CN115257815A - A planning method, device and terminal equipment for a right turn of an autonomous vehicle - Google Patents

Abstract

The planning method for the right turn of the automatic driving automobile comprises the steps of obtaining map information of a turning intersection, identifying the states of obstacles on each zebra crossing which need to pass when the automobile runs through the turning intersection according to a preset route, determining the position of the automobile for obtaining related information of surrounding obstacles according to the states of the obstacles, obtaining the related information and each road information at intervals of a first preset period when the automobile is located at the position, predicting the action track of the surrounding obstacles according to each road information, map information and related information, planning the right turn track of the automobile according to each road information, map information and action track, and controlling the automobile to run according to the right turn track. The safety and the stability of the automatic driving vehicle in the complex road condition driving process can be improved, the safety of the vehicle and passengers can be further guaranteed, and the comfort of the passengers is improved.

Description

A planning method, device and terminal equipment for a right turn of an autonomous vehicle

technical field

The present invention relates to the field of path planning, in particular to a planning method, device and terminal equipment for a right turn of an automatic driving vehicle.

Background technique

Our country has a vast territory. With the rapid development of traffic, there is an unbalanced traffic development. In many places, there are no right-turn lights, and the passage of pedestrians and non-motor vehicles is often accompanied by irregular or even violations of traffic safety laws. , in the case of a large number of people and traffic, self-driving vehicles are prone to traffic safety accidents in the process of turning, which may lead to the loss of people and property in the car.

Contents of the invention

The purpose of the present invention is to provide a right-turn planning method, device, terminal equipment and readable storage medium for an automatic driving vehicle.

In a first aspect, the present invention provides a method for planning a right turn of an automatic driving vehicle, which is applied to a vehicle to be turned, and the method includes:

Obtain the map information of the turning intersection, identify the state of obstacles on each zebra crossing that the vehicle needs to pass through when driving through the turning intersection according to the preset route, and determine that the vehicle obtains the surrounding obstacles according to the obstacle state on each zebra crossing the location of information about the object;

When the vehicle is at the position, acquire the relevant information and various road information every first preset period, and predict the surrounding obstacles based on the various road information, the map information and the relevant information trajectory of action;

Planning a right-turn trajectory of the vehicle based on the various road information, the map information, and the action trajectory, and controlling the vehicle to travel according to the right-turn trajectory.

In an optional implementation manner, the determining the position where the vehicle starts to acquire information about surrounding obstacles according to the obstacle state on the zebra crossing includes:

When there is an obstacle on any one of the zebra crossings, the position at the preset distance from the zebra crossing with the obstacle is used as the position for obtaining relevant information;

When there is no obstacle on each of the zebra crossings, the current position is used as the position obtained from the relevant information.

In an optional implementation manner, the information of each road includes the status of each traffic light of each road, and the method further includes:

When there is an obstacle on any zebra crossing, travel to the position according to the preset route, and detect the state of the obstacle on each zebra crossing every second preset period.

In an optional embodiment, the information on each road includes vehicle traffic status on each road, each road includes a transverse road, and the right-turn trajectory includes the driving direction of the vehicle, and the method further includes:

When the vehicle traffic state of the transverse road is vehicle traffic, and the traffic direction of the traffic vehicle is the same as the travel direction, acquire the traffic direction and traffic speed of the traffic vehicle, based on the traffic direction and the traffic The speed predicts the passing trajectory of the passing vehicle;

If the passing track overlaps with the right-turning track, stop driving;

If the passing trajectory does not overlap with the right-turn trajectory, travel according to the right-turn trajectory, and perform the step of acquiring the passing direction and speed of the passing vehicle.

In an optional implementation manner, the predicting the action trajectory of the surrounding obstacles based on the various road information, the map information and the related information includes:

Predicting advance information of the surrounding obstacles based on the last relevant information of the surrounding obstacles and the current relevant information;

The action trajectory of the surrounding obstacles is determined according to the forward information, the map information and the various road information.

In an optional implementation manner, the planning of the right-turn trajectory of the vehicle based on the various road information, the map information and the action trajectory through a preset method includes:

planning the action path of the vehicle through a dynamic programming algorithm based on the various road information, the map information, and the action trajectory;

The action path is optimized through a quadratic programming algorithm to obtain a right-turn trajectory of the vehicle.

In an optional embodiment, the method also includes:

When it is recognized that there is a special vehicle on each of the roads, stop traveling according to the right-turn trajectory until the special vehicle cannot be recognized.

In a second aspect, the present invention provides a right-turn planning device for an automatic driving vehicle, which is applied to a vehicle to be turned, and the device includes:

The perception module is used to acquire map information of turning intersections, identify the state of obstacles on each zebra crossing that the vehicle needs to pass when driving through the turning intersection according to a preset route, and determine the state of obstacles on each zebra crossing according to the state of obstacles on each zebra crossing. The location where the vehicle obtains the relevant information of the surrounding obstacles;

A prediction module, configured to acquire the relevant information and various road information every first preset period when the vehicle is at the position, and predict based on the various road information, the map information and the relevant information The action trajectory of the surrounding obstacles;

A planning module, configured to plan a right-turn trajectory of the vehicle based on the various road information, the map information, and the action trajectory, and control the vehicle to travel according to the right-turn trajectory.

In a third aspect, the present invention provides a terminal device, including a memory and a processor, the memory stores a computer program, and when the computer program runs on the processor, it executes the planning method for a right turn of an autonomous vehicle .

In a fourth aspect, the present invention provides a readable storage medium, which stores a computer program, and when the computer program runs on a processor, executes the planning method for a right turn of an automatic driving vehicle.

The beneficial effects of the embodiments of the present invention are:

An embodiment of the present application provides a right-turn planning method for an automatic driving vehicle. The right-turn planning method for an automatic driving vehicle is applied to a vehicle. By obtaining map information at a turning intersection, it is recognized that the vehicle needs to pass through the turning intersection when driving along a preset route. The state of obstacles on each zebra crossing, according to the state of obstacles to determine the position of the vehicle to obtain the relevant information of the surrounding obstacles, when the vehicle is located at this position, the relevant information and each road information are obtained every first preset period, and based on each Road information, map information and related information predict the action trajectory of surrounding obstacles, plan the right-turn trajectory of the vehicle based on each road information, map information and action trajectory, and control the vehicle to follow the right-turn trajectory. The present application can not only improve the safety and stability of the self-driving vehicle when driving in complex road conditions, but also further ensure the safety of the vehicle and passengers, and improve the comfort of the passengers.

In order to make the above-mentioned purpose, features and advantages of the present application more comprehensible, preferred embodiments will be described in detail below together with the accompanying drawings.

Description of drawings

In order to illustrate the technical solution of the present invention more clearly, the following drawings will be briefly introduced in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as It is regarded as limiting the protection scope of the present invention. In the respective drawings, similar components are given similar reference numerals.

FIG. 1 shows a schematic diagram of various roads in a planning method for a right turn of an automatic driving vehicle proposed in an embodiment of the present application;

FIG. 2 shows a schematic flow diagram of a planning method for a right turn of an autonomous vehicle proposed in the embodiment of the present application;

FIG. 3 shows a schematic diagram of various zebra crossings and obstacles in a planning method for a right turn of an automatic driving vehicle proposed in an embodiment of the present application;

FIG. 4 shows a schematic flow chart of predicting the action trajectory in a planning method for a right turn of an autonomous vehicle proposed in the embodiment of the present application;

FIG. 5 shows a schematic diagram of a right-turn trajectory planned in a planning method for a right-turn of an automatic driving vehicle proposed in an embodiment of the present application;

FIG. 6 shows a schematic flow diagram of planning a right-turn trajectory in a method for planning a right-turn of an automatic driving vehicle proposed in an embodiment of the present application;

Fig. 7 shows a schematic structural diagram of a planning device for a right turn of an automatic driving vehicle provided by an embodiment of the present application.

Description of main component symbols:

10-The planning device for the right turn of the self-driving car; 11-The perception module; 12-The prediction module; 13-The planning module.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

Hereinafter, the terms "comprising", "having" and their cognates that may be used in various embodiments of the present invention are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing, And it should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing or adding one or more features, numbers, steps, operations, elements, components or a combination of the foregoing possibilities.

In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions, and should not be construed as indicating or implying relative importance.

Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present invention belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, Unless clearly defined in various embodiments of the present invention.

Example 1

During the driving process, the self-driving vehicle may drive to some intersections with more complicated conditions, such as intersections without right-turn indicators, construction or traffic accident intersections, etc. Turning at complex intersections is prone to accidents. Therefore, as far as autonomous driving vehicles are concerned, it is of great significance to ensure the driving safety of the vehicle and the comfort of passengers by making decisions and planning an action path that complies with regulations and can pass smoothly without stagnation. This application combines factors such as the current traffic safety law, traffic lights, pedestrians and non-motor vehicles at intersections, and provides a right-turn planning method for autonomous vehicles applied to scenarios without right-turn indicator lights.

In this embodiment, as shown in Figure 1, when the vehicle travels to point A and is about to make a right turn, the horizontal road and the longitudinal road in this embodiment are as shown in the figure, that is, the driving direction of the vehicle is the longitudinal road, and the longitudinal road is the same as the longitudinal road. Vertical roads are horizontal roads. When the global route planning module of the vehicle is planning the route, a preset route with a right turn is planned. When the self-driving vehicle drives to the vicinity of the right-turn intersection according to the planned route, the self-driving vehicle will retrieve the traffic regulations of the right-turn intersection through the Internet of Things to determine that the vehicle's longitudinal road at the intersection is displayed as a red light, that is, the longitudinal road is red Whether it is possible to turn right when the traffic light is turned on; and it will recognize the signs and traffic lights at the right-turning intersection to determine whether there is a right-turning indicator light at the intersection, and judge whether the vehicle can turn right when the longitudinal road is a red light; The vehicle will also call the high-definition map of the intersection to see if there is a right-turn lane at this intersection. When it is determined that when the longitudinal road at the intersection is displayed as a red light, the driving vehicle is allowed to turn right, and there is no right-turn indicator light and no right-turn lane at the right-turn intersection, the automatic driving vehicle provided by the embodiment of the present application will be called. Turn planning method.

Please refer to FIG. 2 , the embodiment of the present application proposes a right-turn planning method for an automatic driving vehicle, which is applied to a turning vehicle. Exemplarily, the right-turn planning method for an automatic driving vehicle includes steps S100-S300.

Step S100: Obtain the map information of the turning intersection, identify the state of obstacles on each zebra crossing that the vehicle needs to pass through when driving through the turning intersection according to the preset route, and determine the vehicle's ability to obtain information about surrounding obstacles according to the obstacle state on each zebra crossing Location.

It can be understood that when the vehicle travels to a turning intersection, the vehicle will acquire map information of the turning intersection, the map information may be a high-precision map, and the map information includes relevant information of the turning intersection. The vehicle will also use the camera sensor on the vehicle to identify the state of obstacles on each zebra crossing that the vehicle will pass through when the vehicle passes through the turning intersection according to the preset route, so as to determine the relevant information of the vehicle to obtain surrounding obstacles according to the state of obstacles on the zebra crossing s position.

Among them, obstacles include but are not limited to any one or more of pedestrians, non-motorized vehicles, objects, animals and vehicles. Obstacle status includes obstacles in moving state and obstacles in static state. As shown in Figure 3, the vehicle is point A, and the zebra crossing that the vehicle will pass through the turning intersection according to the preset route is the first zebra crossing a and the second zebra crossing b. The oval shaded part in the figure may be an obstacle, that is, a pedestrian or Non-motorized gathering places.

In this embodiment, when it is recognized that there is an obstacle on any one of the zebra crossings that the pre-planned route of the vehicle will pass through, the position at the preset distance from the zebra crossing with the obstacle is used as the position for obtaining relevant information, At this position, the relevant information of the surrounding obstacles is obtained through the laser radar. When the vehicle passes through the turning intersection according to the preset route, when there are no obstacles on each zebra crossing, the current position of the vehicle will be used as the position obtained as relevant information, that is, the relevant information of the surrounding obstacles will be obtained immediately when the vehicle is at the current position. Among them, the preset interval will be set according to the actual situation; relevant information includes but not limited to the position and attitude of the obstacle, and the relative distance between the position of the obstacle and the vehicle.

In this embodiment, the vehicle will also be positioned in real time. Since the vehicle is at an intersection, there are multiple traffic lines, such as zebra crossings, solid lines in front of the zebra crossings, and light strip lines. Violations, and even traffic safety accidents. At present, the accuracy limit of satellite positioning is 2.5m, but the self-driving vehicles in the urban area can not meet the requirements of use only by satellite positioning, so the vehicle of this embodiment adopts satellite positioning and RTK (Real-time kinematic, real-time dynamic) The combined positioning technology can achieve centimeter-level positioning, and the satellite positioning is GPS (Global Positioning System, Global Positioning System) or Beidou satellite navigation system, so that the acquired vehicle position information meets the requirements for autonomous vehicle positioning. In addition, in order to make the vehicle brake accurately in front of the zebra crossing, a positioning technology combining satellite positioning, RTK and camera sensors will also be applied.

Step S200: When the vehicle is at the position, obtain relevant information and various road information every first preset period, and predict the action trajectory of surrounding obstacles based on various road information, map information and relevant information.

It can be understood that, when the vehicle starts to acquire related information immediately at the current position, the related information of surrounding obstacles and various road information will be acquired every first preset period. And it will predict the action trajectory of surrounding obstacles based on the acquired road information, map information and related information.

Wherein, each road information includes, but is not limited to, the status of traffic lights of each road and the status of obstacles on each road, and the status of traffic lights includes a green light state and a red light state. As shown in Figure 1, each road includes but is not limited to horizontal roads and longitudinal roads, and the state of obstacles on each road includes obstacles on each road, no obstacles on each road, obstacles on the There are no obstacles on the road, and there are obstacles on the longitudinal road and no obstacles on the lateral road.

In one embodiment, as shown in FIG. 4 , predicting the action trajectory of surrounding obstacles based on various road information, map information and related information includes sub-steps S210-S220.

Sub-step S210: Predict the progress information of the surrounding obstacles based on the previous relevant information of the surrounding obstacles and the current relevant information.

It can be understood that the vehicle will obtain the relevant information of the surrounding obstacles every first preset period. In this embodiment, the surrounding obstacles will be predicted according to the obtained previous relevant information of the surrounding obstacles and the current relevant information. forward information. Wherein, the advance information includes the traveling direction and traveling speed of surrounding obstacles. Because the environment of the intersection is relatively complex when the autonomous vehicle drives to the intersection, it is possible to control the speed of the autonomous vehicle passing through the intersection to be less than or equal to the preset intersection speed, and the preset intersection speed can be 30km/h.

t_1和t_0表示时间，v_行表示进行速度预测的障碍物的速度，t0(x0，y0)表示t0时刻的周围某一障碍物的位置为(x₀，y₀)，t1(x₁，y₁)表示t₁时刻的该障碍物的位置为(x₁，y₁)，该坐标系可以为以该待转弯路口的中心点为原点建立的平面坐标。通过上述公式，可以确定进行预测的障碍物的速度，由t₀到t₁可确定障碍物的前进方向；依据上述方法可得障碍物t₁和t₂的速度和方向，障碍物t₂和t₃的行进速度和行进方向，障碍物t₃和t₄……。In this example, the formula

t_1 and t_0 represent time, _row v represents the speed of the obstacle for speed prediction, t0(x0, y0) represents the position of an obstacle around t0 at (x ₀ , y ₀ ), t1(x ₁ , y ₁ ) indicates that the position of the obstacle at time t ₁ is (x ₁ , y ₁ ), and the coordinate system may be a plane coordinate established with the center point of the intersection to be turned as the origin. Through the above formula, the speed of the obstacle to be predicted can be determined, and the advancing direction of the obstacle can be determined from t ₀ to t ₁ ; according to the above method, the speed and direction of obstacles t ₁ and t ₂ can be obtained, and obstacles t ₂ and t 2 can be obtained. Travel speed and direction of travel at t ₃ , obstacles t ₃ and t ₄ ... .

Sub-step S220: Determine the action trajectory of surrounding obstacles according to the forward information, map information and various road information.

After determining at least one set of advancing information of the surrounding obstacles, the action track of the surrounding obstacles will be determined in combination with the traffic light status and map information of each road in the various road information acquired by the camera sensor, and the action track includes pedestrians or vehicles. Such as the moving intention of the obstacle, that is, the direction and speed of the obstacle to move and other information.

For example, when the obstacle is a pedestrian, if the pedestrian's forward direction from t ₀ to t ₁ , t ₁ to t ₂ ... is along the direction of the zebra crossing, that is, when the pedestrian is driving on a transverse road, along the same direction as the transverse road When the direction of the zebra crossing on the road is moving forward, and the traveling speed in the multiple sets of forward information obtained by the formula is greater than the preset speed, or most of the traveling speeds are greater than the preset speed, it can be judged that the pedestrian may pass the zebra crossing. At this time, the recognized Traffic light information, predicting the trajectory of pedestrians to avoid obstacles suddenly breaking into the vehicle's driving path.

For example, if the traffic signal light at the zebra crossing where pedestrians are about to pass is in a green state, it can be judged that the pedestrian wants to pass through the zebra crossing, and at the same time, the trajectory of the pedestrian can be predicted based on the relevant information of the zebra crossing, such as the position and width information, and the direction information of the pedestrian; The status of the traffic signal light is red, and it can be judged that pedestrians will not cross the zebra crossing. The preset speed can be set to the normal walking speed of ordinary people according to the situation.

Step S300: planning the right-turn trajectory of the vehicle based on various road information, map information and action trajectory, and controlling the vehicle to drive according to the right-turn trajectory.

It can be understood that after the action path of obstacles around the vehicle is determined, the right-turn trajectory of the vehicle will be planned according to various road information, map information and action trajectories through a preset method, thereby improving the driving safety and driving stability of the vehicle sex.

Wherein, as shown in Figure 5, the right-turning trajectory includes the first turning trajectory and the second turning trajectory, with point A as the center of mass of the vehicle, point B as the intersection of the right longitudinal zebra crossing and the centerline of the right lane, and point C as the right longitudinal zebra crossing and At the intersection of the center line of the left lane, a is the first zebra crossing, which is the lower horizontal zebra crossing, and b is the second zebra crossing, which is the right vertical zebra crossing. A first turning trajectory can be planned by combining points A and C, and a second turning trajectory can be planned by combining points A and B.

In this embodiment, each road information includes the traffic status of vehicles on each road. When the traffic status of vehicles on the lateral roads in each road is vehicle-free traffic, then based on the acquired map information, each road information acquired in real time and The predicted action trajectory is used to plan the first turning trajectory corresponding to the vehicle, that is, to plan the trajectory with a large turning radius, so that the vehicle is far away from the waiting area for pedestrians and non-motorized vehicles on the right.

In one embodiment, each road information includes vehicle traffic status on each road, each road includes a transverse road and a longitudinal road, and the right-turn trajectory includes the driving direction of the vehicle. When the traffic status of vehicles on the transverse roads in each road is that there are vehicles passing, and the passing direction of the passing vehicles is the same as the driving direction of the vehicles, the planned right turn trajectory at this time is the second turning trajectory, that is, the small turning trajectory. Obtain the passing direction and speed of the passing vehicle, and predict the passing trajectory of the passing vehicle according to the passing direction and passing speed. When the predicted passing trajectory and the right-turn trajectory overlap, the vehicle will give up passing, that is, stop driving; when passing When there is no coincidence between the trajectory and the right-turn trajectory, follow the right-turn trajectory of the vehicle, and perform the steps of obtaining the passing direction and speed of the passing vehicle, so as to predict the trajectory of the passing vehicle in real time. If the right-turn trajectory coincides, the vehicle will stop and wait for the passing vehicles to pass, and the vehicle will continue to drive according to the planned right-turn trajectory.

When the vehicle recognizes that there are special vehicles on each road through the camera sensor, that is, when it is recognized that there are warning lights on the vehicle and the vehicle runs a red light on a lateral road, it is determined that it is a special vehicle that is performing a task, and the vehicle will stop according to the planned right Drive on the turning track until the special vehicle cannot be recognized, then continue to drive on the right turning track. Special vehicles include ambulances, fire engines or other special circumstances vehicles.

In one embodiment, as shown in FIG. 6 , the right-turn trajectory of the vehicle is planned by a preset method based on various road information, map information and action trajectory, including sub-steps S310-S320.

Sub-step S310: Based on various road information, map information and action trajectory, the action path of the vehicle is planned through a dynamic programming algorithm.

In this embodiment, whether the vehicle is going to turn right will be determined through traffic decision-making according to various road information, map information and action trajectory, that is, the driving direction of the vehicle will be determined. After determining the driving direction, a number of optional driving paths are planned through DP (Dynamic Programming, dynamic programming), an optimal path is selected through DP path decision-making, and DP speed planning is carried out, so as to plan multiple speeds, and through DP speed decision-making Select the optimal speed curve to determine the vehicle's action path.

Sub-step S320: Optimizing the action path through a quadratic programming algorithm to obtain a right-turn trajectory of the vehicle.

The planned vehicle's action path is mostly uniform points, so interpolation processing is required, and dense points will be needed at the turn to realize the vehicle's path tracking. Because each path point on the planned action path has a corresponding speed, the trajectory and speed of the action path are optimized through QP (quadratic programming, quadratic programming algorithm), so as to obtain the right-turn trajectory of the vehicle. Planning through dynamic programming algorithms and quadratic programming algorithms is not the focus of this application, and will not be described in detail here.

In one embodiment, the method further includes step S400.

Step S400: When there is an obstacle on any zebra crossing, drive to the position according to the preset route, and detect the state of the obstacle on each zebra crossing every second preset period.

It can be understood that when there is an obstacle on any zebra crossing, that is, when there is an obstacle on the zebra crossing that the vehicle will pass through when passing the intersection according to the preset route, the vehicle will travel to the zebra crossing with the obstacle according to the preset route. The position of the distance from the preset interval, and the status of the obstacles on each zebra crossing will be detected every second preset interval, so as to determine whether there is an obstacle on each zebra crossing, and determine whether the obstacle is in a static state or in a moving state . Wherein, the preset distance and the second preset period will be set according to the actual situation.

The status of obstacles on each zebra crossing is detected at intervals of the second preset period. When there is an obstacle on any zebra crossing and the obstacle is in a stationary state, the vehicle will be at a preset interval from the zebra crossing where the obstacle exists. The location starts to get information about surrounding obstacles. For example, when the obstacle is not moving on a certain zebra crossing, such as pedestrians or bicycles waiting to cross the road, standing at the head of the zebra crossing does not move. At this time, relevant information of pedestrians or non-motor vehicles will be detected, so as to predict the movement of pedestrians or non-motor vehicles.

When there is an obstacle on any zebra crossing, and the obstacle is in a moving state, the vehicle will stop at a position with a preset distance from the zebra crossing where the obstacle exists, and every second preset cycle will check the speed of each obstacle on the zebra crossing. The state is detected until there are no obstacles on each zebra crossing. For example, when the horizontal road is in the state of green light, the vertical road is in the state of red light, and there is an obstacle on a certain zebra crossing and it is in a moving state.

In one embodiment, when the vehicle is driving on the longitudinal road according to the preset route, when the vehicle is driving to a position with a preset distance from the zebra crossing, if the recognized state of the traffic signal light of the longitudinal road is a yellow light state, then The vehicle will stop running, and continue to perform the step of identifying the state of obstacles on the zebra crossing that the vehicle at the turning intersection will pass through according to the preset route.

In this application, it can not only improve the safety and stability of the self-driving vehicle when driving in complex road conditions, but also further ensure the safety of the vehicle and passengers, and improve the comfort of passengers.

Based on the planning method for a right turn of an automatic driving vehicle in the above-mentioned embodiment, FIG. 7 shows a schematic structural diagram of a planning device 10 for a right turning of an automatic driving vehicle provided in an embodiment of the present application, which is applied to a vehicle to be turned. The automatic driving vehicle The planning device 10 for turning right comprises:

The perception module 11 is configured to obtain map information on turning intersections, identify the state of obstacles on each zebra crossing that the vehicle needs to pass through when passing through the turning intersection according to a preset route, and determine the state of obstacles on each zebra crossing The vehicle obtains the position of the relevant information of the surrounding obstacles.

A prediction module 12, configured to acquire the relevant information and various road information at intervals of a first preset period when the vehicle is at the position, and obtain the relevant information and various road information based on the various road information, the map information and the relevant information Predict the trajectory of the surrounding obstacles.

A planning module 13, configured to plan a right-turn trajectory of the vehicle based on the various road information, the map information, and the action trajectory, and control the vehicle to travel according to the right-turn trajectory.

The planning device 10 for planning a right turn of an automatic driving vehicle in this embodiment is used to implement the planning method for a right turning of an automatic driving vehicle in the above embodiment, and the implementation solutions and beneficial effects involved in the above embodiment are also applicable in this embodiment, and here No longer.

The embodiment of the present application also provides a terminal device, including a memory and a processor, the memory stores a computer program, and when the computer program runs on the processor, the above-mentioned right-turn planning method for an autonomous vehicle is executed.

The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed on a processor, implements the above-mentioned method for planning a right turn of an autonomous vehicle.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and structural diagrams in the accompanying drawings show the possible implementation architecture and functions of devices, methods and computer program products according to multiple embodiments of the present invention. and operation. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code that includes one or more Executable instructions. It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also to be noted that each block of the block diagrams and/or flow diagrams, and combinations of blocks in the block diagrams and/or flow diagrams, can be implemented by a dedicated hardware-based system that performs the specified function or action may be implemented, or may be implemented by a combination of special purpose hardware and computer instructions.

In addition, each functional module or unit in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. .

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. Should be covered within the protection scope of the present invention.

Claims (10)

1. A planning method for automatically driving a right turn of an automobile is characterized by being applied to a vehicle to be turned, and the method comprises the following steps:

obtaining map information of a turning intersection, identifying the states of obstacles on each zebra crossing which the vehicle needs to pass when the vehicle runs through the turning intersection according to a preset route, and determining the position of the vehicle for obtaining the related information of the surrounding obstacles according to the states of the obstacles on each zebra crossing;

when the vehicle is located at the position, acquiring the related information and each piece of road information at intervals of a first preset period, and predicting the action track of the surrounding obstacles based on each piece of road information, the map information and the related information;

planning a right turn track of the vehicle based on the road information, the map information and the action track, and controlling the vehicle to run according to the right turn track.

2. The method for planning a right turn of an autonomous vehicle of claim 1, wherein the determining the position of the vehicle to start acquiring the relevant information of the surrounding obstacles according to the state of the obstacles on the zebra crossing comprises:

when an obstacle exists on any one of the zebra crossings, the position which is away from the zebra crossings where the obstacle exists by a preset interval is used as the position for acquiring the related information;

and when no obstacle exists on each zebra crossing, taking the current position as the position obtained by the related information.

3. The method of claim 2, wherein the respective road information includes a respective traffic light status for the respective road, the method further comprising:

and when an obstacle exists on any one zebra crossing, driving to the position according to the preset route, and detecting the state of the obstacle on each zebra crossing every other second preset period.

4. The method of claim 1, wherein the respective road information includes a vehicle passing status on respective roads, the respective roads include lateral roads, the right turn trajectory includes a driving direction of the vehicle, the method further comprising:

when the vehicle passing state of the transverse road is that a vehicle passes through, and the passing direction of the passing vehicle is the same as the running direction, acquiring the passing direction and the passing speed of the passing vehicle, and predicting the passing track of the passing vehicle on the basis of the passing direction and the passing speed;

if the passing track is overlapped with the right turning track, stopping running;

and if the passing track does not coincide with the right turning track, driving according to the right turning track, and executing the step of acquiring the passing direction and the passing speed of the passing vehicle.

5. The method for planning a right turn of an autonomous vehicle as claimed in claim 1, wherein the predicting of the action trajectory of the surrounding obstacle based on the respective road information, the map information and the related information comprises:

predicting the advancing information of the surrounding obstacles based on the last relevant information of the surrounding obstacles and the current relevant information;

and determining the action track of the surrounding obstacles according to the advancing information, the map information and the road information.

6. The method for planning a right turn of an autonomous vehicle according to claim 1, wherein the planning a right turn trajectory of the vehicle by a preset method based on the respective road information, the map information and the action trajectory comprises:

drawing a movement path of the vehicle by a dynamic programming rule based on the respective road information, the map information, and the movement trajectory;

and optimizing the action path through a quadratic programming algorithm to obtain a right turning track of the vehicle.

7. The method for planning a right turn of an autonomous vehicle as claimed in claim 1, characterized in that the method further comprises:

and when the special vehicles are identified to exist on each road, stopping running according to the right turning track until the special vehicles cannot be identified.

8. A planning device for automatically driving a right turn of a car, applied to a car to be turned, the device comprising:

the sensing module is used for acquiring map information of a turning intersection, identifying the states of obstacles on each zebra crossing which the vehicle needs to pass when the vehicle runs through the turning intersection according to a preset route, and determining the position of the vehicle for acquiring the related information of the surrounding obstacles according to the states of the obstacles on each zebra crossing;

the prediction module is used for acquiring the related information and each road information every interval of a first preset period when the vehicle is positioned at the position, and predicting the action track of the surrounding obstacles based on each road information, the map information and the related information;

and the planning module is used for planning a right turning track of the vehicle based on the road information, the map information and the action track and controlling the vehicle to run according to the right turning track.

9. A terminal device, characterized in that it comprises a memory and a processor, the memory storing a computer program which, when run on the processor, executes the method for planning a right turn of an autonomous vehicle as claimed in any of claims 1 to 7.

10. A readable storage medium, characterized in that it stores a computer program which, when run on a processor, performs the method of planning a right turn of an autonomous vehicle as claimed in any of claims 1 to 7.

Images