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

Abstract

The application provides a planning method, device and terminal equipment for right turning of an autonomous vehicle. The planning method for right turning of the autonomous vehicle obtains map information of a turning intersection, identifies obstacle states on each zebra crossing through which the vehicle needs to pass when driving through the turning intersection according to a preset route, determines a position at which the vehicle obtains related information of surrounding obstacles according to the obstacle states, obtains the related information and each road information every first preset period when the vehicle is at the position, predicts action trajectories of the surrounding obstacles based on each road information, the map information and the related information, plans a right turning trajectory of the vehicle based on each road information, the map information and the action trajectories, and controls the vehicle to drive according to the right turning trajectory. The application can not only improve the safety and stability of the autonomous vehicle when driving in complex road conditions, but also further guarantee the safety of the vehicle and passengers and improve the comfort of passengers.

Description

Technical Field

[0001] This invention relates to the field of path planning, and more specifically, to a method, apparatus, and terminal device for planning right turns for autonomous vehicles. Background Technology

[0002] my country has a vast territory, and with the rapid development of transportation, there is an imbalance in transportation development. Many places lack right-turn indicators, and pedestrians and non-motorized vehicles often engage in irregular or even illegal traffic behaviors. In situations with high pedestrian and vehicle traffic, autonomous vehicles are prone to traffic accidents while turning, which may result in damage to people and property. Summary of the Invention

[0003] The purpose of this invention is to provide a planning method, apparatus, terminal device, and readable storage medium for right turns of autonomous vehicles.

[0004] In a first aspect, the present invention provides a planning method for right turns of an autonomous vehicle, applied to a vehicle about to turn, the method comprising:

[0005] The system acquires map information of the intersection, identifies the status of obstacles on each zebra crossing that the vehicle needs to pass through when traveling along a preset route through the intersection, and determines the location where the vehicle obtains relevant information about the surrounding obstacles based on the status of the obstacles on each zebra crossing.

[0006] When the vehicle is in the location, the relevant information and various road information are acquired at first preset intervals, and the movement trajectory of the surrounding obstacles is predicted based on the various road information, the map information and the relevant information;

[0007] Based on the road information, the map information, and the movement trajectory, the vehicle's right-turn trajectory is planned, and the vehicle is controlled to travel according to the right-turn trajectory.

[0008] In an optional implementation, determining the location where the vehicle begins acquiring relevant information about surrounding obstacles based on the state of the obstacles on the zebra crossing includes:

[0009] When there is an obstacle on any of the zebra crossings, the position at a preset distance from the zebra crossing with the obstacle will be used as the position for obtaining relevant information.

[0010] When there are no obstacles on any of the zebra crossings, the current position is used as the position obtained from the relevant information.

[0011] In an optional implementation, the road information includes the status of each traffic light on each road, and the method further includes:

[0012] When there is an obstacle on any zebra crossing, the vehicle travels to the location according to the preset route, and the status of the obstacles on each zebra crossing is detected every second preset period.

[0013] In an optional implementation, the road information includes vehicle traffic status on each road, the roads include transverse roads, the right-turn trajectory includes the vehicle's direction of travel, and the method further includes:

[0014] When the vehicle traffic status of the transverse road is that there are vehicles passing through, and the passing direction of the passing vehicles is the same as the driving direction, the passing direction and speed of the passing vehicles are obtained, and the passing trajectory of the passing vehicles is predicted based on the passing direction and the passing speed.

[0015] If the travel trajectory overlaps with the right turn trajectory, then stop driving;

[0016] If the travel trajectory does not overlap with the right turn trajectory, then the vehicle will travel according to the right turn trajectory and the steps of obtaining the travel direction and speed of the passing vehicle will be performed.

[0017] In an optional implementation, predicting the trajectory of the surrounding obstacles based on the various road information, the map information, and the relevant information includes:

[0018] Predict the forward movement information of the surrounding obstacles based on the previous relevant information and the current relevant information of the surrounding obstacles;

[0019] The trajectory of the surrounding obstacles is determined based on the forward information, the map information, and the road information.

[0020] In an optional implementation, the step of planning the vehicle's right-turn trajectory using a preset method based on the various road information, the map information, and the movement trajectory includes:

[0021] Based on the road information, the map information, and the movement trajectory, the vehicle's movement path is planned using a dynamic programming algorithm.

[0022] The right-turn trajectory of the vehicle is obtained by optimizing the movement path using a quadratic programming algorithm.

[0023] In an optional implementation, the method further includes:

[0024] When a special vehicle is detected on any of the roads, stop driving along the right-turn trajectory until no special vehicle can be detected.

[0025] Secondly, the present invention provides a planning device for right turns of an autonomous vehicle, applied to a vehicle about to turn, the device comprising:

[0026] The perception module is used to acquire map information of the turning intersection, identify the status of obstacles on each zebra crossing that the vehicle needs to pass through when traveling along the preset route through the turning intersection, and determine the location where the vehicle obtains relevant information about the surrounding obstacles based on the status of obstacles on each zebra crossing.

[0027] The prediction module is used to acquire the relevant information and various road information at first preset intervals when the vehicle is located at the position, and predict the movement trajectory of the surrounding obstacles based on the various road information, the map information and the relevant information;

[0028] The planning module is used to plan the right-turn trajectory of the vehicle based on the road information, the map information and the movement trajectory, and control the vehicle to drive according to the right-turn trajectory.

[0029] Thirdly, the present invention provides a terminal device, including a memory and a processor, wherein the memory stores a computer program, and the computer program executes the autonomous vehicle right turn planning method when it is run on the processor.

[0030] Fourthly, the present invention provides a readable storage medium storing a computer program that, when run on a processor, executes the method for planning right turns of an autonomous vehicle.

[0031] The beneficial effects of the embodiments of the present invention are:

[0032] This application provides a method for planning right turns for autonomous vehicles. This method is applied to the vehicle and involves acquiring map information of the turning intersection, identifying the obstacle states on each zebra crossing the intersection as the vehicle travels along a preset route, determining the location where the vehicle can obtain relevant information about surrounding obstacles based on the obstacle states, and acquiring relevant information and road information at first preset intervals when the vehicle is at that location. Based on the road information, map information, and relevant information, the method predicts the movement trajectories of surrounding obstacles, plans the vehicle's right-turn trajectory based on the road information, map information, and movement trajectories, and controls the vehicle to travel along the right-turn trajectory. This application not only improves the safety and stability of autonomous vehicles driving in complex road conditions but also further ensures the safety of the vehicle and passengers, improving passenger comfort.

[0033] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0034] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope of protection of the present invention. In the various drawings, similar components are numbered similarly.

[0035] Figure 1 The diagram shows a schematic of each road in a planning method for right turns of an autonomous vehicle according to an embodiment of this application;

[0036] Figure 2 A flowchart illustrating a planning method for right turns of an autonomous vehicle according to an embodiment of this application is shown.

[0037] Figure 3 The diagram shows various zebra crossings and obstacles in a planning method for right turns of an autonomous vehicle according to an embodiment of this application;

[0038] Figure 4 This paper illustrates a flowchart of a method for predicting the trajectory of an autonomous vehicle when making a right turn, as proposed in an embodiment of this application.

[0039] Figure 5 This illustration shows a schematic diagram of the planned right-turn trajectory in a planning method for right turns of an autonomous vehicle according to an embodiment of this application;

[0040] Figure 6 This paper illustrates a flowchart of the planning of a right-turn trajectory in a planning method for right turns of an autonomous vehicle according to an embodiment of this application.

[0041] Figure 7 A schematic diagram of the structure of a planning device for right turns of an autonomous vehicle provided in an embodiment of this application is shown.

[0042] Explanation of key component symbols:

[0043] 10- Planning device for right turns of autonomous vehicles; 11- Perception module; 12- Prediction module; 13- Planning module. Detailed Implementation

[0044] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0045] The components of the embodiments of the invention described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, 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 to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0046] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of the invention, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0047] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0048] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of the invention pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of the invention.

[0049] Example 1

[0050] During operation, autonomous vehicles may encounter complex intersections, such as those without right-turn indicators, intersections under construction, or intersections where accidents have occurred. When traffic and pedestrian flow are heavy, autonomous vehicles are prone to accidents when turning at complex intersections. Therefore, for autonomous vehicles, planning a compliant, smooth, and accident-free route is crucial for ensuring vehicle safety and passenger comfort. This application, taking into account current traffic safety laws, traffic lights, pedestrians, and non-motorized vehicles at intersections, provides a planning method for right turns of autonomous vehicles in scenarios without right-turn indicators.

[0051] In this embodiment, as Figure 1As shown in the diagram, when the vehicle reaches point A and is about to make a right turn, the transverse and longitudinal roads in this embodiment are as follows: the vehicle's travel direction is the longitudinal road, and the road perpendicular to the longitudinal road is the transverse road. When the vehicle's global route planning module is planning the route, it plans a preset route with right turns. When the autonomous vehicle travels to the vicinity of the right-turn intersection according to the planned route, the autonomous vehicle will retrieve the traffic regulations of the right-turn intersection through the Internet of Things to determine whether it is permissible to turn right when the longitudinal road light at the intersection is red. It will also identify the signs and traffic lights at the right-turn intersection to determine if there is a right-turn indicator light and again determine whether the vehicle can turn right when the longitudinal road light is red. The vehicle will also retrieve a high-definition map of the intersection to check if there is a dedicated right-turn lane. When it is determined that the vehicle is allowed to turn right when the longitudinal road light at the intersection is red, and there is no right-turn indicator light or dedicated right-turn lane at the right-turn intersection, the autonomous vehicle right-turn planning method provided in this application embodiment will be invoked.

[0052] Please refer to Figure 2 This application proposes a planning method for right turns of an autonomous vehicle, applied to a vehicle to be turned. Exemplarily, the planning method for right turns of an autonomous vehicle includes steps S100 to S300.

[0053] Step S100: Obtain map information of the turning intersection, identify the status of obstacles on each zebra crossing that the vehicle needs to pass through when traveling along the preset route through the turning intersection, and determine the location where the vehicle obtains relevant information about the surrounding obstacles based on the status of obstacles on each zebra crossing.

[0054] Understandably, when a vehicle approaches a turning intersection, it will acquire map information about that intersection. This map information can be a high-resolution map, including relevant information about the turning intersection. The vehicle will also use its onboard camera sensors to identify the status of obstacles on each zebra crossing it will pass as it travels along a preset route through the intersection. Based on the status of these obstacles, the vehicle will determine the location from which it has acquired information about the surrounding obstacles.

[0055] The obstacles include, but are not limited to, any one or more of pedestrians, non-motorized vehicles, objects, animals, and vehicles. The state of obstacles on a zebra crossing includes both the absence of obstacles and the presence of obstacles. The presence of obstacles on a zebra crossing includes both moving and stationary obstacles. Figure 3 As shown, the vehicle is at point A. The vehicle will pass through the first zebra crossing (a) and the second zebra crossing (b) when it travels through the intersection according to the preset route. The elliptical shaded area in the figure may be an obstacle, namely a gathering place for pedestrians or non-motorized vehicles.

[0056] In this embodiment, when an obstacle is detected on any of the zebra crossings along the vehicle's pre-planned route, the location at a preset distance from the zebra crossing with the obstacle is used as the location for acquiring relevant information. At this location, LiDAR is used to acquire information about the surrounding obstacle. When the vehicle passes the intersection along the preset route and there are no obstacles on any of the zebra crossings, the vehicle's current position is used as the location for acquiring relevant information; that is, the vehicle immediately acquires information about the surrounding obstacle at its current position. The preset interval will be set according to the actual situation; the relevant information includes, but is not limited to, the position and orientation of the obstacle, and the relative distance between the obstacle and the vehicle.

[0057] In this embodiment, the vehicle will also be located in real time. Since the vehicle is at an intersection with multiple traffic lines, such as zebra crossings, solid lines before the zebra crossings, and traffic light strips, inaccurate vehicle positioning can easily lead to traffic violations and even traffic accidents. Currently, the maximum accuracy of satellite positioning is 2.5 meters, but for autonomous vehicles in urban areas, relying solely on satellite positioning is far from sufficient. Therefore, this embodiment uses a combination of satellite positioning and RTK (Real-time Kinematic) positioning technology, achieving centimeter-level positioning. The satellite positioning is either GPS (Global Positioning System) or the BeiDou Navigation Satellite System, ensuring that the acquired vehicle location information meets the requirements for autonomous vehicle positioning. Furthermore, to ensure the vehicle brakes accurately before the zebra crossing, a combination of satellite positioning, RTK, and camera sensors will be used.

[0058] Step S200: When the vehicle is in this position, relevant information and various road information are acquired at first preset intervals, and the movement trajectory of surrounding obstacles is predicted based on the various road information, map information and relevant information.

[0059] Understandably, when the vehicle begins acquiring relevant information immediately at its current location, it will acquire information about surrounding obstacles and various roads every first preset period. Furthermore, it will predict the movement trajectories of surrounding obstacles based on the acquired road information, map information, and related information.

[0060] This road information includes, but is not limited to, the status of traffic lights and obstacles on each road. Traffic light status includes green and red light states. For example... Figure 1As shown, each road includes, but is not limited to, transverse roads and longitudinal roads. The obstacle status on each road includes the following states: obstacles exist on all roads, obstacles do not exist on any roads, obstacles exist on transverse roads but not on longitudinal roads, and obstacles exist on longitudinal roads but not on transverse roads.

[0061] In one implementation, such as Figure 4 As shown, the movement trajectory of surrounding obstacles is predicted based on various road information, map information and related information, including sub-steps S210 to S220.

[0062] Sub-step S210: Predict the forward movement information of surrounding obstacles based on the previous relevant information and the current relevant information of surrounding obstacles.

[0063] It is understood that the vehicle will acquire relevant information about surrounding obstacles every first preset period. In this embodiment, the forward movement information of the surrounding obstacles will be predicted based on the previously acquired relevant information and the current relevant information. The forward movement information includes the direction and speed of the surrounding obstacles. Because the intersection environment is complex when the autonomous vehicle approaches an intersection, the speed of the autonomous vehicle passing through the intersection can be controlled to be less than or equal to a preset intersection speed, which can be 30 km / h.

[0064] In this embodiment, the formula will be used. t_1 and t_0 represent time, v 行 Let t0(x0, y0) represent the speed of the obstacle being predicted, t1(x1, y1) represent the position of a nearby obstacle at time t0 (x0, y0), and t1(x1, y1) represent the position of that obstacle at time t1 (x1, y1). This coordinate system can be a planar coordinate system with the center point of the intersection to be turned as the origin. Using the above formula, the speed of the predicted obstacle can be determined. From t0 to t1, the direction of travel of the obstacle can be determined. Based on the above method, the speed and direction of obstacles t1 and t2, the speed and direction of travel of obstacles t2 and t3, and so on, can be obtained for obstacles t3 and t4, and so on.

[0065] Sub-step S220: Determine the trajectory of surrounding obstacles based on forward information, map information, and road information.

[0066] After determining at least one set of forward information about the surrounding obstacles, the movement trajectory of the surrounding obstacles will be determined by combining the traffic light status of each road and map information obtained through the camera sensor. The movement trajectory includes the movement intention of obstacles such as pedestrians or vehicles, that is, information such as the direction and speed of the obstacle's movement.

[0067] For example, when the obstacle is a pedestrian, if the pedestrian's direction of travel from t0 to t1, t1 to t2, etc., is along the zebra crossing direction, that is, when the pedestrian is traveling on the transverse road, they are moving along the zebra crossing direction on the transverse road, and the speed in multiple sets of forward information obtained by the formula is greater than the preset speed, or most of the forward speeds are greater than the preset speed, then it can be determined that the pedestrian may be about to cross the zebra crossing. At this time, the traffic light information will be identified to predict the pedestrian's movement trajectory in order to prevent the obstacle from suddenly entering the vehicle's driving path.

[0068] For example, if the traffic light at the zebra crossing where a pedestrian is about to cross is green, it can be determined that the pedestrian intends to cross the zebra crossing. At the same time, based on relevant information about the zebra crossing, such as its location and width, as well as the pedestrian's direction of travel, the pedestrian's trajectory can be predicted. If the traffic light at the zebra crossing is red, it can be determined that the pedestrian will not cross the zebra crossing. The preset speed can be set to the speed of a normal person walking normally, depending on the situation.

[0069] Step S300: Based on various road information, map information and movement trajectory, plan the vehicle's right turn trajectory and control the vehicle to drive according to the right turn trajectory.

[0070] Understandably, after determining the movement paths of obstacles around the vehicle, the vehicle's right-turn trajectory will be planned using preset methods based on various road information, map information, and movement trajectory, thereby improving the vehicle's driving safety and stability.

[0071] Among them, such as Figure 5 As shown, the right turn trajectory includes a first turn trajectory and a second turn trajectory. Point A is the vehicle's center of gravity, point B is the intersection of the right longitudinal zebra crossing and the center line of the right lane, and point C is the intersection of the right longitudinal zebra crossing and the center line of the left lane. 'a' is the first zebra crossing, which is the lower transverse zebra crossing, and 'b' is the second zebra crossing, which is the right longitudinal zebra crossing. The first turn trajectory can be planned by combining points A and C, and the second turn trajectory can be planned by combining points A and B.

[0072] In this embodiment, the road information includes the vehicle traffic status on each road. When the vehicle traffic status on the transverse road in each road is that there are no vehicles passing through, the first turning trajectory corresponding to the vehicle will be planned based on the acquired map information, the real-time acquired road information and the predicted movement trajectory. That is, a large turning radius trajectory will be planned so that the vehicle stays away from the waiting area for pedestrians and non-motorized vehicles on the right.

[0073] In one implementation, the road information includes the traffic status of vehicles on each road, and each road includes transverse roads and longitudinal roads. The right-turn trajectory includes the vehicle's direction of travel. When there are vehicles traveling on the transverse roads, and the direction of travel of the vehicles is the same as the direction of travel of the vehicles, the planned right-turn trajectory is the second turning trajectory, i.e., the small turning trajectory. The direction and speed of the passing vehicles are acquired, and the trajectory of the passing vehicles is predicted based on the direction and speed. When the predicted trajectory overlaps with the right-turn trajectory, the vehicle will abandon its journey and stop. When the trajectory does not overlap with the right-turn trajectory, the vehicle will proceed according to the right-turn trajectory and the steps of acquiring the direction and speed of the passing vehicles will be executed to predict the trajectory of oncoming vehicles in real time. If the vehicle trajectory changes and overlaps with the right-turn trajectory during the journey, the vehicle will stop and wait for oncoming vehicles to pass. The vehicle will then continue to travel according to the planned right-turn trajectory.

[0074] When a vehicle's camera sensors detect special vehicles on various roads—for example, vehicles with warning lights or those running red lights on cross roads—it is determined to be special vehicles on a mission. The vehicle will stop following its planned right-turn trajectory until no more special vehicles are detected, at which point it will resume its right-turn trajectory. Special vehicles include ambulances, fire trucks, or other vehicles used in special circumstances.

[0075] In one implementation, such as Figure 6 As shown, the right-turn trajectory of the vehicle is planned using a preset method based on various road information, map information and movement trajectory, including sub-steps S310 to S320.

[0076] Sub-step S310: Based on various road information, map information, and movement trajectory, the vehicle's movement path is planned using a dynamic programming algorithm.

[0077] In this embodiment, traffic decision-making is used to determine whether a vehicle will turn right, i.e., to determine the vehicle's direction of travel, based on various road information, map information, and travel trajectory. After determining the direction of travel, multiple optional travel paths are planned using Dynamic Programming (DP). The optimal path is selected through DP path decision-making, and DP speed planning is performed to plan multiple speed segments. The optimal speed curve is then selected through DP speed decision-making to determine the vehicle's travel path.

[0078] Sub-step S320: Optimize the movement path using a quadratic programming algorithm to obtain the vehicle's right turn trajectory.

[0079] The planned vehicle path consists mostly of uniformly distributed points, requiring interpolation. At turns, denser points are needed for path tracking. Since each point on the planned path has a corresponding speed, quadratic programming (QP) is used to optimize the trajectory and speed, resulting in the vehicle's right-turn trajectory. The use of dynamic programming and quadratic programming algorithms for planning is not the focus of this application and will not be elaborated upon here.

[0080] In one embodiment, the method further includes step S400.

[0081] Step S400: When there is an obstacle on any zebra crossing, drive to that location according to the preset route, and detect the status of the obstacles on each zebra crossing every second preset period.

[0082] Understandably, when an obstacle exists on any zebra crossing—that is, when a vehicle travels along a preset path through the intersection and encounters an obstacle on one of the zebra crossings—the vehicle will follow the preset route to a position at a preset distance from the zebra crossing containing the obstacle. Furthermore, every second preset period, the status of obstacles on each zebra crossing will be detected to determine whether an obstacle exists on each zebra crossing and whether the obstacle is stationary or moving. The preset distance and the second preset period will be set according to actual conditions.

[0083] Every second preset cycle, the status of obstacles on each zebra crossing is detected. When an obstacle exists on any zebra crossing and is stationary, the vehicle will begin acquiring relevant information about surrounding obstacles at a preset distance from the zebra crossing where the obstacle is located. For example, when an obstacle is stationary on a zebra crossing, such as when a pedestrian or non-motorized vehicle is waiting to cross the road and standing still at the end of the zebra crossing, relevant information about the pedestrian or non-motorized vehicle will be detected to predict their movement.

[0084] When an obstacle is present on any zebra crossing and is in motion, the vehicle will stop at a preset distance from the zebra crossing where the obstacle is located. The vehicle will then check the status of obstacles on each zebra crossing every second preset period until no obstacles remain on any zebra crossing. For example, when the crosswalk light is green and the road light is red, and an obstacle is present on a zebra crossing and is in motion.

[0085] In one implementation, when a vehicle is traveling along a longitudinal road according to a preset route, if the traffic light on the longitudinal road is detected to be yellow when the vehicle reaches a position at a preset distance from the zebra crossing, the vehicle will stop and continue to execute the step of identifying the status of obstacles on each zebra crossing that the vehicle will pass through when traveling along the preset route at the turning intersection.

[0086] This application not only improves the safety and stability of autonomous vehicles when driving in complex road conditions, but also further ensures the safety of the vehicle and passengers, and improves passenger comfort.

[0087] The autonomous vehicle right turn planning method based on the above embodiments, Figure 7 This illustration shows a structural schematic diagram of a right-turn planning device 10 for an autonomous vehicle according to an embodiment of this application. Applied to a vehicle about to turn, the right-turn planning device 10 for an autonomous vehicle includes:

[0088] The perception module 11 is used to acquire map information of the turning intersection, identify the status of obstacles on each zebra crossing that the vehicle needs to pass through when traveling along a preset route through the turning intersection, and determine the location where the vehicle obtains relevant information about the surrounding obstacles based on the status of the obstacles on each zebra crossing.

[0089] The prediction module 12 is used to acquire the relevant information and various road information at first preset intervals when the vehicle is located at the position, and predict the movement trajectory of the surrounding obstacles based on the various road information, the map information and the relevant information.

[0090] The planning module 13 is used to plan the right-turn trajectory of the vehicle based on the road information, the map information and the movement trajectory, and control the vehicle to drive according to the right-turn trajectory.

[0091] The autonomous vehicle right-turn planning device 10 of this embodiment is used to execute the autonomous vehicle right-turn planning method of the above embodiment. The implementation schemes and beneficial effects involved in the above embodiments are also applicable to this embodiment, and will not be repeated here.

[0092] This application also provides a terminal device, including a memory and a processor. The memory stores a computer program, and the computer program executes the above-described planning method for right turns of an autonomous vehicle when it runs on the processor.

[0093] This application also provides a computer-readable storage medium storing a computer program that, when executed on a processor, implements the above-described method for planning right turns for an autonomous vehicle.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0095] In addition, the functional modules or units in the various embodiments 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.

[0096] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0097] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A planning method for right turns of an autonomous vehicle, characterized in that, Applied to vehicles about to turn, the method includes: The system acquires map information of the intersection, identifies the status of obstacles on each zebra crossing that the vehicle needs to pass through when traveling along a preset route through the intersection, and determines the location where the vehicle obtains relevant information about the surrounding obstacles based on the status of the obstacles on each zebra crossing. When the vehicle is in the location, the relevant information and various road information are acquired at first preset intervals, and the movement trajectory of the surrounding obstacles is predicted based on the various road information, the map information and the relevant information; Based on the road information, the map information, and the movement trajectory, the vehicle's right-turn trajectory is planned, and the vehicle is controlled to travel according to the right-turn trajectory. The feature is that determining the location where the vehicle begins acquiring relevant information about surrounding obstacles based on the state of the obstacles on the zebra crossing includes: When there is an obstacle on any of the zebra crossings, the position at a preset distance from the zebra crossing with the obstacle will be used as the position for obtaining relevant information. When there are no obstacles on any of the zebra crossings, the current position is used as the position obtained from the relevant information.

2. The planning method for right turns of an autonomous vehicle according to claim 1, characterized in that, The road information includes the status of each traffic light on each road, and the method further includes: When there is an obstacle on any zebra crossing, the vehicle travels to the location according to the preset route, and the status of the obstacles on each zebra crossing is detected every second preset period.

3. The planning method for right turns of an autonomous vehicle according to claim 1, characterized in that, The road information includes vehicle traffic status on each road, the roads include transverse roads, the right turn trajectory includes the vehicle's direction of travel, and the method further includes: When the vehicle traffic status of the transverse road is that there are vehicles passing through, and the passing direction of the passing vehicles is the same as the driving direction, the passing direction and speed of the passing vehicles are obtained, and the passing trajectory of the passing vehicles is predicted based on the passing direction and the passing speed. If the travel trajectory overlaps with the right turn trajectory, then stop driving; If the travel trajectory does not overlap with the right turn trajectory, then the vehicle will travel according to the right turn trajectory and the steps of obtaining the travel direction and speed of the passing vehicle will be performed.

4. The planning method for right turns of an autonomous vehicle according to claim 1, characterized in that, The prediction of the movement trajectory of the surrounding obstacles based on the road information, the map information, and the relevant information includes: Predict the forward movement information of the surrounding obstacles based on the previous relevant information and the current relevant information of the surrounding obstacles; The trajectory of the surrounding obstacles is determined based on the forward information, the map information, and the road information.

5. The planning method for right turns of an autonomous vehicle according to claim 1, characterized in that, The step of planning the vehicle's right-turn trajectory using a preset method based on the road information, map information, and movement trajectory includes: Based on the road information, the map information, and the movement trajectory, the vehicle's movement path is planned using a dynamic programming algorithm. The right-turn trajectory of the vehicle is obtained by optimizing the movement path using a quadratic programming algorithm.

6. The planning method for right turns of an autonomous vehicle according to claim 1, characterized in that, The method further includes: When a special vehicle is detected on any of the roads, stop driving along the right-turn trajectory until no special vehicle can be detected.

7. A planning device for right turns of an autonomous vehicle, characterized in that, Applied to vehicles about to turn, the device includes: The perception module is used to acquire map information of the turning intersection, identify the status of obstacles on each zebra crossing that the vehicle needs to pass through when traveling along the preset route through the turning intersection, and determine the location where the vehicle obtains relevant information about the surrounding obstacles based on the status of obstacles on each zebra crossing. The prediction module is used to acquire the relevant information and various road information at first preset intervals when the vehicle is located at the position, and predict the movement trajectory of the surrounding obstacles based on the various road information, the map information and the relevant information; The planning module is used to plan the right-turn trajectory of the vehicle based on the road information, the map information and the movement trajectory, and control the vehicle to drive according to the right-turn trajectory.

8. A terminal device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed on the processor, performs the planning method for right turns of an autonomous vehicle according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that, It stores a computer program that, when run on a processor, executes the planning method for right turns of an autonomous vehicle as described in any one of claims 1 to 6.

Images