CN117657216A

CN117657216A - Speed planning method, device and equipment for automatic driving vehicle and vehicle

Info

Publication number: CN117657216A
Application number: CN202311726706.1A
Authority: CN
Inventors: 贾昌昊; 黄云华; 张瑶港
Original assignee: Neolithic Yancheng Intelligent Manufacturing Co ltd
Current assignee: Neolithic Yancheng Intelligent Manufacturing Co ltd
Priority date: 2023-12-14
Filing date: 2023-12-14
Publication date: 2024-03-08

Abstract

The application discloses a speed planning method, device and equipment for an automatic driving vehicle and the vehicle, and belongs to the technical field of computers. The method comprises the following steps: acquiring travel information of a host vehicle and travel information of an obstacle in a travel area of the host vehicle; determining a driving lane condition of the own vehicle based on the driving information of the own vehicle; acquiring a risk barrier in the driving lane condition based on the driving lane condition of the own vehicle, the driving information of the own vehicle and the driving information of the barrier; determining an interaction scene of the own vehicle and the risk obstacle based on the running information of the risk obstacle and the running information of the own vehicle; and obtaining a speed track corresponding to the interaction scene by utilizing a preset speed track planning strategy based on the interaction scene, the running information of the risk barrier and the running information of the own vehicle. The method and the device optimize the reliability and the efficiency of vehicle speed planning.

Description

Speed planning method, device and equipment for automatic driving vehicle and vehicle

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to the technical fields of intelligent transportation, automatic driving, and the like, and in particular, to a method, an apparatus, a device, and a storage medium for speed planning of an automatic driving vehicle.

Background

In the automatic driving field, after determining the path of the own vehicle, a common speed planning scheme needs to consider all obstacles with potential collision risks, and according to the positions occupied by the dynamic and static obstacles on the path of the own vehicle and the occurrence time, a safe speed track capable of running is generated by sampling the safe position of the own vehicle on the path at each time point and according to the sampling points.

However, the road environment conditions in the actual driving scene are complex, and the reliability and safety of the speed track planning of the automatic driving vehicle need to be improved.

Disclosure of Invention

The application provides a speed planning method, device and equipment for an automatic driving vehicle and the vehicle, which ensure the reliability of the speed planning of the automatic driving vehicle, and the technical scheme is as follows:

in a first aspect, a method for speed planning of an autonomous vehicle is provided, the method comprising:

acquiring travel information of a host vehicle and travel information of an obstacle in a travel area of the host vehicle;

determining a driving lane condition of the own vehicle based on the driving information of the own vehicle;

acquiring a risk barrier in the driving lane condition based on the driving lane condition of the own vehicle, the driving information of the own vehicle and the driving information of the barrier;

Determining an interaction scene of the own vehicle and the risk obstacle based on the running information of the risk obstacle and the running information of the own vehicle;

and obtaining a speed track corresponding to the interaction scene by utilizing a preset speed track planning strategy based on the interaction scene, the running information of the risk barrier and the running information of the own vehicle.

In a second aspect, there is provided a speed planning apparatus for an autonomous vehicle, the apparatus comprising:

a first acquisition unit configured to acquire travel information of a host vehicle and travel information of an obstacle in a travel area of the host vehicle;

a first determination unit configured to determine a driving lane condition of the own vehicle based on driving information of the own vehicle;

a first obtaining unit configured to obtain a risk obstacle in a driving lane situation of the own vehicle based on the driving lane situation of the own vehicle, driving information of the own vehicle, and driving information of the obstacle;

a second determining unit, configured to determine an interaction scenario of the own vehicle and the risk obstacle based on the traveling information of the risk obstacle and the traveling information of the own vehicle;

the second obtaining unit is used for obtaining a speed track corresponding to the interaction scene by utilizing a preset speed track planning strategy based on the interaction scene, the running information of the risk barrier and the running information of the own vehicle.

In a third aspect, there is provided a computer readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement the method of the aspects and any one possible implementation as described above.

In a fourth aspect, there is provided an electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the aspects and methods of any one of the possible implementations described above.

In a fifth aspect, there is provided an autonomous vehicle comprising an electronic device as described above.

The beneficial effects of the technical scheme that this application provided include at least:

according to the technical scheme, the running information of the self-vehicle and the running information of the obstacle in the running area of the self-vehicle can be obtained, the running lane condition of the self-vehicle can be determined based on the running information of the self-vehicle, the risk obstacle under the running lane condition can be obtained based on the running lane condition of the self-vehicle, the running information of the self-vehicle and the running information of the obstacle, the interaction scene of the self-vehicle and the risk obstacle can be determined based on the running information of the risk obstacle and the running information of the self-vehicle, so that the speed track corresponding to the interaction scene can be obtained by utilizing a preset speed track planning strategy, and the speed track can be planned more effectively according to the interaction scene of the self-vehicle and the risk obstacle, the speed track can be planned more effectively, and the speed track can be planned more flexibly and more flexibly.

It should be understood that the description of this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for speed planning of an autonomous vehicle according to one embodiment of the present application;

FIG. 2 is a flow chart of a method for speed planning of an autonomous vehicle according to another embodiment of the present application;

FIG. 3 is a schematic illustration of the presence of merge lane regions in a method provided in another embodiment of the present application;

FIG. 4 is a schematic illustration of a risk barrier in a method provided in accordance with another embodiment of the present application;

FIG. 5 is a schematic illustration of a risk barrier in a method provided in accordance with another embodiment of the present application;

FIG. 6 is a schematic illustration of a risk barrier in a method provided in accordance with another embodiment of the present application;

fig. 7 is a schematic diagram of a speed trajectory planning strategy of an obstacle retrograde driving scenario in a method according to another embodiment of the present disclosure;

FIG. 8 shows a block diagram of a speed planning apparatus for an autonomous vehicle according to one embodiment of the present application;

fig. 9 is a block diagram of an electronic device for implementing a method of speed planning for an autonomous vehicle according to an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It will be apparent that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

It should be noted that, the terminal device in the embodiment of the present application may include, but is not limited to, smart devices such as a mobile phone, a Personal digital assistant (Personal DigitalAssistant, PDA), a wireless handheld device, and a Tablet Computer (Tablet Computer); the display device may include, but is not limited to, a personal computer, a television, or the like having a display function.

In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

Currently, in the related art, in general, when planning a speed, first, traveling information of a given planned path and an obstacle of a vehicle is converted into a flea (frenet) coordinate system. Secondly, through collision detection of the predicted track in the converted planned path of the own vehicle and the predicted track in the running information of the obstacle, the obstacle which occupies the given path information in one planning period is screened out, namely the obstacle which possibly collides with the own vehicle. And mapping the track information of the obstacles with collision risk into an ST image, sampling s based on each time t, and screening out a speed curve which has no collision with the obstacles and is continuous in second order in a curve fitting mode to obtain the speed track of the vehicle.

However, in the related art, on one hand, when sampling all the time t during the specific speed curve generation and generating a speed curve that is collision-free with an obstacle and is continuous in second order through curve fitting, it is necessary to evaluate the quality of each sampling point, which results in a lot of time consumption. On the other hand, for a relatively complex traffic scenario, such as a reverse obstacle occupying a planned path of a vehicle in the whole planning period, a collision-free speed track may not be solved.

Referring to fig. 1, a flow chart of a speed planning method for an automatic driving vehicle according to an embodiment of the present application is shown. The speed planning method of the automatic driving vehicle specifically comprises the following steps:

step 101, acquiring running information of a self-vehicle and running information of an obstacle in a running area of the self-vehicle.

And 102, determining the driving lane condition of the self-vehicle based on the driving information of the self-vehicle.

Step 103, obtaining a risk barrier in the driving lane condition based on the driving lane condition of the self-vehicle, the driving information of the self-vehicle and the driving information of the barrier.

Step 104, determining an interaction scene of the own vehicle and the risk obstacle based on the running information of the risk obstacle and the running information of the own vehicle.

And 105, obtaining a speed track corresponding to the interaction scene by utilizing a preset speed track planning strategy based on the interaction scene, the running information of the risk barrier and the running information of the own vehicle.

The traveling area of the own vehicle may be a traveling environment of the autonomous vehicle. The number of obstacles in the traveling area of the own vehicle may be plural. The obstacles may include static obstacles and dynamic obstacles. Dynamic obstacles may include, but are not limited to, autonomous vehicles, ordinary automobiles, low speed vehicles, pedestrians, and other traffic participants. Static obstacles may include, but are not limited to, stationary vehicles, stationary pedestrians, and stationary traffic facilities.

The travel information of the own vehicle may include, but is not limited to, planned route information of the own vehicle, a position of the own vehicle, a speed of the own vehicle, and map information of the own vehicle. The travel information of the obstacle may include, but is not limited to, planned path information of the obstacle, a position of the obstacle, a speed of the obstacle, map information of the obstacle.

It should be noted that the obstacle may include, but is not limited to, an object that the own vehicle may detect and an object predicted by the own vehicle that may have a running collision.

Here, the risk obstacle may include a vehicle (closest inpath vehicle, CIPV) closest to the path, and other obstacles that coincide with the path of the own vehicle.

It should be noted that the obtained speed track corresponding to the interaction scene may be a speed track sequence that can be safely driven by the vehicle corresponding to the interaction scene. The speed trajectory within a planning period may include, but is not limited to, a trajectory within the planning period, a trajectory with speed information within the planning period, and the like.

It should be noted that, part or all of the execution bodies of steps 101 to 105 may be an application located at the local terminal, or may be a functional unit such as a plug-in unit or a Software development kit (Software DevelopmentKit, SDK) provided in the application located at the local terminal, or may be a processing engine located in a server on the network side, or may be a distributed system located on the network side, for example, a processing engine or a distributed system in an autopilot platform on the network side, which is not limited in this embodiment.

It will be appreciated that the application may be a native program (native app) installed on the native terminal, or may also be a web page program (webApp) of a browser on the native terminal, which is not limited in this embodiment.

In this way, risk barriers under different driving lanes can be obtained according to the driving information of the vehicle and the driving information of the barriers, and then the interactive scene of speed planning is obtained according to the driving information of the vehicle and the risk barriers, so that corresponding speed track planning is performed according to the interactive scene of the vehicle and the risk barriers, more reasonable and effective speed tracks can be planned under the condition that the road environment is complex, and therefore the reliability and safety of the speed track planning of the vehicle can be improved.

Alternatively, in one possible implementation manner of the present embodiment, the driving lane condition may include a presence of a merging lane area and an absence of a merging lane area, in step 102, specifically, it may be determined, based on map information of a vehicle, whether the vehicle performs lane change processing in the current planning period, in response to the vehicle performing lane change processing, the driving lane condition is determined to be the presence of the merging lane area, and in response to the vehicle not performing lane change processing, the driving lane condition is determined to be the absence of the merging lane area.

In the present embodiment, the map information of the own vehicle may be map information of a traveling area of the own vehicle corresponding to each planning period. The map information may include lane information, road information, etc. within a traveling area of the own vehicle.

It is understood that the map information of the own vehicle may be acquired based on a preset high-precision map or may be acquired based on a preset navigation map.

In one specific implementation of this implementation, first, lane information on a planned path of a host vehicle may be obtained based on map information of the host vehicle. And secondly, based on the lane information of the own vehicle, the lane change condition on the planning path of the own vehicle corresponding to each planning period can be obtained. Again, it may be determined whether the own vehicle is lane changing in the current planning period based on the lane change situation on the planned path of the own vehicle.

In another specific implementation of this implementation, in response to the driving lane condition being that there is a merging lane region, in step 103, first, the target lane information of the own vehicle merging may be acquired. Next, a distance between an obstacle in the target lane information and the own vehicle may be obtained based on the target lane information, the travel information of the own vehicle, and the travel information of the obstacle. Again, a risk obstacle in the case of a driving lane in which there is a merging lane region may be obtained based on a preset distance condition and a distance between the obstacle in the target lane information and the own vehicle.

In this specific implementation, the obstacle in the target lane information may include a first obstacle in the target lane information that travels in front of the host vehicle and a second obstacle in the target lane information that travels behind the host vehicle.

It will be appreciated that the number of first obstacles may be one or more. The number of second obstacles may be one or more.

In this specific implementation process, the preset distance condition may include that the distance between the obstacle and the own vehicle is the minimum value of the distances between each obstacle and the own vehicle in the target lane information.

In one case of the specific implementation, for a first obstacle traveling in front of the host vehicle in the target lane information, when a distance between any one of the first obstacles and the host vehicle satisfies a preset distance condition, the first obstacle may be used as a risk obstacle in front of the host vehicle.

Another case of the specific implementation procedure is that, for a second obstacle traveling behind the own vehicle in the target lane information, when a distance between any one of the second obstacles and the own vehicle satisfies a preset distance condition, the second obstacle may be used as a risk obstacle in front of the own vehicle.

In this way, the situation of the lane where the own vehicle runs can be obtained according to the map information of the own vehicle, so that the risk barrier of the own vehicle can be determined based on different lane situations, and the effectiveness and reliability of the obtained risk barrier are improved.

In another specific implementation process of the implementation manner, the driving information of the own vehicle may further include planned path information, and in response to the driving lane condition being that the merging lane area does not exist, in step 103, a candidate obstacle on the planned path of the own vehicle may be determined specifically based on the planned path information of the own vehicle and the driving information of the obstacle, and further, the candidate obstacle may be subjected to screening processing based on a preset risk condition, the planned path information of the own vehicle and the driving information of the candidate obstacle, so that the risk obstacle in the driving lane condition may be obtained based on a result of the screening processing.

In this specific implementation process, the candidate obstacle may be an obstacle whose travel path coincides with or intersects the planned path of the own vehicle.

In this specific implementation process, the preset risk condition may include determining that the number of obstacles for which the risk time reaches the time target value is a first preset number; determining that the risk time reaches a time target value and the number of barriers of which the risk distance reaches a distance target value is a first preset number; determining that the number of obstacles for which the risk time reaches the time target value, the risk distance reaches the distance target value, and the risk evaluation value reaches the evaluation target value is a first preset number.

One case of this specific implementation is to take a first preset number of candidate obstacles as a result of the screening process in response to the risk time of the first preset number of candidate obstacles reaching a time target value.

Another case of this concrete implementation is that, in response to the risk time of a second preset number of candidate obstacles reaching the time target value, the number of candidate obstacles in which the risk distance reaches the distance target value is determined in the second preset number of candidate obstacles, and in response to the number of candidate obstacles reaching the distance target value being equal to the first preset number, the candidate obstacles reaching the distance target value are taken as the result of the screening process.

In still another case of the specific implementation, the number of candidate obstacles for which the risk evaluation value reaches the evaluation target value in the candidate obstacle reaching the distance target value is determined in response to the number of candidate obstacles for which the distance target value is reached being greater than the first preset number, and the candidate obstacle for which the evaluation target value is reached is regarded as a result of the screening process in response to the number of candidate obstacles for which the evaluation target value is reached being equal to the first preset number.

Here, the second preset number may be greater than the first preset number. The first preset number and the second preset number may be preconfigured according to actual service requirements. Wherein reaching may represent equality.

Preferably, the first preset number may be 1, and the second preset number may be N, which is an integer greater than 1.

Therefore, a risk barrier can be rapidly and effectively screened out, so that the follow-up speed track of the vehicle can be rapidly planned more accurately based on the motion relation between the risk barrier and the vehicle, and the reliability of the vehicle speed planning is further improved.

Here, the risk time may be a point in time at which the path of the obstacle intersects with the path of the own vehicle, and the time target value may be a minimum value among points in time at which the path of each obstacle intersects with the path of the own vehicle. The risk distance may be a distance between a path intersection point of the obstacle and the own vehicle and a current position point of the own vehicle, and the distance target value is a minimum distance among distances between the path intersection point of each obstacle and the own vehicle and the current position point of the own vehicle. The risk evaluation value may be a degree of risk characterizing the obstacle after being collided, and the evaluation target value may be a maximum value in the risk evaluation value of each obstacle.

Further, after the result of the screening process is obtained, a risk obstacle in which the traveling lane condition is a condition in which there is no merging lane region may be obtained based on the result of the screening process.

It will be appreciated that here, one or more risk barriers may be obtained by a screening process for candidate barriers.

It should be noted that, the specific implementation process provided in the present implementation manner may be combined with the various specific implementation processes provided in the foregoing implementation manner to implement the speed planning method of the autonomous vehicle of the present embodiment. The detailed description may refer to the relevant content in the foregoing implementation, and will not be repeated here.

Optionally, in one possible implementation manner of this embodiment, the driving information of the risk obstacle includes a position of the risk obstacle and a speed of the risk obstacle, and the driving information of the own vehicle includes a position of the own vehicle and a speed of the own vehicle, in step 104, specifically, a driving relationship between the own vehicle and the risk obstacle may be obtained based on the position of the own vehicle and the speed of the own vehicle, the position of the risk obstacle and the speed of the risk obstacle, and an interaction scene of the own vehicle and the risk obstacle may be determined based on the driving relationship between the own vehicle and the risk obstacle and a preset interaction driving condition.

In this implementation, the interaction scenario may include, but is not limited to, a self-vehicle following obstacle travel scenario, an obstacle reverse travel scenario, an obstacle merging travel scenario, a static obstacle scenario, and a self-vehicle merging travel scenario.

In this implementation, the driving relationship of the own vehicle and the risk obstacle may include a positional relationship of the own vehicle and the risk obstacle, a speed relationship of the own vehicle and the risk obstacle, and other movement relationships of the own vehicle and the risk obstacle. The positional relationship of the own vehicle and the risk obstacle may include a distance of the own vehicle from the risk obstacle, a difference between an orientation angle of the own vehicle and an orientation angle of the risk obstacle, or an angle of the own vehicle from the risk obstacle.

Optionally, the preset interactive driving conditions may include an interactive driving condition corresponding to each interactive scene.

In a specific implementation process of the implementation manner, the running relationship between the own vehicle and the risk obstacle and the preset interactive running condition corresponding to each interactive scene can be subjected to matching processing in parallel, so that the interactive scene of the own vehicle and the risk obstacle is determined.

In one case of the specific implementation process, the first interactive driving condition corresponding to the driving scene of the vehicle following the obstacle may include that the risk obstacle is located on a lane of the vehicle and a planned path of the vehicle, a longitudinal distance between the risk obstacle and the vehicle is greater than a preset longitudinal distance threshold, a path length of less than one planning period, and a speed of the vehicle is greater than a preset speed threshold.

Preferably, the preset speed threshold may be 0.5 meters per second (m/s).

Here, according to the planned path information of the own vehicle and the traveling information of the candidate obstacle, it is determined whether the traveling relationship between the own vehicle and the risk obstacle satisfies the first interactive traveling condition, that is, whether the traveling relationship between the own vehicle and the risk obstacle is that the risk obstacle is located on the lane of the own vehicle and the planned path of the own vehicle, whether the longitudinal distance between the risk obstacle and the own vehicle is greater than a preset longitudinal distance threshold, and is smaller than the path length of one planning period, and whether the speed of the own vehicle is greater than the preset speed threshold. If the running relationship between the own vehicle and the risk obstacle meets the first interactive running condition, the interactive scene can be determined to be the running scene of the own vehicle following the obstacle.

In another case of the specific implementation process, the second interactive driving condition corresponding to the obstacle retrograde driving scene may include: the difference between the heading angle of the risk obstacle and the heading angle of the vehicle reaches a preset angle threshold, and the speed of the risk obstacle is greater than a preset speed threshold.

Here, if the driving relationship between the own vehicle and the risk obstacle satisfies the second interactive driving condition, the interactive scene may be determined to be an obstacle reverse driving scene.

In still another case of the specific implementation process, the third interactive driving condition corresponding to the obstacle parallel driving scene may include: the travel lane of the risk obstacle is changed to the travel lane of the own vehicle, the speed of the risk obstacle is greater than the speed of the own vehicle, or slightly less than the speed of the own vehicle.

Here, if the driving relationship between the own vehicle and the risk obstacle satisfies the third interactive driving condition, the interactive scene may be determined to be an obstacle parallel driving scene.

Furthermore, it will be appreciated that in the event that the speed of the risk obstacle is much less than the speed of the vehicle, the vehicle will be subject to an emergency braking process.

In still another case of the specific implementation, the fourth interactive driving condition corresponding to the static obstacle scene may include that a speed of the risk obstacle is less than a preset speed threshold.

Preferably, the preset speed threshold may be 0.5m/s.

Here, if the driving relationship between the own vehicle and the risk obstacle satisfies the fourth interactive driving condition, the interactive scene may be a static obstacle scene.

The other situation of the specific implementation process is that the own vehicle is in a lane-merging running scene, namely, a map corresponding to a planning path in a planning period of the own vehicle has a conflict area, whether the own vehicle performs lane-changing processing in the current planning period can be determined based on map information, if the own vehicle performs lane-changing processing, the situation of a running lane is determined to be a lane-merging area, and further, the situation that a risk obstacle is in the own vehicle lane-merging running scene can be directly determined.

Therefore, the running relation between the vehicle and the risk obstacle can be obtained according to the position of the vehicle, the speed of the vehicle, the position of the risk obstacle and the speed of the risk obstacle, and then the corresponding interaction scene of the vehicle and the risk obstacle can be determined according to the running relation and the preset interaction running condition, so that the following speed track planning of the vehicle can be conveniently performed based on the corresponding interaction scene, and the reliability of the planned speed track of the vehicle is further improved.

Optionally, in one possible implementation manner of this embodiment, in step 105, a speed track planning policy corresponding to the interaction scene may be specifically obtained based on the interaction scene and a preset speed track planning policy, and then a speed track corresponding to the interaction scene may be obtained based on the running information of the risk obstacle and the running information of the own vehicle by using the speed track planning policy corresponding to the interaction scene.

In this implementation, the preset speed trajectory planning policy may include a speed trajectory planning policy corresponding to each interaction scenario.

In this implementation, the travel information of the risk obstacle may include a travel path of the risk obstacle, a position of the risk obstacle, and a speed of the risk obstacle. The travel information of the own vehicle may include a position of the own vehicle and a speed of the own vehicle. The speed of the own vehicle may include an initial speed, which may be the speed of the own vehicle at the beginning of a planning period, and a target speed, which may be the speed of the own vehicle at the end of a planning period.

In a specific implementation process of the implementation manner, using a first speed track planning strategy corresponding to a driving scene of a self-vehicle following an obstacle, obtaining a speed track corresponding to the interaction scene based on driving information of a risk obstacle and driving information of the self-vehicle specifically may include: if the speed difference between the initial speed of the own vehicle and the target speed of the own vehicle is smaller than the absolute value of the preset speed difference, a speed curve can be obtained directly based on the target speed by calculation so as to obtain a planned speed track; if the initial speed of the own vehicle is greater than the target speed, a first distance and a second distance corresponding to the speed of the own vehicle from the speed of the own vehicle to the target speed can be calculated and obtained by the first preset deceleration and the second preset deceleration respectively. If the distance between the vehicle and the risk barrier is larger than the first distance, uniformly decelerating based on a third preset deceleration to obtain a planned speed track; if the distance between the vehicle and the risk obstacle is between the first distance and the second distance, calculating a first planning deceleration based on a preset safety distance between the vehicle and the risk obstacle to obtain a planned speed track; if the distance between the vehicle and the risk barrier is greater than the second distance, decelerating based on a third preset deceleration to obtain a planned speed track; if the initial speed of the vehicle is smaller than the target speed, the vehicle is accelerated to the target speed based on the first preset acceleration, so that a planned speed track is obtained.

Preferably, the absolute value of the preset speed difference may be 0.5m/s, i.e. the speed difference is positive and negative 0.5m/s. The first preset deceleration may be 0.8 meters square seconds (m/s) ² ) The second preset deceleration may be 4m/s ² The third preset deceleration may be 1m/s ² The fourth preset deceleration may be 4m/s ² . The first preset acceleration may be 1m/s ² 。

In another specific implementation of this implementation, the second speed trajectory planning strategy corresponding to the obstacle retrograde driving scenario may include determining a plurality of speed trajectory planning strategies based on a preset risk level. The second speed trajectory planning strategy may include a speed trajectory planning strategy corresponding to each risk level.

Here, different risk level levels may be classified according to the longitudinal distance between the reverse running risk obstacle and the own vehicle. The risk level classes include a risk class, a more risk class, and a non-risk class.

Alternatively, the risk level may indicate that the distance between the risk obstacle and the own vehicle is within a first preset distance range, which may be calculated from the fifth preset deceleration.

Alternatively, the more dangerous level may indicate that the distance between the risk obstacle and the own vehicle is within a second preset distance range, which may be calculated from the sixth preset deceleration and the fifth preset deceleration.

Alternatively, the non-dangerous level may indicate that the distance between the risk obstacle and the own vehicle is within a third preset distance range, which may be calculated from the sixth preset deceleration.

Further, in the case that the risk level is dangerous, obtaining the planned speed trajectory by using the corresponding speed trajectory planning strategy may include: on the one hand, the own vehicle can directly perform deceleration treatment with a fifth preset deceleration until stopping, so as to obtain a planned speed track; alternatively, on the other hand, first, when the lateral distance between the risk obstacle and the own vehicle is smaller than the first lateral preset distance, the first planned acceleration may be calculated based on the traveling information of the own vehicle and the traveling information of the risk obstacle. And secondly, performing speed limiting processing based on the first planned acceleration, and performing sudden braking processing based on a fifth preset deceleration when the lateral distance between the risk obstacle and the vehicle is smaller than a second lateral distance threshold value so as to obtain a planned speed track.

Further, under the condition that the risk level is dangerous, obtaining the planned speed track by using the corresponding speed track planning strategy may include: on the one hand, the own vehicle can directly perform deceleration processing based on a sixth preset deceleration until stopping to obtain a planned speed track; or on the other hand, first, when the lateral distance between the risk obstacle and the own vehicle is smaller than the first lateral preset distance, the own vehicle may calculate the second planned acceleration based on the running information of the own vehicle and the running information of the risk obstacle. And secondly, performing speed limiting processing based on the second planned acceleration, and performing sudden braking processing based on a sixth preset deceleration when the lateral distance between the risk obstacle and the vehicle is smaller than a second lateral distance threshold value so as to obtain a planned speed track.

Exemplary, as shown in FIG. 7, a sixthThe preset deceleration can be 1m/s ² I.e. -1m/s ² Is used for the acceleration of the vehicle,

further, under the condition that the risk level is not dangerous, obtaining the planned speed track by using the corresponding speed track planning strategy may include: firstly, limiting the speed of the vehicle based on preset acceleration, and calculating to obtain a third planned acceleration based on the running information of the vehicle and the running information of the risk obstacle when the lateral distance between the vehicle and the vehicle is smaller than the first lateral preset distance. And secondly, performing speed limiting processing based on the third planned acceleration to obtain a planned speed track.

Further, the obtaining a planned speed track by using the corresponding third speed track planning strategy according to the obstacle parallel track driving scene, that is, the scene of the obstacle cut-in (cut_in) lane where the own vehicle is driving, may specifically include: when the lateral distance between the risk barrier and the vehicle is smaller than or equal to a third lateral distance threshold value, performing sudden braking processing based on a seventh preset deceleration speed to obtain a planned speed track; when the lateral distance between the risk obstacle and the own vehicle is greater than the third lateral distance threshold, a fourth planned acceleration or a second planned deceleration can be calculated according to the running information of the own vehicle and the running information of the risk obstacle, and the vehicle can run based on the fourth planned acceleration or the second planned deceleration to obtain a planned speed track.

Specifically, the obtaining a planned speed track by using a fourth speed track planning strategy corresponding to the static obstacle scene may specifically include: when the distance between the risk obstacle serving as the static obstacle and the own vehicle is smaller than a first preset safe distance threshold value, calculating to obtain the maximum deceleration based on the first preset safe distance threshold value, and directly performing sudden braking processing based on the maximum deceleration to obtain a planned speed track; and when the distance between the risk barrier and the own vehicle is between the first preset safety distance threshold value and the second preset safety distance threshold value, performing slow braking processing based on the eighth preset deceleration, and planning the speed track of the own vehicle.

Here, the first preset safety distance threshold may characterize a safety distance that the desired static obstacle maintains from the host vehicle. The second preset safety distance threshold may be indicative of a desired distance for slow brake of the own vehicle.

In addition, the distance between the risk barrier and the own vehicle is greater than a second preset safety distance threshold, and no processing can be performed to perform planning processing based on the current running information of the own vehicle so as to obtain a planned speed track.

Preferably, the first lateral distance threshold may be 0.5m, the second lateral distance threshold may be 0.2m, and the third lateral distance threshold may be 2m. The fifth preset deceleration may be 4m/s ² The sixth preset deceleration may be 1m/s ² The seventh preset deceleration may be 4m/s ² The eighth preset deceleration may be 1m/s ² 。

Specifically, the obtaining a planned speed track by using a fifth speed track planning strategy corresponding to a vehicle merging driving scene, namely a vehicle lane merge scene, may specifically include: it is determined whether a travel path of a risk obstacle behind the host vehicle in the target lane intersects the host vehicle travel path. If the vehicle is intersected, calculating the collision time, the headway and the collision distance of the rear risk obstacle and the vehicle according to the running information of the rear risk obstacle and the running information of the vehicle, and if the collision time is smaller than a preset time threshold value, the headway is smaller than a preset headway threshold value and the collision distance is smaller than a third preset safety distance threshold value, controlling the vehicle to stop at a lane intersection, for example, a lane merging intersection. If the collision time is greater than or equal to a preset time threshold, the headway is greater than or equal to a preset headway threshold, and the collision distance is greater than or equal to a third preset safety distance threshold, determining the motion relationship of the front risk barrier and the own vehicle according to the combined risk barrier driving information and the own vehicle driving information in front of the target lane, and determining the own vehicle to drive based on a following mode according to the motion relationship so as to obtain a planned speed track, or determining the own vehicle to drive based on a cruising mode according to the motion relationship so as to obtain the planned speed track.

Here, the collision time may be calculated based on the vehicle distance of the two vehicles and the relative speed of the two vehicles. The headway can be calculated based on the distance between the two vehicles and the speed of the own vehicle. The preset time threshold may be 4 seconds(s), the preset time distance threshold may be 2s, and the third preset safe distance threshold may be 5 meters (m).

In this way, the speed track planning strategy corresponding to the interaction scene can be obtained according to the interaction scene and the preset speed track planning strategy, and then the speed track corresponding to the interaction scene can be obtained based on the running information of the risk barrier and the running information of the vehicle by utilizing the speed track planning strategy corresponding to the interaction scene, so that the speed tracks of the vehicle under different interaction scenes can be planned, and the more rational and effective speed track planning under the condition of complex road environment is realized, thereby improving the reliability and safety of the speed track planning of the vehicle.

For a better understanding of the method according to the embodiments of the present application, the following description refers to the accompanying drawings and specific application scenarios.

Fig. 2 is a flow chart of a speed planning method for an autonomous vehicle according to another embodiment of the present application, as shown in fig. 2.

Step 201, acquiring traveling information of a vehicle and traveling information of an obstacle in a traveling area of the vehicle.

Step 202, determining whether the own vehicle performs lane change processing in the current planning period based on map information in the running information of the own vehicle.

And 203, responding to the self-vehicle to perform lane changing processing, determining that the driving lane condition is that a merging lane area exists, and acquiring the target lane information merged by the self-vehicle.

Step 204, obtaining the distance between the obstacle in the target lane information and the own vehicle based on the target lane information, the running information of the own vehicle and the running information of the obstacle.

Step 205, obtaining a risk obstacle in the case of a driving lane with a merging lane area based on a preset distance condition and a distance between the obstacle in the target lane information and the own vehicle.

In this embodiment, the preset distance condition may include that the distance between the obstacle and the own vehicle in the target lane information reaches a preset distance threshold. The preset distance condition may also be that the distance between the obstacle and the own vehicle is the minimum value of the distances between each obstacle and the own vehicle in the target lane information.

Here, the preset distance threshold may be determined according to a lateral safety distance and a longitudinal safety distance between the own vehicle and the obstacle. Alternatively, the preset distance threshold may be preconfigured according to the actual traffic scenario.

Alternatively, on the one hand, in the case that the distance between the obstacle in front of the own vehicle and the own vehicle in the own vehicle traveling direction in the target lane information is obtained based on the target lane information, the traveling information of the own vehicle, and the traveling information of the obstacle, and the distance between the obstacle in front and the own vehicle can further satisfy the preset distance condition, the obstacle in front is taken as the risk obstacle in front of the own vehicle in the own vehicle traveling direction in the target lane information, that is, the CIPV in front of the own vehicle.

Alternatively, on the other hand, the distance between the rear obstacle of the own vehicle and the own vehicle in the own vehicle traveling direction in the target lane information may be obtained based on the target lane information, the traveling information of the own vehicle, and the traveling information of the obstacle, and then, if the distance between the rear obstacle and the own vehicle satisfies a preset distance condition, the rear obstacle may be used as a risk obstacle behind the own vehicle in the own vehicle traveling direction in the target lane information, that is, CIPV behind the own vehicle.

In this embodiment, by way of example, fig. 3 is a schematic diagram illustrating the presence of a merge lane region in a method provided in another embodiment of the present application. The driving lane condition is that a merging lane area exists, and the driving lane condition can be an area which represents that a vehicle performs merging or lane changing driving, and a lane merging (merge) exists in a planned path. In the case where there is a merging lane region, the own vehicle may select, as CIPV, a front obstacle obs_l nearest in front of the own vehicle and a rear obstacle obs_f nearest in rear of the target lane.

It will be appreciated that in the case where there is a merge lane region, the risk obstacle may include the obstacle obs_l nearest in front of the host vehicle and the obstacle obs_f nearest behind in the target lane.

And step 206, determining that the driving lane condition is that the merging lane area does not exist in response to the self-vehicle not performing lane changing processing, and determining candidate obstacles on the planned path of the self-vehicle based on the planned path information in the driving information of the self-vehicle and the driving information of the obstacles.

Step 207, screening the candidate obstacles based on the planned path information of the own vehicle and the running information of the candidate obstacles based on the preset risk condition, so as to obtain the risk obstacle when the running lane is the situation without the merging lane area.

In this embodiment, collision risk information of the candidate obstacle may be obtained based on planned path information of the own vehicle and traveling information of the candidate obstacle, and then screening processing may be performed on the candidate obstacle based on preset risk conditions and collision risk information of the candidate obstacle.

Here, the collision risk information includes a risk time, a risk distance, and a risk evaluation value. The risk time may be a point in time at which the travel position of the obstacle and the planned path of the own vehicle intersect. The risk distance may be a distance between a collision point at which the obstacle and the own vehicle may collide and the own vehicle, and the risk evaluation value may be a risk degree indicating after the obstacle is collided.

Further, in response to the risk time of a first preset number of candidate obstacles reaching a time target value, taking the first preset number of candidate obstacles as a result of the screening process; and determining the number of candidate obstacles in which the risk distance reaches the distance target value in the second preset number of candidate obstacles in response to the risk time of the second preset number of candidate obstacles reaching the time target value. And in response to the number of candidate obstacles reaching the distance target value being equal to the first preset number, taking the candidate obstacles reaching the distance target value as a result of the screening process. In response to the number of candidate obstacles reaching the distance target value being greater than the first preset number, determining the number of candidate obstacles in which the risk evaluation value reaches the evaluation target value among the candidate obstacles reaching the distance target value. In response to the number of candidate obstacles reaching the evaluation target value being equal to the first preset number, the candidate obstacles reaching the evaluation target value are taken as the result of the screening process.

For example, the situation of driving lanes is that no merging lane area exists, and the situation that no lane conflict exists and the lane is changed on a map corresponding to the planned path of the own vehicle can be represented. In the case of a driving lane in which there is no merging lane region, only one obstacle may be selected as a risk obstacle CIPV.

Fig. 4 is a schematic diagram of a risk barrier in a method according to another embodiment of the present application, where, as shown in fig. 4, the points in time when the locations of the candidate barriers intersect with the planned path of the vehicle may be ordered, and one barrier with the closest intersection point in time is selected as the CIPV of the vehicle. The risk time of the obstacle 1 is t1, the risk time of the obstacle 2 is t2, t2 is less than t1, and the obstacle 2 can be selected as CIPV.

For example, fig. 5 is a schematic diagram of a risk obstacle in a method according to another embodiment of the present application, if two obstacles with the same time point of entering a planned path of a host vehicle exist in fig. 5, then an obstacle with a collision point closer to the host vehicle is selected as CIPV of the host vehicle, if in fig. 5, the risk time of the obstacle 1 is t1, the risk time of the obstacle 2 is t2, t2=t1, the risk distance of the collision between the obstacle 2 and the host vehicle is smaller than the risk distance of the collision between the obstacle 1 and the host vehicle, and the obstacle 2 is selected as CIPV.

For example, fig. 6 is a schematic diagram of a risk obstacle in the method provided in another embodiment of the present application, if there is still an obstacle with the same risk time and risk distance as shown in fig. 6, then, according to the movement information of the obstacle, for example, the running speed of the obstacle, an obstacle with a larger risk of collision is selected as CIPV, as shown in fig. 6, the risk time of the obstacle 1 is t1, the risk time of the obstacle 2 is t2, t2=t1, but the risk evaluation value of collision is larger, and the obstacle 2 can be selected as CIPV.

Step 208, determining an interaction scene of the own vehicle and the risk obstacle based on the preset interaction driving condition, the driving information of the risk obstacle and the driving information of the own vehicle.

In this embodiment, the interaction scene includes at least one of a self-vehicle following obstacle traveling scene, an obstacle reverse traveling scene, an obstacle parallel traveling scene, a static obstacle scene, and a self-vehicle parallel traveling scene.

Alternatively, the driving relationship between the own vehicle and the risk obstacle may be obtained based on the position and the speed of the own vehicle, the position of the risk obstacle and the speed of the risk obstacle, and then the interaction scene of the own vehicle and the risk obstacle may be determined based on the driving relationship between the own vehicle and the risk obstacle and the preset interaction driving condition.

Optionally, the running relationship between the vehicle and the risk obstacle and the preset interactive running condition corresponding to each interactive scene may be matched in parallel, so as to determine the interactive scene of the vehicle and the risk obstacle.

Specifically, the first interactive driving condition corresponding to the driving scene of the own vehicle following the obstacle, namely the following scene of the own vehicle may include: the CIPV is located on a lane of the own vehicle and a planned path of the own vehicle, wherein the CIPV is greater than a preset longitudinal distance threshold value, and is smaller than the path length of one planning period, and the speed of the own vehicle is greater than a preset speed threshold value.

For example, the first interactive driving condition may be that the CIPV target is on the same lane as the host vehicle, the CIPV is on a planned path (path) of the host vehicle, i.e. the CIPV driving path coincides with the planned path of the host vehicle, the CIPV is spaced from the host vehicle by a distance of more than 5m and less than a path length of one planning cycle, and the host vehicle speed is more than 0.5m/s.

Thus, based on the first interactive driving condition, the situation that the own vehicle has a following scene, the own vehicle is inconvenient to overtake CIPV, the following is the optimal choice, and the proper following space can be ensured.

Here, if the driving relationship between the own vehicle and the risk obstacle satisfies the first interactive driving condition, it may be determined that the interactive scene is a driving scene of the own vehicle following the obstacle.

Specifically, the obstacle reverse travel scene, i.e., the reverse travel scene, the corresponding second interactive travel condition may include: the difference between the CIPV's heading angle and the vehicle's heading angle reaches a preset angle threshold, and the CIPV's speed is greater than a preset speed threshold.

For example, the second alternate travel condition may be a CIPV heading angle that differs from the own vehicle heading angle by 3 pi/4, with a CIPV speed greater than 0.5m/s.

In this way, it is possible to more accurately determine whether the CIPV is in a retrograde state, and may have an influence on the running of the host vehicle.

Specifically, the obstacle parallel driving scene, that is, the scene in which the obstacle cuts into the lane in which the own vehicle is driving, the corresponding third interactive driving condition may include: the driving lane of the CIPV is changed to the driving lane of the host vehicle, the speed of the CIPV is greater than the speed of the host vehicle, or slightly less than the speed of the host vehicle.

For example, the third interactive driving condition may be that the CIPV is not in the lane of the vehicle, enters the lane of the vehicle at the rear, and the driving speed of the CIPV is greater than the speed of the vehicle, or slightly less than the speed of the vehicle, so that whether the CIPV has a cut_in scene may be determined more accurately, and the condition of sudden braking may be excluded.

In addition, in the case where the CIPV speed is much smaller than the own vehicle speed, the own vehicle performs the sudden braking process.

Specifically, the fourth interactive traveling condition corresponding to the static obstacle scene may include: the speed of the CIPV is less than a preset speed threshold. Preferably, the preset speed threshold may be 0.5m/s.

Here, if the driving relationship between the own vehicle and the risk obstacle satisfies the fourth interactive driving condition, it may be determined that the interactive scene is a static obstacle scene.

Specifically, the own vehicle parallel road driving scene, that is, the map corresponding to the planned path in the planning period of the own vehicle has a conflict area, can determine whether the own vehicle performs lane changing processing in the current planning period based on map information, if the own vehicle performs lane changing processing, determines that the driving lane condition is a merged lane area, and further can directly determine that the risk barrier is in the own vehicle parallel road driving scene.

Step 209, obtaining a speed track planning strategy corresponding to the interaction scene based on the interaction scene and a preset speed track planning strategy.

In this embodiment, the preset speed track planning strategy may include a speed track planning strategy corresponding to each interaction scenario.

Step 210, obtaining a speed track corresponding to the interaction scene based on the running information of the risk barrier and the running information of the own vehicle by using a speed track planning strategy corresponding to the interaction scene.

In the present embodiment, the travel information of the risk obstacle may include a travel path of the risk obstacle, a position of the risk obstacle, and a speed of the risk obstacle. The travel information of the own vehicle may include a position of the own vehicle and a speed of the own vehicle. The speed of the own vehicle may include an initial speed, which may be the speed of the own vehicle at the beginning of a planning period, and a target speed, which may be the speed of the own vehicle at the end of a planning period.

Specifically, the first speed track planning strategy corresponding to the driving scene of the own vehicle following the obstacle, namely the following scene, may include that if the speed difference between the initial speed of the own vehicle and the target speed of the own vehicle is smaller than the absolute value of the preset speed difference, a speed curve may be obtained directly based on the target speed by calculation, so as to obtain the planned speed track.

Preferably, for example, the absolute value of the preset speed difference may be 0.5m/s, i.e. the speed difference is within plus or minus 0.5 m/s.

If the initial speed of the own vehicle is greater than the target speed, a first distance (s_soft) and a second distance (s_hard) corresponding to the speed of the own vehicle from the speed of the own vehicle to the target speed can be calculated and obtained by the first preset deceleration and the second preset deceleration respectively. If the distance between the vehicle and the risk obstacle is greater than the first distance s_soft, uniformly decelerating based on a third preset deceleration to obtain a planned speed track; if the distance between the own vehicle and the risk obstacle is between s_soft and s_hard, calculating a first planning deceleration based on a preset safety distance between the own vehicle and the risk obstacle to obtain a planned speed track; and if the distance between the vehicle and the risk obstacle is greater than the second distance s_hard, decelerating based on the third preset deceleration to obtain a planned speed track.

Preferably, the first preset deceleration may be 0.8m/s ² The second preset deceleration may be 4m/s ² The third preset deceleration may be 1m/s ² The fourth preset deceleration may be 4m/s ² 。

If the initial speed of the vehicle is smaller than the target speed, the vehicle is uniformly accelerated to the target speed based on the first preset acceleration, so that a planned speed track is obtained.

Preferably, the first preset acceleration may be 1m/s ² 。

Specifically, the obstacle reverse driving scenario, the reverse driving scenario, and the corresponding second speed trajectory planning strategy may include a plurality of speed trajectory planning strategies determined based on a preset risk level. The second speed trajectory planning strategy may include a speed trajectory planning strategy corresponding to each risk level.

Here, fig. 7 is a schematic diagram of a speed track planning strategy of a reverse driving scene of an obstacle in the method provided in another embodiment of the present application, as shown in fig. 7, different risk level grades may be obtained according to a longitudinal distance between a reverse risk obstacle and a vehicle. The risk level includes dangerous, more dangerous, and not dangerous. The distance between the self-vehicle and the retrograde risk obstacle is expressed on an sl coordinate system, and the speed track of the self-vehicle is planned and obtained through the distance relation between the self-vehicle and the retrograde risk obstacle in the s direction and the transverse distance relation in the l direction.

In particular, the risk level may represent that the distance between the risk obstacle and the own vehicle is within a first preset distance range, which may be calculated from the fifth preset deceleration.

Here, the first preset distance range may be determined according to a braking distance obtained by performing braking processing on the own vehicle based on the fifth preset deceleration, that is, a braking distance obtained by performing braking processing on the own vehicle based on the fifth preset deceleration is a maximum distance value of the first preset distance range. The first preset distance range may represent that the distance between the reverse-driving risk obstacle and the longitudinal direction of the host vehicle is very short.

Here, the second preset distance range may be determined according to a braking distance obtained by performing braking processing on the own vehicle based on the sixth preset deceleration and a braking distance obtained by performing braking processing on the own vehicle based on the fifth preset deceleration, that is, a minimum distance value of the second preset distance range obtained by performing braking processing on the own vehicle based on the fifth preset deceleration and a maximum distance value of the second preset distance range obtained by performing braking processing on the own vehicle based on the sixth preset deceleration. The second preset distance range may represent that the distance between the reverse-driving risk obstacle and the longitudinal direction of the host vehicle is relatively short.

Here, the third preset distance range may be determined according to a braking distance obtained by performing braking processing on the own vehicle based on the sixth preset deceleration, that is, a braking distance obtained by performing braking processing on the own vehicle based on the sixth preset deceleration is a minimum distance value of the third preset distance range. It will be appreciated that the third predetermined distance range represents that the longitudinal distance between the reverse-driving risk obstacle and the host vehicle is significant.

Further, in the case that the risk level is dangerous, the corresponding speed trajectory planning strategy may include: the own vehicle can directly perform deceleration treatment with a fifth preset deceleration until stopping to obtain a planned speed track; or, when the lateral distance between the risk obstacle and the vehicle is smaller than the first lateral preset distance, the first planned acceleration is calculated based on the running information of the vehicle and the running information of the risk obstacle, the speed limiting process is performed based on the first planned acceleration, and when the lateral distance between the risk obstacle and the vehicle is smaller than the second lateral distance threshold, the sudden braking process is performed based on the fifth preset deceleration, and the planned speed track is obtained based on the speed limiting and the sudden braking process.

Preferably, the first lateral distance threshold may be 0.5m and the second lateral distance threshold may be 0.2m.

Exemplary, as shown in FIG. 7, the fifth preset deceleration may be 4m/s ² The short distance range in the map of the risk level is dangerous, which indicates that the own vehicle must take 4m/s ² The collision can be avoided only by sudden braking of the deceleration of (a). If the distance between the reverse risk obstacle and the own vehicle is within the short distance range, and when the lateral distance from the own vehicle is smaller than 0.5m, the first planning acceleration can be calculated based on the running information of the own vehicle and the running information of the risk obstacle, the speed limit processing is carried out on the own vehicle based on the first planning acceleration, namely, l < 0.5m speed limit is carried out, and when the lateral distance from the own vehicle is smaller than 0.2m, the speed limit processing is carried out on the own vehicle at 4m/s ² The deceleration of (1) is subjected to sudden braking treatment, namely, the sudden braking with l less than 0.2m, and the planned speed track is obtained based on the speed limiting and sudden braking treatment.

Further, in the case that the risk level is dangerous, the corresponding speed trajectory planning strategy may include: the own vehicle can directly perform deceleration processing based on a sixth preset deceleration until stopping to obtain a planned speed track; or, when the lateral distance between the risk obstacle and the own vehicle is smaller than the first lateral preset distance, the own vehicle can calculate and obtain a second planning acceleration based on the running information of the own vehicle and the running information of the risk obstacle, speed limiting processing is performed based on the second planning acceleration, and when the lateral distance between the risk obstacle and the own vehicle is smaller than the second lateral distance threshold, slow braking processing is performed based on the sixth preset deceleration, so that a planned speed track is obtained.

Exemplary, as shown in FIG. 7, the sixth preset deceleration may be 1m/s ² I.e. -1m/s ² The acceleration of the vehicle is represented by the medium distance range in the map when the risk level is a higher risk level, and the vehicle is required to be at 1m/s ² The deceleration of (2) is reduced comfortably to avoid collision. And if the distance between the reverse risk obstacle and the own vehicle is in the middle distance range, the own vehicle can be subjected to speed limiting treatment when the transverse distance between the reverse risk obstacle and the own vehicle is smaller than 0.5m, namely l < 0.5m speed limiting, and is subjected to slow braking treatment when the transverse distance is smaller than 0.2m, namely l < 0.2m slow braking, and the planned speed track is obtained based on the speed limiting and the slow braking treatment.

Further, in the case that the risk level is not dangerous, the corresponding speed trajectory planning strategy may include: and limiting the speed of the self-vehicle based on the preset acceleration, and calculating to obtain a third planning acceleration based on the running information of the self-vehicle and the running information of the risk obstacle when the transverse distance between the self-vehicle and the self-vehicle is smaller than the first transverse preset distance, and limiting the speed based on the third planning acceleration to obtain a planned speed track.

For example, as shown in fig. 7, the risk level is a far distance range in the graph, if the reverse obstacle is within the distance range and the lateral distance from the vehicle is less than 0.5m, the speed limiting process is performed, i.e., l < 0.5m speed limiting, based on which the planned speed track is obtained.

Specifically, the obstacle parallel driving scenario, i.e. the scenario in which the obstacle cuts into the lane in which the own vehicle is driving, the corresponding third speed trajectory planning strategy may include: when the lateral distance between the risk barrier and the vehicle is smaller than or equal to a third lateral distance threshold value, performing sudden braking processing based on a seventh preset deceleration speed to obtain a planned speed track; when the lateral distance between the risk obstacle and the own vehicle is greater than the third lateral distance threshold, a fourth planned acceleration or a second planned deceleration can be calculated according to the running information of the own vehicle and the running information of the risk obstacle, and the vehicle can run based on the fourth planned acceleration or the second planned deceleration to obtain a planned speed track.

Exemplary, the third lateral distance threshold may be 2m and the seventh preset deceleration may be 4m/s ² . When the lateral distance between the risk barrier and the own vehicle, namely the collision distance is smaller than 2m, the risk cut_in is considered, the own vehicle can select to carry out sudden braking at the deceleration of 4m/s2, and the speed track of the own vehicle is planned; when the lateral distance between the risk obstacle and the own vehicle, i.e. the collision distance, is greater than 2m, an acceleration or deceleration can be calculated from the speed difference between the own vehicle and the cut_in risk obstacle, based on which the speed trajectory of the own vehicle is planned.

Specifically, the fourth speed trajectory planning strategy corresponding to the static obstacle scene may include: when the distance between the risk obstacle serving as the static obstacle and the own vehicle is smaller than a first preset safe distance threshold value, calculating to obtain the maximum deceleration based on the first preset safe distance threshold value, and directly performing sudden braking processing based on the maximum deceleration to obtain a planned speed track; and when the distance between the risk barrier and the own vehicle is between the first preset safety distance threshold value and the second preset safety distance threshold value, performing slow braking processing based on the eighth preset deceleration, and planning the speed track of the own vehicle.

Here, the first preset safety distance threshold may characterize a safety distance that the desired static obstacle maintains from the host vehicle. The second preset safety distance threshold may be indicative of a desired distance for slow brake of the own vehicle. The eighth preset deceleration may be 1m/s ² 。

Specifically, the own vehicle parallel track driving scene, namely an own vehicle lane merge scene, the corresponding fifth speed track planning strategy may include: it is determined whether a travel path of a risk obstacle behind the host vehicle in the target lane intersects the host vehicle travel path. If the vehicle is intersected, calculating collision time (ttc), headway (thw) and collision distance of the rear risk obstacle and the vehicle according to the rear risk obstacle driving information and the driving information of the vehicle, and controlling the vehicle to stop at a lane intersection, for example, a lane merge intersection, if ttc is smaller than a preset time threshold, thw is smaller than a preset headway threshold and the collision distance is smaller than a third preset safety distance threshold. If ttc is larger than the preset time threshold, thw is larger than the preset time distance threshold and the collision distance is larger than the third preset safety distance threshold, determining the motion relation between the risk barrier and the own vehicle according to the risk barrier obs_l running information in front of the merge lane and the running information of the own vehicle, and determining the own vehicle to run based on a following mode according to the motion relation so as to obtain a planned speed track, or determining the own vehicle to run based on a cruising mode according to the motion relation so as to obtain the planned speed track.

Here, the collision time (ttc) may be calculated based on the vehicle distance between the two vehicles and the relative speed of the two vehicles. The headway (thw) can be calculated based on the distance between the two vehicles and the speed of the own vehicle. The preset time threshold may be 4s, the preset time distance threshold may be 2s, and the third preset safe distance threshold is 5m.

In an exemplary lane merge scene, it may be first determined whether a rear vehicle of the merge lane intersects with the own vehicle path, if so, the distance between the rear vehicle ob_f of the own vehicle merge lane and ttc, thw and two vehicles of the own vehicle may be calculated to determine whether a safe merge process is performed, if ttc is less than 4s, thw is less than 2s and the collision distance is less than 5m, then merge is considered unsafe, and the vehicle may be stopped at the merge intersection. Otherwise, whether the own vehicle enters a following mode or a cruising mode can be judged according to the motion relation of the own vehicle and the front vehicle obs_l of the merge lane so as to obtain a planned speed track.

In this embodiment, the predicted running information of the own vehicle and the predicted running information of the obstacles may be used to screen out the obstacles occupying the given path of the own vehicle in one planning period, and at least one obstacle having the greatest influence on the own vehicle may be selected as the CIPV according to the time and the position of the obstacle occupying the given path of the own vehicle.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

Fig. 8 is a block diagram of a speed planning apparatus for an autonomous vehicle according to an embodiment of the present application, as shown in fig. 8. The speed planning apparatus 800 of the autonomous vehicle of the present embodiment may include a first acquisition unit 801, a first determination unit 802, a first acquisition unit 803, a second determination unit 804, and a second acquisition unit 805. Wherein, the first obtaining unit 801 is configured to obtain driving information of a self-vehicle and driving information of an obstacle in a driving area of the self-vehicle; a first determining unit 802 for determining a driving lane condition of the own vehicle based on the driving information of the own vehicle; a first obtaining unit 803 for obtaining a risk obstacle in a driving lane situation of the own vehicle based on the driving lane situation of the own vehicle, the driving information of the own vehicle, and the driving information of the obstacle; a second determining unit 804, configured to determine an interaction scenario between the own vehicle and the risk obstacle based on the driving information of the risk obstacle and the driving information of the own vehicle; a second obtaining unit 805, configured to obtain, based on the interaction scenario, the driving information of the risk obstacle, and the driving information of the own vehicle, a speed track corresponding to the interaction scenario by using a preset speed track planning strategy.

It should be noted that, part or all of the speed planning apparatus for an autopilot vehicle in this embodiment may be an application located at a local terminal, or may be a functional unit such as a plug-in unit or a Software development kit (Software DevelopmentKit, SDK) disposed in the application located at the local terminal, or may be a processing engine located in a server on a network side, or may be a distributed system located on the network side, for example, a processing engine or a distributed system in an autopilot platform on the network side, which is not limited in this embodiment.

Optionally, in one possible implementation manner of this embodiment, the driving information of the own vehicle includes map information, and the first determining unit 802 may specifically be configured to determine, based on the map information, whether the own vehicle performs lane change processing in the current planning period, determine, in response to the own vehicle performing the lane change processing, that the driving lane condition is a merging lane region, and determine, in response to the own vehicle not performing the lane change processing, that the driving lane condition is a merging lane region not.

Optionally, in one possible implementation manner of this embodiment, the first obtaining unit 803 may be further configured to obtain, in response to the driving lane condition being that a merging lane area exists, target lane information that the own vehicle merges into, obtain, based on the target lane information, the driving information of the own vehicle, and the driving information of the obstacle, a distance between the obstacle in the target lane information and the own vehicle, and obtain, based on a preset distance condition and a distance between the obstacle in the target lane information and the own vehicle, a risk obstacle in the driving lane condition.

Optionally, in one possible implementation manner of this embodiment, the driving information of the own vehicle includes planned path information, and the first obtaining unit 803 is further configured to determine, in response to the driving lane condition being that there is no merging lane area, a candidate obstacle on the planned path of the own vehicle based on the planned path information of the own vehicle and the driving information of the obstacle; screening the candidate barriers based on preset risk conditions, planned path information of the vehicle and running information of the candidate barriers; based on the result of the screening process, a risk obstacle in the case of the driving lane is obtained.

Alternatively, in one possible implementation manner of the present embodiment, the first obtaining unit 803 may be further configured to obtain collision risk information of the candidate obstacle based on planned path information of the own vehicle and traveling information of the candidate obstacle; and screening the candidate barriers based on preset risk conditions and collision risk information of the candidate barriers.

Optionally, in one possible implementation manner of the present embodiment, the collision risk information includes a risk time, a risk distance, and a risk evaluation value, and the first obtaining unit 803 is further configured to, in response to the risk time of a first preset number of candidate obstacles reaching a time target value, use the first preset number of candidate obstacles as a result of the screening process; determining the number of candidate obstacles in which the risk distance reaches the distance target value in the second preset number of candidate obstacles in response to the risk time of the second preset number of candidate obstacles reaching the time target value; and in response to the number of candidate obstacles reaching the distance target value being equal to the first preset number, taking the candidate obstacles reaching the distance target value as a result of the screening process.

Alternatively, in one possible implementation manner of the present embodiment, the first obtaining unit 803 may be further configured to determine, in response to the number of candidate obstacles reaching the distance target value being greater than the first preset number, the number of candidate obstacles in which the risk evaluation value reaches the evaluation target value among the candidate obstacles reaching the distance target value; in response to the number of candidate obstacles reaching the evaluation target value being equal to the first preset number, the candidate obstacles reaching the evaluation target value are taken as the result of the screening process.

Optionally, in one possible implementation manner of this embodiment, the driving information of the risk obstacle includes a position of the risk obstacle and a speed of the risk obstacle, the driving information of the own vehicle includes a position of the own vehicle and a speed of the own vehicle, and the second determining unit 804 may be further configured to obtain a driving relationship between the own vehicle and the risk obstacle based on the position of the own vehicle and the speed of the own vehicle, the position of the risk obstacle and the speed of the risk obstacle; and determining the interaction scene of the own vehicle and the risk obstacle based on the running relation between the own vehicle and the risk obstacle and the preset interaction running condition.

Optionally, in one possible implementation manner of the present embodiment, the interaction scene includes at least one of a self-vehicle following obstacle driving scene, an obstacle reverse driving scene, an obstacle parallel driving scene, a static obstacle scene, and a self-vehicle parallel driving scene.

Optionally, in one possible implementation manner of this embodiment, the second obtaining unit 805 may be specifically configured to obtain a speed trajectory planning policy corresponding to the interaction scenario based on the interaction scenario and a preset speed trajectory planning policy; and obtaining a speed track corresponding to the interaction scene based on the running information of the risk barrier and the running information of the own vehicle by utilizing a speed track planning strategy corresponding to the interaction scene.

In this embodiment, the traveling information of the own vehicle and the traveling information of the obstacle in the traveling area of the own vehicle may be acquired by the first acquisition unit. The first determining unit may determine the driving lane condition of the own vehicle based on the driving information of the own vehicle, the first obtaining unit may obtain the risk barrier under the driving lane condition based on the driving lane condition of the own vehicle, the driving information of the own vehicle and the driving information of the barrier, the second determining unit may determine the interaction scene of the own vehicle and the risk barrier based on the driving information of the risk barrier and the driving information of the own vehicle, so that the second obtaining unit may obtain a speed track corresponding to the interaction scene based on the interaction scene, the driving information of the risk barrier and the driving information of the own vehicle by using a preset speed track planning strategy.

One embodiment of the present application provides a computer readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement a method of speed planning for an autonomous vehicle as described above.

One embodiment of the present application provides an electronic device comprising a processor and a memory having at least one instruction stored therein, the instruction being loaded and executed by the processor to implement a method of speed planning for an autonomous vehicle as described above.

One embodiment of the present application provides an autonomous vehicle including an electronic device as described above. Specifically, the autonomous vehicle may be a vehicle of the L2 class and above. The autonomous vehicle may include, but is not limited to, an unmanned delivery vehicle, an unmanned logistics vehicle, and the like.

In the technical scheme of the application, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

Fig. 9 shows a schematic block diagram of an example electronic device 900 that may be used to implement embodiments of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.

As shown in fig. 9, the electronic device 900 includes a computing unit 901 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 902 or a computer program loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other by a bus 904. An input/output (I/O) interface 906 is also connected to bus 904.

A number of components in the electronic device 900 are connected to the I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, or the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, an optical disk, or the like; and a communication unit 909 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 909 allows the electronic device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunications networks.

The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 901 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the respective methods and processes described above, such as a speed planning method of an autonomous vehicle. For example, in some embodiments, the method of speed planning for an autonomous vehicle may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 900 via the ROM 902 and/or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the above-described speed planning method of the autonomous vehicle may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the speed planning method of the autonomous vehicle by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present application may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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 application, 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. The 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 portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions disclosed in the present application are achieved, and are not limited herein.

The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.

Claims

1. A method of speed planning for an autonomous vehicle, the method comprising:

2. The method of claim 1, wherein the travel information of the host vehicle includes map information, the travel lane condition includes a presence merge lane area and an absence merge lane area, and wherein determining the travel lane condition of the host vehicle based on the travel information of the host vehicle includes:

determining whether the own vehicle performs lane change processing in the current planning period based on the map information;

responding to the self-vehicle to perform lane changing processing, and determining the driving lane condition as the presence of a merging lane area;

and determining that the driving lane condition is that a merging lane area does not exist in response to the self-vehicle not carrying out lane change processing.

3. The method according to claim 2, wherein the obtaining a risk obstacle in the driving lane situation based on the driving lane situation of the own vehicle, the driving information of the own vehicle, and the driving information of the obstacle, comprises:

Responding to the situation of the driving lane as the existence of a merging lane area, and acquiring the merging target lane information of the own vehicle;

obtaining the distance between the obstacle in the target lane information and the own vehicle based on the target lane information, the running information of the own vehicle and the running information of the obstacle;

and acquiring a risk barrier under the condition of the driving lane based on a preset distance condition and the distance between the barrier in the target lane information and the own vehicle.

4. The method according to claim 2, wherein the traveling information of the own vehicle includes planned path information, and the obtaining the risk obstacle in the traveling lane condition based on the traveling lane condition of the own vehicle, the traveling information of the own vehicle, and the traveling information of the obstacle includes:

determining a candidate obstacle on the planned path of the own vehicle based on the planned path information of the own vehicle and the traveling information of the obstacle in response to the traveling lane condition being that no merging lane region exists;

screening the candidate barriers based on preset risk conditions, planned path information of the vehicle and running information of the candidate barriers;

Based on the result of the screening process, a risk obstacle in the case of the driving lane is obtained.

5. The method according to claim 4, wherein the screening the candidate obstacle based on the preset risk condition, the planned path information of the own vehicle, and the traveling information of the candidate obstacle includes:

acquiring collision risk information of the candidate obstacle based on the planned path information of the own vehicle and the running information of the candidate obstacle;

and screening the candidate barriers based on preset risk conditions and collision risk information of the candidate barriers.

6. The method according to claim 5, wherein the collision risk information includes a risk time, a risk distance, and a risk evaluation value, and the screening process for the candidate obstacle based on a preset risk condition and collision risk information of the candidate obstacle and the own vehicle includes:

responding to the risk time of a first preset number of candidate barriers in the candidate barriers to reach a time target value, and taking the first preset number of candidate barriers as a screening processing result;

Determining the number of candidate obstacles in which the risk distance reaches the distance target value in the second preset number of candidate obstacles in response to the risk time of the second preset number of candidate obstacles reaching the time target value;

and in response to the number of candidate obstacles reaching the distance target value being equal to the first preset number, taking the candidate obstacles reaching the distance target value as a result of the screening process.

7. The method according to claim 6, further comprising:

determining a number of candidate obstacles in which the risk evaluation value reaches the evaluation target value in the candidate obstacles reaching the distance target value in response to the number of candidate obstacles reaching the distance target value being greater than a first preset number;

in response to the number of candidate obstacles reaching the evaluation target value being equal to the first preset number, the candidate obstacles reaching the evaluation target value are taken as the result of the screening process.

8. The method of claim 1, wherein the travel information of the risk obstacle includes a position of the risk obstacle and a speed of the risk obstacle, the travel information of the own vehicle includes a position of the own vehicle and a speed of the own vehicle, and the determining the interaction scenario of the own vehicle and the risk obstacle based on the travel information of the risk obstacle and the travel information of the own vehicle includes:

Obtaining a driving relationship between the own vehicle and the risk obstacle based on the position and the speed of the own vehicle, the position of the risk obstacle and the speed of the risk obstacle;

and determining the interaction scene of the own vehicle and the risk obstacle based on the running relation between the own vehicle and the risk obstacle and the preset interaction running condition.

9. The method of claim 1, wherein the interaction scenario comprises at least one of a self-propelled following obstacle travel scenario, an obstacle reverse travel scenario, an obstacle parallel travel scenario, a static obstacle scenario, and a self-propelled parallel travel scenario.

10. The method according to any one of claims 1 to 9, wherein the obtaining a speed trajectory corresponding to the interaction scenario using a preset speed trajectory planning strategy based on the interaction scenario, the driving information of the risk barrier, and the driving information of the own vehicle includes:

acquiring a speed track planning strategy corresponding to the interaction scene based on the interaction scene and a preset speed track planning strategy;

and obtaining a speed track corresponding to the interaction scene based on the running information of the risk barrier and the running information of the own vehicle by utilizing a speed track planning strategy corresponding to the interaction scene.

11. A speed planning apparatus for an autonomous vehicle, the apparatus comprising:

12. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.