according to main vehicle, be determined to influence the main vehicle at least one One obstacle target, and the first prediction is carried out to the motion profile of at least one first obstacle target;
Planning module, for predicting according to described first as a result, the candidate row garage that the planning main vehicle is able to carry out For;
Second prediction module, for current based on the candidate vehicular behavior and at least one first obstacle target State is determined to influence at least one second obstacle target of the main vehicle, and based on the candidate vehicular behavior to institute The motion profile for stating at least one the second obstacle target carries out the second prediction;And
Determining module, for predicting according to described second as a result, determining the main vehicle from the candidate vehicular behavior Pending vehicular behavior.
In one embodiment, at least one described first obstacle target and at least one described second obstacle target energy It is enough same or different.
In one embodiment, first prediction module and second prediction module respectively include:
Acquiring unit, for obtaining history travelling data;
Assessment unit, for assessing each practical vehicular behavior according to the history travelling data;
Behavior determination unit, for according to the assessment as a result, determine obstacle target vehicular behavior;And
Obstacle predicting unit predicts the obstacle mesh for the vehicular behavior and current state according to the obstacle target Target motion profile,
Wherein, the obstacle target is at least one described first obstacle target and at least one described second obstacle target In one.
In one embodiment, the history travelling data include: the main vehicle and obstacle target have with it is current In the case of state same state, the practical vehicular behavior of the obstacle target.
In one embodiment, the determining module includes:
Performance indicator assessment unit, for based on each of described candidate vehicular behavior and its corresponding described second Prediction result assesses the performance indicator of the main vehicle respectively;
Selecting unit, for the performance indicator based on each main vehicle, select one in the candidate vehicular behavior with For the main Che Zhihang.
In one embodiment, the selecting unit includes marking unit, is referred to for the performance based on each main vehicle It marks to give a mark to corresponding candidate vehicular behavior;And
The selecting unit selects one in the candidate vehicular behavior according to the marking to each candidate vehicular behavior It is a for the main Che Zhihang.
The third aspect, the embodiment of the invention provides a kind of device of vehicle behavior planning, the function of described device can be with By hardware realization, corresponding software realization can also be executed by hardware.The hardware or software include it is one or more with The corresponding module of above-mentioned function.
It include processor and memory, the memory in the structure of vehicle behavior planning in a possible design Device for vehicle behavior planning executes the program of above-mentioned vehicle behavior planning, the processor is configured to for executing institute State the program stored in memory.The device of the vehicle behavior planning can also include communication interface, advise for vehicle behavior The device and other equipment or communication drawn.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, for vehicle behavior planning Computer software instructions used in device, including program involved in the method for executing above-mentioned vehicle behavior planning.
Any one technical solution in above-mentioned technical proposal have the following advantages that or the utility model has the advantages that
The embodiment of the present invention determines the vehicular behavior of main vehicle by predicting at least twice.Tentative prediction obstacle target first Wheelpath, the candidate vehicular behavior for planning main vehicle is then carried out using the wheelpath of tentative prediction.At this point, in main vehicle In the case where being not carried out any vehicular behavior, that is, the case where obstacle target does not know the behavior that main vehicle will be taken completely Under, determine new obstacle target again respectively based on each candidate vehicular behavior, and predict based on each candidate vehicular behavior Then the wheelpath of new obstacle target recycles these tracks to go to assess the feasibility of each candidate vehicular behavior, Cong Zhongxuan Select a suitable candidate vehicular behavior vehicular behavior pending as main vehicle.In this way, predetermined speed not only can be improved, The security performance of main vehicle traveling can be improved.Certainly, the embodiment of the present invention can be applied in multiple circular prediction, and most The pending vehicular behavior of main vehicle is determined in a prediction result afterwards.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing description Schematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is further Aspect, embodiment and feature, which will be, to be readily apparent that.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 is the flow diagram of one embodiment of the method for vehicle behavior planning provided by the invention.
Fig. 2 is the flow diagram of one embodiment of the prediction process of motion profile provided by the invention.
Fig. 3 is the flow diagram of one embodiment of the selection course of vehicular behavior provided by the invention.
Fig. 4 is the structural schematic diagram of one embodiment of the device of vehicle behavior planning provided by the invention.
Fig. 5 is the structural schematic diagram of one embodiment of terminal device provided by the invention.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes. Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Referring to Fig. 1, the embodiment of the invention provides a kind of methods of vehicle behavior planning.The present embodiment can be by following Motor vehicle executes, comprising: the motor vehicle of the two-wheeleds such as electric bicycle, motorcycle, the four-wheels such as electronic, mixed dynamic or gasoline it is motor-driven The transit equipments such as vehicle and aircraft, steamer.The present embodiment may include step S100 to S400, as follows:
S100 is determined to influence at least one first obstacle target of main vehicle, and right according to the current state of main vehicle The motion profile of at least one the first obstacle target carries out the first prediction.
In the present embodiment, main vehicle can be described as automatic driving vehicle, can be also simply referred to as vehicle.It can be in automatic Pilot mould Formula downward driving may include that driver also may not include driver in vehicle.If including driver in vehicle, pressed in vehicle When driving according to automatic driving mode, driver can not input driving instruction or only input a small amount of driving instruction.Wherein, vehicle It can be travelled in following running environment, such as expressway, viaduct, national highway, mountainous region or winding road etc..In these traveling rings In border, other obstacle targets relative to main vehicle may include the vehicles such as motor vehicle, electric vehicle, bicycle, and can also wrap Include pedestrian, static-obstacle thing.Static-obstacle thing may include traffic sign, traffic light, lane line, building around lane Build object etc..Wherein, other vehicles in running environment in addition to main vehicle can be travelled according to automatic driving mode, can also not It travels and is input operation instruction by the driver in vehicle to travel according to automatic driving mode.
Wherein, the first obstacle target refer to first prediction during determined by can influence main vehicle other vehicles, Pedestrian and static-obstacle thing etc..Second obstacle target refers to its identified that can influence main vehicle during the second prediction His vehicle, pedestrian and static-obstacle thing etc..N obstacle target simply means to the barrier decided during corresponding prediction Hinder target.N is positive integer.Determine that the obstacle target come can be identical or different each time.
The current state of vehicle may include vehicle in the speed at current time, corner, steering, position, place vehicle Road etc..
The motion profile of obstacle target may include obstacle target in the movement velocity at current time and one section of future In movement velocity, vehicle is in the trace informations such as the position at current time and the position in following a period of time.Fortune Dynamic rail mark can also include the probability for the vehicular behavior that vehicle executes.Wherein, vehicular behavior may include accelerate, slow down, turning, It is incorporated to left-lane, is incorporated to the behaviors such as right lane.
Illustratively, if it is determined that the obstacle target for influencing main vehicle traveling includes: obstacle target A, obstacle target B and obstacle Target C.Then, predict obstacle target A, obstacle target B and obstacle target C the vehicular behavior of following a period of time probability or Trace information.By taking obstacle target A as an example, probability that obstacle target A gives it the gun in following 1 minute and Reduced Speed Now Probability.For example, the probability to give it the gun is 80%, the probability of Reduced Speed Now is 20%.
S200 is predicting according to first as a result, planning the candidate vehicular behavior that main vehicle is able to carry out.
Wherein, the result of the first prediction may include the motion profile of each first obstacle target.Main vehicle is planning that it can When the candidate vehicular behavior of execution, in addition to reference to first prediction as a result, can also in conjunction with main vehicle current state and main vehicle Driving purpose.Wherein, driving purpose may include acceleration, deceleration, straight trip, turning and the behaviors such as road.It also may include reaching To some final position.
Therefore, in some embodiments, the current location planning road in the final position and main vehicle that need to reach according to main vehicle Line can determine one or more approach positions.Then, according to main vehicle current time position and speed, need by way of Position, each first obstacle target motion profile, to carry out planning the candidate vehicular behavior that main vehicle is able to carry out.Wherein, candidate Vehicular behavior may include accelerating, deceleration, straight trip, turning, the simultaneously behaviors such as road.
In some embodiments, it can also determine that main vehicle executes each driving according to the motion profile of each first obstacle target The risk of behavior.The risk that each vehicular behavior is executed according to main vehicle determines the candidate vehicular behavior that main vehicle is able to carry out.
Illustratively, if it is determined that the first obstacle target include vehicle A, B and C, the result of the first prediction includes vehicle A, B and C respectively in following 1 minute the probability to give it the gun and Reduced Speed Now probability, then according to vehicle A, B and C probability Data drive into the risk of left-lane to calculate main vehicle within 1 minute future.Finally planned main vehicle 1 minute following according to risk The behaviors such as left-lane inside whether is driven into, whether accelerates or whether slows down.Wherein, candidate vehicular behavior may include one or more It is a.
S300, the current state based on candidate vehicular behavior He at least one the first obstacle target are determined to influence master At least one second obstacle target of vehicle, and based on candidate vehicular behavior to the motion profile of determining each second obstacle target Carry out the second prediction.
Automatic driving vehicle, i.e., main vehicle are selecting different candidate vehicular behaviors to carry out that when driving, difference can be influenced Obstacle target traveling, and there is also the subsequent travelings that different obstacle targets will influence whether automatic driving vehicle.Cause This is determined to influence automatic driving vehicle again for each candidate vehicular behavior of automatic driving vehicle selection The obstacle target of traveling, i.e. the second obstacle target.And the wheelpath for the obstacle target that prediction respectively newly determines again, i.e., Identified second obstacle target is corresponded to it for each candidate's vehicular behavior carries out the second prediction.Wherein, first is pre- Survey and second predict used by prediction technique can be it is same or similar, the main distinction be predict object difference with And second prediction process also need to consider the candidate vehicular behavior of automatic driving vehicle.The object of first prediction is the first obstacle mesh The object of mark, the second prediction is the second obstacle target.
During the second prediction, main vehicle can inform other main vehicles of obstacle target of running environment in a specified pattern The candidate vehicular behavior of selection.At this point, other obstacle targets can after learning the candidate vehicular behavior of main vehicle, acceptor's vehicle It influences and readjusts motion profile.At this point, the obstacle target for influencing main vehicle traveling changes and motion profile also occurs Change.It is thus necessary to determine that influence main vehicle traveling the second obstacle target and to the motion profile of the second obstacle target into Row prediction, i.e., the second prediction.Wherein, specific form may include V2V (vehicletovehicle, vehicle is to vehicle) mode Or traditional turn signal mode etc..
It should be noted that V2V mode needs a wireless network, letter is mutually transferred between vehicle over this network Breath, tells what other side oneself doing, these information include speed, position, steering direction, brake etc..V2V technology uses Dedicated short-range communication (Dedicated Short Range Communications, DSRC), by similar FCC (Federal Communications Commission, Federal Communications Commission) and ISO (International Organization For Standardization, International Organization for standardization) the standard set up of mechanism.Sometimes it can be described as WiFi net Network, because the frequency that may be used is 5.9GHz, this is also the frequency that WiFi is used.But more precisely, DSRC It is class WiFi network, its coverage area is up to 300 meters.V2V is a kind of mesh network, node (vehicle, intelligence in network Traffic lights etc.) it can emit, capture simultaneously forward signal.The jump of 5-10 node can collect the traffic outside one mile on network Situation.This has the enough reply time for most drivers.
In the present embodiment, the first obstacle target is also possible to similar or adopts with the determination process of the second obstacle target With identical determining method.Wherein, the determination process of the second obstacle target also needs to consider the candidate vehicular behavior of main vehicle.True Relativeness, main vehicle and barrier when the obstacle target of fixed main vehicle, in addition to considering main vehicle place lane and obstacle target place lane Hinder except the relationships such as relative distance and the relative velocity of target, it can also be in conjunction with traffic law to the movement rail of main vehicle and obstacle vehicle The limitation of mark.For example, whether the speed limit situation in place lane, place lane allow doubling, turn left and turn right.
Illustratively, it is assumed that the candidate vehicular behavior doubling of main vehicle, the road where main vehicle include two lanes.So, It can be based on the requirement " not influencing the normally travel of rear car " for handing over rule, to determine the obstacle vehicle for influencing main vehicle.For example, if main vehicle The road at place includes two lanes, during doubling, then needs to consider that " People's Republic of China Road Traffic Safety Law is real Apply regulations " the 44th article: there are 2 articles or more car lanes at equidirectional stroke of road, left side is express lane, and right side is at a slow speed Lane.It should be travelled according to speed as defined in express lane in the motor vehicle of express lane traveling, not up to express lane provides Travel speed, should in lanes at a slow speed.Motorcycle should be in rightmost side lanes.There is traffic sign to indicate traveling Speed, it is travelled according to the travel speed indicated.When the motor vehicle in lane surmounts front truck at a slow speed, express lane row can be borrowed It sails.
S400, according to the second prediction as a result, determining the pending vehicular behavior of main vehicle from candidate vehicular behavior.
In some embodiments, the movement rail of the respective second obstacle target based on determined by different candidate vehicular behaviors Mark, respectively each candidate vehicular behavior determine its risk factor or safety coefficient.Then, the risk based on each candidate vehicular behavior Coefficient or safety coefficient therefrom select the candidate vehicular behavior most beneficial for main vehicle, using the vehicular behavior pending as main vehicle.
In some embodiments, it can recycle and execute above-mentioned steps S300.Assuming that being currently n-th prediction, i.e. N is pre- It surveys.According to the candidate vehicular behavior of the preceding main vehicle once determined and the current state of the preceding obstacle target once determined, energy is determined Enough influence at least one obstacle target of main vehicle, i.e. N obstacle target.And based on the candidate row garage of the preceding main vehicle once determined N prediction is carried out for the motion profile to determining each N obstacle target.The condition of convergence of circular prediction are as follows: currently determine Obstacle target is identical as preceding once determining obstacle target, and currently determining obstacle target prediction result and it is preceding it is primary really The same or similar degree of the prediction result of fixed obstacle target meets the similar threshold value of setting.If meeting the condition of convergence, basis Current predictive as a result, determining pending vehicular behavior from the candidate vehicular behavior currently determined.If being unsatisfactory for restraining Condition then continues to execute the operation of similar above-mentioned steps S300, until meeting the condition of convergence.
The embodiment of the present invention can use the prediction of the motion profile of the obstacle target above at least twice, to determine main vehicle Vehicular behavior, predetermined speed not only can be improved, can also be improved the security performance of main vehicle traveling.In the movement for predicting main vehicle During track if it is considered that obstacle destination number it is very few or less, then although forecasting efficiency can be improved, predict main vehicle The prediction order of accuarcy of vehicular behavior can reduce accordingly.But if according to the repeatedly prediction back and forth of the present embodiment, not only effectively The efficiency for predicting that main garage is is improved, also ensures the order of accuarcy for predicting that main garage is.
It will be described by way the process for being determined to influence the obstacle target of main vehicle below.Wherein, the first obstacle target and Two obstacle targets can be carried out as follows prediction, comprising:
If main vehicle is biased to right lane in left-lane, current corner, the obstacle target that can influence main vehicle is included in It is arranged on left-lane or right lane before main vehicle and is arranged with main vehicle apart from nearest vehicle, on left-lane or right lane Apart from nearest vehicle behind main vehicle and with main vehicle.Meanwhile also judging whether the distance between these vehicles and main vehicle are pacifying Within full distance.If this vehicle excluded within the obstacle target that can influence main vehicle, within safe distance if not Within safe distance, then this vehicle is still judged to influence the obstacle target of main vehicle.
If main vehicle is kept straight in left-lane, current holding along lane, the obstacle target that can influence main vehicle is included in a left side Be arranged on lane before main vehicle and be arranged in main vehicle apart from nearest vehicle, on left-lane behind main vehicle and with main vehicle Apart from nearest vehicle.Meanwhile also judging the distance between these vehicles and main vehicle whether within safe distance.If pacifying Within full distance, then this vehicle is excluded within the obstacle target that can influence main vehicle, if not within safe distance, this Vehicle is still judged to influence the obstacle target of main vehicle.For the vehicle on right lane, it can be determined that on right lane with main vehicle The distance between vehicle not within safe distance whether have left rotaring signal lamp bright, if so, this vehicle is also then included in energy Enough influence the obstacle target of main vehicle.
It in some embodiments, can be according to the current state and each obstacle target of main vehicle after determining obstacle target Current state, use trained trajectory predictions algorithm predicts the motion profile of each obstacle target.Wherein, it transports Dynamic rail mark may include probability, the trace information of some vehicular behavior etc. of vehicle selection.
In some embodiments, the preceding obstacle target once predicted and the obstacle target once predicted afterwards can be identical It is also possible to different.I.e. in the above-described embodiments, in the step s 100 determined by the first obstacle target and in step Second obstacle target determined by S300 can be identical or different.For example, the identified barrier in preceding primary prediction Hindering target includes vehicle A, B and C, and the obstacle target determined in current predictive includes vehicle A, B and C, then this is determined twice Obstacle target it is identical.For another example, identified obstacle target includes vehicle A, B and C in preceding primary prediction, in current predictive The obstacle target of middle determination includes vehicle A, B, C and D, then this twice determined by obstacle target it is different.
In some embodiments, referring to fig. 2, the fixed obstacle target of prediction of above-mentioned steps S100 and step S300 The process of wheelpath may include step S110 to step S140, as follows:
S110 obtains history travelling data.
S120 assesses each practical vehicular behavior according to history travelling data.
S130, according to assessment as a result, determining the vehicular behavior of obstacle target.
S140 predicts the motion profile of obstacle target according to the vehicular behavior and current state of obstacle target.Wherein, hinder Hindering target may include the first obstacle target and the second obstacle target of above-mentioned determination.And if the present embodiment includes N pre- It surveys, N > 2, then obstacle target may include N obstacle target.
In the present embodiment, history travelling data may include main vehicle and obstacle target in the past period expert The practical vehicular behavior sailed.Due to being the motion profile for predicting obstacle target, more specifically, sieved from historical data The history travelling data selected can be with are as follows: in the case of the main vehicle and obstacle target have with current state same state , the practical vehicular behavior of the obstacle target.
Illustratively, if the current state of main vehicle is state X1, the state of obstacle target A is state X2, then acquired History travelling data should have for main vehicle state X1 and obstacle target A under vehicle condition as state X2, obstacle target A Practical vehicular behavior.History travelling data may include a large amount of similar data.
In some embodiments, it can be assessed according to probability of occurrence of each practical vehicular behavior in history travelling data Each practical vehicular behavior.Then, the probability of occurrence according to each practical vehicular behavior selects one or selection from each practical vehicular behavior Several vehicular behaviors as obstacle target.
In some embodiments, probability of occurrence of each practical vehicular behavior in history travelling data can be first determined, so The weighted value of each practical vehicular behavior is determined afterwards, and is weighted in conjunction with both weighted value and probability of occurrence, is determined each The point value of evaluation of practical vehicular behavior.Finally, the point value of evaluation according to each practical vehicular behavior, therefrom selects one or selects several Vehicular behavior of the practical vehicular behavior as this obstacle target.
In some embodiments, there is thing during travelling by obstacle target according to corresponding practical vehicular behavior Therefore probability or risk, can determine the weighted value of this practical vehicular behavior.Certainly, it if risk is excessively high, can accordingly reduce Weighted value can be improved if risk is lower in weighted value.Wherein, the definition of accident may include bring to a halt or and other Vehicle distances are excessively close etc..
Illustratively, it is assumed that history travelling data includes 100 practical vehicular behaviors, wherein including two categories: being accelerated Traveling and Reduced Speed Now.If the practical vehicular behavior to give it the gun have 80, the practical vehicular behavior of Reduced Speed Now have 20, The probability of occurrence then to give it the gun is 80%, and the frequency of occurrences of Reduced Speed Now is 20%.At this point, a possibility that judgement is given it the gun Large scale is greater than Reduced Speed Now, can determine that the vehicular behavior of obstacle vehicle is to give it the gun.
If it is determined that obstacle target is in the probability for giving it the gun with accident occurring when Reduced Speed Now, for example, obstacle Target is brought to a halt in the case where giving it the gun or the probability excessively close with other vehicle distances is 60%, corresponding weight Value is 2, and obstacle target is brought to a halt in the case where Reduced Speed Now or the probability excessively close with other vehicle distances is 10%, Corresponding weighted value is 10.The point value of evaluation then to give it the gun is 80% multiplied by 2, i.e., 1.6;The point value of evaluation of Reduced Speed Now is 20% multiplied by 10, i.e., 2.At this point, Reduced Speed Now is safer, hence, it can be determined that the vehicular behavior of this obstacle target is to slow down Traveling.
The determination of above-mentioned weighted value is merely illustrative, and the determination process of similar weighted value should also be included in the present embodiment Within the scope of.
In some embodiments, referring to Fig. 3, it may comprise steps of S410 in above-mentioned steps 400 to step 420, such as Under:
S410 assesses main vehicle based on each of candidate vehicular behavior and its corresponding second prediction result respectively Performance indicator.
S420, based on the performance indicator for the main vehicle for including in each assessment result, select one in candidate vehicular behavior with For main Che Zhihang.Any assessment result may include one or more performance indicators.
In some embodiments, it can use automatic Pilot simulation algorithm, assess the performance indicator of main vehicle.Specifically, may be used The candidate vehicular behavior of main vehicle and the corresponding second prediction result input automatic Pilot emulation of this candidate's vehicular behavior to be calculated Method is emulated, and exports the performance indicator of main vehicle emulation traveling.Performance indicator may include the safety coefficient of main vehicle, drive Body-sensing variation, the velocity variations situation of main vehicle and change in location situation etc. of the member in main vehicle.
In some embodiments, the source that can be collided based on main vehicle with the second obstacle target is by prediction The motion profile of main vehicle.The movement of main vehicle motion profile of main vehicle and the second obstacle target when executing a certain candidate vehicular behavior Track is compared, and therefrom determines the performance indicator of main vehicle.For example, being in most similar distance or most similar speed in the two When, using the performance indicator of main vehicle at this time as the performance indicator of the main vehicle of step S410.
In some embodiments, the selection course of above-mentioned steps 420 may include: each property based on vehicle main in assessment result Can index give a mark to corresponding candidate vehicular behavior;And according to the marking to each candidate vehicular behavior, choosing One in candidate vehicular behavior is selected for main Che Zhihang.
It in some embodiments, can be corresponding candidate row in conjunction with the weight of each performance indicator and each performance indicator Garage is to give a mark.For example, the weighted value of safety coefficient can be improved if main vehicle focuses on safety coefficient.If emphasis is driven The body-sensing for the person of sailing changes, and the weighted value of body-sensing variation can be improved.If main vehicle focuses on velocity variations situation or change in location feelings Its weighted value can be improved in condition.
And in some embodiments, unified standard can be used, each performance indicator is normalized or standard Change, determines the numerical value of each performance indicator.Then, the numerical value of each performance indicator is weighted summation with corresponding weighted value, it will Marking numerical value of the numerical value of acquisition as corresponding candidate vehicular behavior.
In some embodiments, the highest candidate vehicular behavior of score, the driving row pending as main vehicle be can choose For.Alternatively, can choose the candidate vehicular behavior that score meets the threshold value of setting, the vehicular behavior pending as main vehicle.
Referring to Fig. 4, the embodiment of the present invention provides a kind of device of vehicle behavior planning, comprising:
First prediction module 100 is determined to influence at least one of the main vehicle for the current state according to main vehicle First obstacle target, and the first prediction is carried out to the motion profile of at least one first obstacle target;
Planning module 200, for predicting according to described first as a result, the candidate driving that the planning main vehicle is able to carry out Behavior;
Second prediction module 300, for based on the candidate vehicular behavior and at least one first obstacle target Current state is determined to influence at least one second obstacle target of the main vehicle, and based on the candidate vehicular behavior Second prediction is carried out to the motion profile of at least one second obstacle target;And
Determining module 400, for predicting according to described second as a result, determining the master from the candidate vehicular behavior The pending vehicular behavior of vehicle.
In one embodiment, at least one described first obstacle target and at least one described second obstacle target energy It is enough same or different.
In one embodiment, first prediction module 100 and second prediction module 200 respectively include:
Acquiring unit, for obtaining history travelling data;
Assessment unit, for assessing each practical vehicular behavior according to the history travelling data;
Behavior determination unit, for according to the assessment as a result, determine obstacle target vehicular behavior;And
Obstacle predicting unit predicts the obstacle mesh for the vehicular behavior and current state according to the obstacle target Target motion profile,
Wherein, the obstacle target is at least one described first obstacle target and at least one described second obstacle target In one.
In some embodiments, the history travelling data include: the main vehicle and obstacle target have with it is current In the case of state same state, the practical vehicular behavior of the obstacle target.
In some embodiments, the determining module includes:
Performance indicator assessment unit, for based on each of described candidate vehicular behavior and its corresponding described second Prediction result assesses the performance indicator of the main vehicle respectively;
Selecting unit, for the performance indicator based on each main vehicle, select one in the candidate vehicular behavior with For the main Che Zhihang.
In some embodiments, the selecting unit includes marking unit, is referred to for the performance based on each main vehicle It marks to give a mark to corresponding candidate vehicular behavior;And
The selecting unit selects one in the candidate vehicular behavior according to the marking to each candidate vehicular behavior It is a for the main Che Zhihang.
The function of described device can also execute corresponding software realization by hardware realization by hardware.It is described Hardware or software include one or more modules corresponding with above-mentioned function.
It include processor and memory, the memory in the structure of vehicle behavior planning in a possible design Device for vehicle behavior planning executes the program that vehicle behavior is planned in above-mentioned first aspect, the processor is configured to For executing the program stored in the memory.The device of the vehicle behavior planning can also include communication interface, be used for The device and other equipment or communication of vehicle behavior planning.
The embodiment of the present invention also provides a kind of terminal device of vehicle behavior planning, as shown in figure 5, the equipment includes: to deposit Reservoir 21 and processor 22, being stored in memory 21 can be in the computer program on processor 22.Processor 22 executes calculating The method of the vehicle behavior planning in above-described embodiment is realized when machine program.The quantity of memory 21 and processor 22 can be one It is a or multiple.
The equipment further include:
Communication interface 23, for the communication between processor 22 and external equipment.
Memory 21 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-volatile Memory), a for example, at least magnetic disk storage.
If memory 21, processor 22 and the independent realization of communication interface 23, memory 21, processor 22 and communication are connect Mouth 23 can be connected with each other by bus and complete mutual communication.Bus can be industry standard architecture (ISA, Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral Component) be total Line or extended industry-standard architecture (EISA, Extended Industry Standard Component) bus etc..Always Line can be divided into address bus, data/address bus, control bus etc..Only to be indicated with a thick line in Fig. 5, but simultaneously convenient for indicating Only a bus or a type of bus are not indicated.
Optionally, in specific implementation, if memory 21, processor 22 and communication interface 23 are integrated in chip piece On, then memory 21, processor 22 and communication interface 23 can complete mutual communication by internal interface.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example Point is included at least one embodiment of the present invention or example.Moreover, particular features, structures, materials, or characteristics described It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise Clear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicating, propagating or passing Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment It sets.
The computer-readable medium of the embodiment of the present invention can be computer-readable signal media or computer-readable deposit Storage media either the two any combination.The more specific example at least (non-exclusive of computer readable storage medium List) include the following: there is the electrical connection section (electronic device) of one or more wirings, portable computer diskette box (magnetic dress Set), random access memory (RAM), read-only memory (ROM), erasable edit read-only storage (deposit by EPROM or flash Reservoir), fiber device and portable read-only memory (CDROM).In addition, computer readable storage medium can even is that Can the paper of print routine or other suitable media on it because can for example be swept by carrying out optics to paper or other media It retouches, is then edited, interprets or handled when necessary with other suitable methods electronically to obtain program, then will It is stored in computer storage.
In embodiments of the present invention, computer-readable signal media may include in a base band or as carrier wave a part The data-signal of propagation, wherein carrying computer-readable program code.The data-signal of this propagation can use a variety of Form, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media is also It can be any computer-readable medium other than computer readable storage medium, which can send, pass It broadcasts or transmits for instruction execution system, input method or device use or program in connection.Computer can The program code for reading to include on medium can transmit with any suitable medium, including but not limited to: wirelessly, electric wire, optical cable, penetrate Frequently (Radio Frequency, RF) etc. or above-mentioned any appropriate combination.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries It suddenly is the program that relevant hardware can be instructed to complete by program, which can store in a kind of computer-readable storage In medium, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould Block both can take the form of hardware realization, can also be realized in the form of software function module.If integrated module with The form of software function module is realized and when sold or used as an independent product, also can store computer-readable at one In storage medium.Storage medium can be read-only memory, disk or CD etc..
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement, these It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims It is quasi-.

Claims (14)

1. a kind of method of vehicle behavior planning characterized by comprising
According to the current state of main vehicle, it is determined to influence at least one first obstacle target of the main vehicle, and to described The motion profile of at least one the first obstacle target carries out the first prediction;
According to first prediction as a result, the candidate vehicular behavior that the planning main vehicle is able to carry out;
Based on the current state of the candidate vehicular behavior and at least one first obstacle target, it is determined to described in influence At least one second obstacle target of main vehicle, and based on the candidate vehicular behavior at least one described second obstacle target Motion profile carry out second prediction;And
According to second prediction as a result, determining the pending vehicular behavior of the main vehicle from the candidate vehicular behavior.
2. the method as described in claim 1, which is characterized in that at least one described first obstacle target and it is described at least one Second obstacle target can be identical.
3. the method as described in claim 1, which is characterized in that first prediction and second prediction include:
Obtain history travelling data;
According to the history travelling data, each practical vehicular behavior is assessed;
According to the assessment as a result, determining the vehicular behavior of obstacle target;And
According to the vehicular behavior and current state of the obstacle target, the motion profile of the obstacle target is predicted,
Wherein, the obstacle target includes at least one described first obstacle target and at least one described second obstacle target.
4. method as claimed in claim 3, which is characterized in that the history travelling data includes: in the main vehicle and obstacle Target has the practical vehicular behavior with obstacle target in the case of current state same state, described.
5. the method as described in claim 1, feature is according to second prediction as a result, from the candidate row garage For the pending vehicular behavior of the middle determination main vehicle, comprising:
Based on each of described candidate vehicular behavior and its corresponding second prediction result, the main vehicle is assessed respectively Performance indicator;
Based on the performance indicator of each main vehicle, select one in the candidate vehicular behavior for the main Che Zhihang.
6. method as claimed in claim 5, feature is in selecting the candidate row based on the performance indicator of each main vehicle Garage be in one for the main Che Zhihang, comprising:
It is given a mark based on the performance indicator of each main vehicle to corresponding candidate vehicular behavior;And
According to the marking to each candidate vehicular behavior, select one in the candidate vehicular behavior so that the main vehicle is held Row.
7. a kind of device of vehicle behavior planning characterized by comprising
First prediction module is determined to influence at least one first barrier of the main vehicle for the current state according to main vehicle Hinder target, and the first prediction is carried out to the motion profile of at least one first obstacle target;
Planning module, for predicting according to described first as a result, the candidate vehicular behavior that the planning main vehicle is able to carry out;
Second prediction module, for the current shape based on the candidate vehicular behavior and at least one first obstacle target State is determined to influence at least one second obstacle target of the main vehicle, and based on the candidate vehicular behavior to described The motion profile of at least one the second obstacle target carries out the second prediction;And
Determining module, for predicting according to described second as a result, determining that the main vehicle waits holding from the candidate vehicular behavior Capable vehicular behavior.
8. device as claimed in claim 7, which is characterized in that at least one described first obstacle target and it is described at least one Second obstacle target can be same or different.
9. device as claimed in claim 7, which is characterized in that first prediction module and second prediction module difference Include:
Acquiring unit, for obtaining history travelling data;
Assessment unit, for assessing each practical vehicular behavior according to the history travelling data;
Behavior determination unit, for according to the assessment as a result, determine obstacle target vehicular behavior;And
Obstacle predicting unit predicts the obstacle target for the vehicular behavior and current state according to the obstacle target Motion profile,
Wherein, the obstacle target is at least one described first obstacle target and at least one described second obstacle target One.
10. device as claimed in claim 9, which is characterized in that the history travelling data includes: in the main vehicle and obstacle Target have in the case of current state same state, the practical vehicular behavior of the obstacle target.
11. device as claimed in claim 7, feature is in the determining module includes:
Performance indicator assessment unit, for based on each of described candidate vehicular behavior and its corresponding second prediction As a result, assessing the performance indicator of the main vehicle respectively;
Selecting unit selects one in the candidate vehicular behavior for institute for the performance indicator based on each main vehicle State main Che Zhihang.
12. device as claimed in claim 11, feature is in the selecting unit includes marking unit, for being based on each institute The performance indicator of main vehicle is stated to give a mark to corresponding candidate vehicular behavior;And
The selecting unit according to the marking to each candidate vehicular behavior, select one in the candidate vehicular behavior with For the main Che Zhihang.
13. a kind of terminal device for realizing vehicle behavior planning, which is characterized in that the terminal device includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors Realize such as method as claimed in any one of claims 1 to 6.
14. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the program is held by processor Such as method as claimed in any one of claims 1 to 6 is realized when row.
CN201910172670.4A 2019-03-07 2019-03-07 Vehicle behavior planning method and device, storage medium and terminal equipment Active CN109910880B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910172670.4A CN109910880B (en) 2019-03-07 2019-03-07 Vehicle behavior planning method and device, storage medium and terminal equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910172670.4A CN109910880B (en) 2019-03-07 2019-03-07 Vehicle behavior planning method and device, storage medium and terminal equipment

Publications (2)

Publication Number Publication Date
CN109910880A true CN109910880A (en) 2019-06-21
CN109910880B CN109910880B (en) 2021-06-29

Family

ID=66963741

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910172670.4A Active CN109910880B (en) 2019-03-07 2019-03-07 Vehicle behavior planning method and device, storage medium and terminal equipment

Country Status (1)

Country Link
CN (1) CN109910880B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110908375A (en) * 2019-11-14 2020-03-24 北京三快在线科技有限公司 Method and device for acquiring lane change decision information, storage medium and vehicle
CN111123933A (en) * 2019-12-24 2020-05-08 华为技术有限公司 Vehicle track planning method and device, intelligent driving area controller and intelligent vehicle
CN116499487A (en) * 2023-06-28 2023-07-28 新石器慧通(北京)科技有限公司 Vehicle path planning method, device, equipment and medium
CN116946089A (en) * 2023-09-20 2023-10-27 深圳市蓝鲸智联科技股份有限公司 Intelligent brake auxiliary system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105549597A (en) * 2016-02-04 2016-05-04 同济大学 Unmanned vehicle dynamic path programming method based on environment uncertainty
CN105573323A (en) * 2016-01-12 2016-05-11 福州华鹰重工机械有限公司 automatic driving track generation method and apparatus
CN105599764A (en) * 2014-11-12 2016-05-25 现代自动车株式会社 Driving path planning apparatus and method for autonomous vehicle
CN107339997A (en) * 2016-05-03 2017-11-10 现代自动车株式会社 The path planning apparatus and method of autonomous vehicle
US20180261093A1 (en) * 2017-03-07 2018-09-13 Denso International America, Inc. Inference-Aware Motion Planning
CN108693878A (en) * 2017-04-06 2018-10-23 丰田自动车株式会社 Advance route setting device and advance route setting method
CN108875998A (en) * 2018-04-20 2018-11-23 北京智行者科技有限公司 A kind of automatic driving vehicle method and system for planning

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105599764A (en) * 2014-11-12 2016-05-25 现代自动车株式会社 Driving path planning apparatus and method for autonomous vehicle
CN105573323A (en) * 2016-01-12 2016-05-11 福州华鹰重工机械有限公司 automatic driving track generation method and apparatus
CN105549597A (en) * 2016-02-04 2016-05-04 同济大学 Unmanned vehicle dynamic path programming method based on environment uncertainty
CN107339997A (en) * 2016-05-03 2017-11-10 现代自动车株式会社 The path planning apparatus and method of autonomous vehicle
US20180261093A1 (en) * 2017-03-07 2018-09-13 Denso International America, Inc. Inference-Aware Motion Planning
CN108693878A (en) * 2017-04-06 2018-10-23 丰田自动车株式会社 Advance route setting device and advance route setting method
CN108875998A (en) * 2018-04-20 2018-11-23 北京智行者科技有限公司 A kind of automatic driving vehicle method and system for planning

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110908375A (en) * 2019-11-14 2020-03-24 北京三快在线科技有限公司 Method and device for acquiring lane change decision information, storage medium and vehicle
CN111123933A (en) * 2019-12-24 2020-05-08 华为技术有限公司 Vehicle track planning method and device, intelligent driving area controller and intelligent vehicle
CN111123933B (en) * 2019-12-24 2021-10-01 华为技术有限公司 Vehicle track planning method and device, intelligent driving area controller and intelligent vehicle
CN116499487A (en) * 2023-06-28 2023-07-28 新石器慧通(北京)科技有限公司 Vehicle path planning method, device, equipment and medium
CN116499487B (en) * 2023-06-28 2023-09-05 新石器慧通(北京)科技有限公司 Vehicle path planning method, device, equipment and medium
CN116946089A (en) * 2023-09-20 2023-10-27 深圳市蓝鲸智联科技股份有限公司 Intelligent brake auxiliary system
CN116946089B (en) * 2023-09-20 2024-01-02 深圳市蓝鲸智联科技股份有限公司 Intelligent brake auxiliary system

Also Published As

Publication number Publication date
CN109910880B (en) 2021-06-29

Similar Documents

Publication Publication Date Title
CN109910880A (en) Method, apparatus, storage medium and the terminal device of vehicle behavior planning
CN113366497B (en) Agent Prioritization for Autonomous Vehicles
CN103158705B (en) Method and system for controlling a host vehicle
CN110488802B (en) Decision-making method for dynamic behaviors of automatic driving vehicle in internet environment
CN111696373B (en) Motorcade cooperative sensing method, motorcade cooperative control method and motorcade cooperative control system
CN110562258B (en) Method for vehicle automatic lane change decision, vehicle-mounted equipment and storage medium
CN102800214B (en) Vehicle lane change conflict resolution method under vehicle information interaction condition
CN109878515A (en) Predict method, apparatus, storage medium and the terminal device of track of vehicle
CN110562222B (en) Emergency braking control method for curve scene, vehicle-mounted device and storage medium
CN108628206A (en) Road construction detecting system and method
CN110533913A (en) Method for early warning, device, vehicle and the storage medium of vehicle collision
CN107993487A (en) Avoid the method and device of emergency vehicle
CN105151043A (en) Emergency avoidance system and method for unmanned automobile
CN106470885A (en) Vehicle control system and the behavior planning system possessing this vehicle control system
CN109760675A (en) Predict method, apparatus, storage medium and the terminal device of track of vehicle
CN114077541A (en) Method and system for validating automatic control software for an autonomous vehicle
CN113844451B (en) Driving device control method and device, electronic device and storage medium
US20220314968A1 (en) Electronic control device
CN109835347A (en) Movable traffic participant
CN110473419A (en) A kind of passing method of automatic driving vehicle in no signal lamp intersection
CN110171420A (en) Controller of vehicle
WO2022240483A1 (en) Detecting driving behavior of vehicles
US11615702B2 (en) Determining vehicle path
EP4043309A1 (en) Vehicle control method, device, controller and intelligent vehicle
CN113895456A (en) Intersection driving method and device for automatic driving vehicle, vehicle and medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant