Trajectory planning method, device and electronic equipment for autonomous vehicle

Abstract

The application discloses a trajectory planning method and device of an automatic driving vehicle and electronic equipment, and the method comprises the following steps: obtaining a global path planning result of the automatic driving vehicle, and the result specifically comprises a global lane center line; obtaining current driving state information of the automatic driving vehicle, and the information specifically comprises a current distance between the vehicle and a parking point and a current driving speed; determining a current driving stage according to the current driving state information, and the stage specifically comprises a starting stage, a cruising stage and a parking stage; and performing local trajectory planning by using a local trajectory planning strategy corresponding to the current driving stage based on the global path planning result, so as to control the automatic driving vehicle to drive according to a local trajectory planning result, and the local trajectory planning result comprises a longitudinal speed planning result corresponding to the current driving stage. The application realizes trajectory planning of the automatic driving vehicle in each driving stage, focuses on solving the planning of a longitudinal reference speed, and meets the comfort and precision requirements of each driving stage, especially the parking stage.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a trajectory planning method, apparatus and electronic device for autonomous vehicles. Background Technology

[0002] Trajectory planning for autonomous vehicles involves planning the desired driving path of the vehicle over a future period. It needs to meet requirements such as vehicle kinematics, dynamics, comfort, collision avoidance, and driving accuracy. Since the requirements for these aspects differ at different driving stages, accurately and efficiently planning the vehicle's trajectory at different driving stages is of great significance for ensuring the driving safety, accuracy, and comfort of autonomous vehicles.

[0003] Taking the parking phase as an example, existing autonomous driving parking systems are mostly called Automatic Parking Systems (APS). Autonomous parking refers to a vehicle automatically identifying parking spaces based on vehicle and roadside sensors, planning a feasible parking trajectory through path planning algorithms, and finally, under the control of the controller, following the planned trajectory to achieve parking. The entire process involves the coordinated work of multiple modules such as vehicle environmental perception, path planning, and control. Because perception is greatly affected by the surrounding environment, it is not very accurate in parking space identification. Moreover, the positioning modules of most vehicles cannot receive signals in underground parking garages, making path planning difficult. This poses a significant obstacle to the application of autonomous parking systems in family SUVs or sedans. However, when autonomous vehicles operate on open urban main roads with fixed parking spots, they can use GPS for high-precision positioning without environmental interference. Furthermore, on open roads, LiDAR and cameras have a high obstacle recognition rate, thus providing important support for trajectory planning of autonomous vehicles during the parking phase.

[0004] However, there is still a lack of a systematic and refined trajectory planning scheme for autonomous vehicles across all stages in the current technology, especially the trajectory planning and control effect for the precise parking stage still needs to be improved. Summary of the Invention

[0005] This application provides a trajectory planning method, apparatus, and electronic device for autonomous vehicles to meet the accuracy and comfort requirements of autonomous vehicles at various driving stages.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, embodiments of this application provide a trajectory planning method for an autonomous vehicle, wherein the method includes:

[0008] Obtain the global path planning results for autonomous vehicles, including global lane centerlines;

[0009] Obtain the current driving status information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle;

[0010] The current driving stage of the autonomous vehicle is determined based on the current driving status information of the autonomous vehicle. The current driving stage includes the starting stage, the cruising stage, and the parking stage.

[0011] Based on the global path planning results, the autonomous vehicle is used to perform local trajectory planning using a local trajectory planning strategy corresponding to the current driving stage, so as to control the autonomous vehicle's driving according to the local trajectory planning results. The local trajectory planning results include the longitudinal speed planning results corresponding to the current driving stage.

[0012] Optionally, determining the current driving stage of the autonomous vehicle based on its current driving state information includes:

[0013] The trigger speed for the parking phase is determined based on the current driving status information of the autonomous vehicle.

[0014] Based on the current driving speed of the autonomous vehicle and the trigger speed of the parking phase, it is determined whether the autonomous vehicle needs to enter the parking phase.

[0015] Optionally, determining the trigger speed for the parking phase based on the current driving status information of the autonomous vehicle includes:

[0016] The trigger acceleration for the parking phase is determined based on the current driving speed of the autonomous vehicle.

[0017] The trigger speed for the parking phase is determined based on the current distance between the autonomous vehicle and the parking point and the trigger acceleration for the parking phase.

[0018] Optionally, determining whether the autonomous vehicle needs to enter the parking phase based on the current driving speed of the autonomous vehicle and the trigger speed of the parking phase includes:

[0019] If the current driving speed of the autonomous vehicle is not less than the trigger speed of the parking phase, then it is determined that the autonomous vehicle needs to enter the parking phase.

[0020] Otherwise, it is determined that the autonomous vehicle does not need to enter the parking phase.

[0021] Optionally, the current driving stage is the parking stage, and the step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using a local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes:

[0022] Obtain the planning parameters for the parking phase, including the first braking rate;

[0023] Based on the global path planning results and the planning parameters of the parking stage, local trajectory planning for the parking stage is performed to obtain the local trajectory planning results for the parking stage.

[0024] Optionally, the current driving stage is the starting stage, and the step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using a local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes:

[0025] The planning parameters for the initial stage are obtained, including a first acceleration and a second acceleration, wherein the first acceleration is the maximum acceleration of the autonomous vehicle, and the second acceleration is the acceleration caused by the change in the impact rate during the operation of the autonomous vehicle.

[0026] Based on the global path planning results and the planning parameters of the initial stage, local trajectory planning for the initial stage is performed to obtain the local trajectory planning results for the initial stage.

[0027] Optionally, the current driving stage is the cruise stage, and the step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using a local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes:

[0028] The planning parameters for the cruise phase are obtained, including the maximum speed limit of the autonomous vehicle, the maximum speed limit of the road where the autonomous vehicle is located, the safe speed of the autonomous vehicle relative to the obstacle in front, and the delay factor.

[0029] Based on the global path planning results and the planning parameters of the cruise phase, local trajectory planning for the cruise phase is performed to obtain the local trajectory planning results for the cruise phase.

[0030] Optionally, the safe speed of the autonomous vehicle relative to the obstacle ahead is determined in the following manner:

[0031] Obtain the current speed of the autonomous vehicle;

[0032] The safe distance between the autonomous vehicle and the obstacle ahead is determined based on the current speed of the autonomous vehicle and the safety margin constant.

[0033] The safe speed of the autonomous vehicle relative to the obstacle ahead is determined based on the safe distance between the autonomous vehicle and the obstacle ahead and the maximum deceleration of the autonomous vehicle.

[0034] Secondly, embodiments of this application also provide a trajectory planning device for an autonomous vehicle, wherein the device includes:

[0035] The first acquisition unit is used to acquire the global path planning result of the autonomous vehicle, the global path planning result including the global lane centerline;

[0036] The second acquisition unit is used to acquire the current driving status information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle.

[0037] The determining unit is configured to determine the current driving stage of the autonomous vehicle based on the current driving state information of the autonomous vehicle, wherein the current driving stage includes a starting stage, a cruising stage, and a parking stage.

[0038] The planning unit is used to perform local trajectory planning for the autonomous vehicle based on the global path planning result and using the local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle, so as to control the driving of the autonomous vehicle according to the local trajectory planning result. The local trajectory planning result includes the longitudinal speed planning result corresponding to the current driving stage.

[0039] Thirdly, embodiments of this application also provide an electronic device, including:

[0040] Processor; and

[0041] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0042] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform any of the methods described above.

[0043] The above-mentioned at least one technical solution adopted in the embodiments of this application can achieve the following beneficial effects: The trajectory planning method for autonomous vehicles in the embodiments of this application first obtains the global path planning result of the autonomous vehicle, which includes the global lane centerline; then, it obtains the current driving state information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle; then, it determines the current driving stage of the autonomous vehicle based on the current driving state information, which includes the starting stage, the cruising stage, and the parking stage; finally, based on the global path planning result, it performs local trajectory planning for the autonomous vehicle using the local trajectory planning strategy corresponding to the current driving stage, so as to control the driving of the autonomous vehicle according to the local trajectory planning result, which includes the longitudinal speed planning result corresponding to the current driving stage. The trajectory planning method for autonomous vehicles in the embodiments of this application realizes the local trajectory planning of the autonomous vehicle in each driving stage, focuses on solving the planning of the longitudinal reference speed of the autonomous vehicle, and meets the comfort and accuracy requirements of each driving stage, especially the parking stage. Attached Figure Description

[0044] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0045] Figure 1 This is a schematic diagram of the overall process of trajectory planning for an autonomous vehicle in an embodiment of this application;

[0046] Figure 2 This is a flowchart illustrating a trajectory planning method for an autonomous vehicle according to an embodiment of this application.

[0047] Figure 3 This is a schematic diagram of a global path planning result in an embodiment of this application;

[0048] Figure 4 This is a schematic diagram of a local trajectory planning method in an embodiment of this application;

[0049] Figure 5 This is a schematic diagram illustrating a process of entering the parking stage in an embodiment of this application;

[0050] Figure 6 This is a schematic diagram of the control flow of a dual closed-loop PID algorithm in an embodiment of this application;

[0051] Figure 7 This is a schematic diagram of the self-test process of an autonomous driving system in an embodiment of this application;

[0052] Figure 8 This is a schematic diagram of the structure of a trajectory planning device for an autonomous vehicle according to an embodiment of this application;

[0053] Figure 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0056] For ease of understanding of the various embodiments of this application, such as Figure 1 The diagram illustrates the overall process of trajectory planning for an autonomous vehicle according to an embodiment of this application. This process is primarily accomplished through the cooperation of various modules within the autonomous driving system. The autonomous driving system mainly comprises an APP application module, a perception module, a positioning module, a 5G communication module, a path planning module, and a control module. Wherein:

[0057] 1) APP application module

[0058] An in-vehicle terminal is installed in autonomous vehicles to deploy an app. The app module transmits order data in real-time to the vehicle's domain controller via network communication. The planning module uses this order information to determine the starting and ending points of the route, performs global route planning, and selects the optimal path. Simultaneously, the app receives high-precision map positioning data and obstacle data from the perception module, displaying and broadcasting obstacle information in real-time on the terminal interface. The app serves as a command transmitter and visualizes environmental perception data, acting as a human-machine interface software integrated with autonomous driving.

[0059] 2) 5G communication module

[0060] Autonomous driving systems involve many modules, and the data of each module is interdependent and highly coupled. They also have high requirements for the real-time performance and responsiveness of data transmission. By using 5G communication networks, the advantages of low latency and fast response of 5G communication can be used to transmit data to each module in real time for algorithm calculation and solution. 5G communication is one of the essential components for realizing real-time data transmission.

[0061] 3) Positioning and Sensing Module

[0062] The vehicle needs a positioning module to obtain its real-time location so that it knows where it is. Guided by a "path," the vehicle will move along the path and stop at the designated parking spot. Therefore, the positioning module must be present at all times and updated in real time. The data obtained from the positioning is transmitted to other modules via 5G network communication for their use. When there are pedestrians or other obstacles in front of the vehicle, the perception system needs to obtain obstacle information and provide it to the planning module to make corresponding decisions.

[0063] 4) Path planning module

[0064] The path planning module is divided into global path planning and local trajectory planning. There are countless drivable paths between the starting point and the final destination. However, considering traffic rules, time, and cost, the path planning module first plans an optimal path—the lane centerline—globally. Then, based on the lane centerline, it uses a local planning algorithm to plan a reference trajectory with time information, enabling the vehicle to follow the reference trajectory. One of the improvements in this application is the local trajectory planning for the autonomous vehicle during the parking phase, ensuring that the vehicle can park smoothly and accurately when it is about to reach each parking point in the entire driving path.

[0065] 5) Control Module

[0066] The main task of the control module is to follow the reference trajectory, enabling the vehicle to drive to the parking point and stop according to the reference trajectory.

[0067] The entire autonomous driving system is a serial system, with each module having its own task division and interdependence, which provides important support for the trajectory planning method of autonomous vehicles in this application.

[0068] Based on this, embodiments of this application provide a trajectory planning method for autonomous vehicles, such as... Figure 2 The diagram shows a flowchart of a trajectory planning method for an autonomous vehicle according to an embodiment of this application. The method includes at least the following steps S210 to S240:

[0069] Step S210: Obtain the global path planning result of the autonomous vehicle, wherein the global path planning result includes the global lane centerline.

[0070] The trajectory planning method for autonomous vehicles in this application mainly targets the local trajectory planning of autonomous vehicles. However, local trajectory planning depends on the results of global path planning. Therefore, this application requires obtaining the global path planning results of autonomous vehicles first, which may include information such as global lane center lines.

[0071] The role of global path planning is to plan the global lane centerline based on the location information of the starting point and final destination points issued by the application program. For example, for a global path from point A to point B, algorithms such as Dijkstra's algorithm, Rapidly Exploring Random Tree (RRT) or A* algorithm can be used to quickly find a driving route that meets the given conditions. Figure 3 As shown, a schematic diagram of a global path planning result in an embodiment of this application is provided.

[0072] Taking the A* algorithm as an example, in the embodiments of this application, a cost function cosFun can be pre-designed when performing global path planning. Considering relevant influencing factors such as path length, time, and congestion level, the optimal path is determined, and the lane centerline from the starting point to the final destination is determined.

[0073] cosFun = f(path, path length, time, congestion level), (1)

[0074] Step S220: Obtain the current driving status information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle.

[0075] The lane centerline contains position and heading information, and a local trajectory for the vehicle can be set based on the lane centerline. However, the local trajectory differs from the global path; it contains reference speed information in the time dimension. Therefore, the main task of the local trajectory planning layer is to plan the longitudinal reference speed of the vehicle.

[0076] Before planning the longitudinal reference speed for vehicle travel, it is necessary to obtain the current driving status information of the autonomous vehicle. Specifically, this can include the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle. The current distance between the autonomous vehicle and the parking point can be measured based on the lidar on the autonomous vehicle, and the current driving speed can be collected based on the speed sensor on the autonomous vehicle.

[0077] It should be noted that the "parking point" in this application embodiment is not limited to the stopping stations of autonomous vehicles, but may also include traffic intersections where parking is required. Specifically, whether parking is required at a traffic intersection can be determined by recognizing the traffic light status. In addition, it may include any other location where parking is required. Since multiple parking points may be passed during the entire global driving path, the parking point here can refer to the parking point that is closest to the current position of the autonomous vehicle.

[0078] Step S230: Determine the current driving stage of the autonomous vehicle based on the current driving status information of the autonomous vehicle. The current driving stage includes the starting stage, the cruising stage, and the parking stage.

[0079] The driving speed and distance to the parking point of an autonomous vehicle determine its current driving stage. Therefore, the current driving stage of an autonomous vehicle can be determined based on its current distance to the parking point and its current driving speed. The driving stage can be divided into the starting stage, the cruising stage, and the parking stage. The starting stage can be regarded as the first stage of vehicle driving, the cruising stage as the second stage, and the parking stage as the third stage.

[0080] like Figure 4 As shown, a schematic diagram of local trajectory planning in an embodiment of this application is provided. It can be seen that the driving speed and driving acceleration required by the autonomous vehicle are different in different driving stages. How to achieve the optimal local trajectory planning effect in each driving stage is one of the objectives of this application embodiment.

[0081] The three stages described above can be seen as the possible stages an autonomous vehicle may experience as it travels from one parking spot to the next. For example, an autonomous vehicle traveling from parking spot A1 to parking spot A2 may first enter the starting stage, then the constant speed cruising stage, and finally the parking stage. Similarly, an autonomous vehicle traveling from intersection B1 to intersection B2 may first enter the starting stage, then the constant speed cruising stage, and finally the parking stage. The core of this application's design lies in planning when and at what speed the autonomous vehicle enters which stage.

[0082] The above three stages are a stage division method that can be applied to most scenarios. The local planning control of the three stages takes into account both the accuracy requirements of the vehicle's driving trajectory and the comfort requirements of passengers.

[0083] Step S240: Based on the global path planning result, the autonomous vehicle is localized using a local trajectory planning strategy corresponding to the current driving stage, so as to control the autonomous vehicle's driving according to the local trajectory planning result. The local trajectory planning result includes the longitudinal speed planning result corresponding to the current driving stage.

[0084] Based on the aforementioned steps, different driving stages require different driving speeds and accelerations, which in turn leads to different local trajectory planning strategies for different driving stages. Therefore, in this embodiment, the corresponding local trajectory planning strategy can be adopted to perform local trajectory planning based on the current driving stage of the autonomous vehicle. The core of this planning is the planning of longitudinal speed, that is, the speed at which the autonomous vehicle travels along the center line of the lane. The planning result of longitudinal speed needs to be able to provide a reference for the driving speed of the autonomous vehicle in different stages, so as to ensure that the autonomous vehicle arrives at the parking point smoothly and accurately, and to ensure the safe boarding and alighting of passengers.

[0085] Planning for longitudinal reference speed requires consideration of many factors, such as Figure 4 As shown, the longitudinal speed planning in this application embodiment can be divided into three stages based on the scenario: uniform acceleration motion in the start-up stage, uniform cruising motion after acceleration, and precise parking motion.

[0086] The trajectory planning method for autonomous vehicles in this application realizes local trajectory planning for autonomous vehicles at various driving stages, focusing on solving the planning of the longitudinal reference speed of autonomous vehicles, and meeting the comfort and accuracy requirements of each driving stage, especially the parking stage.

[0087] In one embodiment of this application, when performing global path planning, it is necessary to first determine the location of the starting point and the final destination of the autonomous vehicle. Taking a small or medium-sized passenger minibus as an example, on the main urban road, the starting point and the final destination of the minibus's route can be determined. Therefore, the latitude and longitude coordinates of the starting point and the final destination can be easily collected through the GPS positioning module. Then, the collected latitude and longitude coordinates are converted into UTM (Universal Transverse Mercator) coordinates, i.e. (x,y,z) coordinates, through an algorithm. The 5G communication module transmits the converted UTM coordinates (x,y,z) of the starting point and the final destination to the APP application. The APP application software then sends the location of the starting point and the final destination to the downstream planning module, which is responsible for calculating the globally optimal path between the two points.

[0088] In one embodiment of this application, determining the current driving stage of the autonomous vehicle based on its current driving state information includes: determining the trigger speed of the parking stage based on the current driving state information of the autonomous vehicle; and determining whether the autonomous vehicle needs to enter the parking stage based on its current driving speed and the trigger speed of the parking stage.

[0089] Existing solutions for local trajectory planning during the parking phase primarily rely on the distance between the autonomous vehicle and the parking spot to determine whether the vehicle has entered the parking phase. However, this approach has a problem: when the current distance between the autonomous vehicle and the parking spot meets the distance requirement for entering the parking phase, but the current driving speed is high, the autonomous vehicle often needs to decelerate significantly to ensure that it stops precisely at the parking spot. This results in a substantial reduction in passenger comfort and also affects the stability of the vehicle.

[0090] Furthermore, since the design concepts and algorithms for the longitudinal reference speeds in the parking phase and the cruise phase are different, and the two phases are clearly divided, how to automatically switch from the cruise phase to the precise parking phase is a key consideration in the embodiments of this application.

[0091] Based on this, this application defines a "trigger speed" for entering the parking phase. This trigger speed is used to automatically determine the appropriate time for the autonomous vehicle to enter the parking phase. By comparing the current speed of the autonomous vehicle with the trigger speed for the parking phase, it is determined whether the autonomous vehicle needs to transition from the cruising phase to the parking phase. The trigger speed setting must ensure that the vehicle can accurately stop at the parking point while also maintaining vehicle stability and passenger comfort.

[0092] In one embodiment of this application, determining the trigger speed of the parking phase based on the current driving status information of the autonomous vehicle includes: determining the trigger acceleration of the parking phase based on the current driving speed of the autonomous vehicle; and determining the trigger speed of the parking phase based on the current distance between the autonomous vehicle and the parking point and the trigger acceleration of the parking phase.

[0093] The existing solution determines whether an autonomous vehicle needs to enter the parking phase based on the current distance between the autonomous vehicle and the parking point, which is a fixed condition judgment. That is, as long as the current distance between the autonomous vehicle and the parking point meets the distance requirement of the parking phase, the vehicle needs to directly enter the parking phase regardless of its current speed. This is not good for passenger comfort or the vehicle's own driving stability.

[0094] The "trigger speed" designed in this application embodiment needs to consider not only the current distance between the vehicle and the parking point, but also the current driving speed v of the vehicle. That is, the trigger acceleration a during the parking phase can be determined first based on the current driving speed of the autonomous vehicle. trigger The magnitude of the trigger acceleration during the parking phase varies depending on the current driving speed. Then, based on the displacement calculation formula, the current distance s between the autonomous vehicle and the parking point is used. targetTriggering acceleration a during the parking phase trigger Calculate the trigger speed v during the parking phase. trigger .

[0095] For ease of understanding, the calculation can be performed in the following form:

[0096] a trigger = a*v+b, (2)

[0097]

[0098] In the above formula (1), a and b are empirical values ​​obtained from multiple experiments.

[0099] In one embodiment of this application, determining whether the autonomous vehicle needs to enter the parking phase based on the current driving speed of the autonomous vehicle and the trigger speed of the parking phase includes: if the current driving speed of the autonomous vehicle is not less than the trigger speed of the parking phase, then it is determined that the autonomous vehicle needs to enter the parking phase; otherwise, it is determined that the autonomous vehicle does not need to enter the parking phase.

[0100] Based on the aforementioned embodiments, the trigger speed v of the parking phase is determined. trigger Afterwards, if the trigger speed v during the parking phase... trigger >v indicates that the autonomous vehicle is still far from the parking spot and its current speed has not yet reached the trigger speed, so it can continue driving at the longitudinal speed planned during the cruise phase. As the vehicle continues to move forward, the distance between the front of the vehicle and the parking spot decreases, and v... trigger As the speed decreases, there will be a point in time when the trigger speed v for the stopping phase will occur. trigger If the distance to the parking spot is less than or equal to v, it indicates that the autonomous vehicle is close enough to the parking spot and its current speed has reached the trigger speed. It needs to enter the parking phase immediately and proceed with the planned longitudinal speed according to the parking phase parameters. For example... Figure 5 The diagram shown illustrates a process for entering the parking stage according to an embodiment of this application.

[0101] As can be seen from the foregoing embodiments, due to the constraint of trigger speed, when the current driving speed v of the autonomous vehicle is large, the corresponding trigger speed v trigger The speed will also be relatively high, so when the autonomous vehicle is traveling at a relatively high speed, it will reach the trigger speed. This means that the autonomous vehicle needs to enter the parking stage in advance to decelerate. This can avoid the situation where the autonomous vehicle has to brake suddenly in order to reduce speed as soon as possible when it is already close to the parking point, thus ensuring the comfort of passengers and the smoothness of parking.

[0102] In one embodiment of this application, the current driving stage is the parking stage. The step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using the local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes: obtaining planning parameters for the parking stage, the planning parameters for the parking stage including a braking rate; and performing local trajectory planning for the parking stage according to the global path planning result and the planning parameters for the parking stage to obtain the local trajectory planning result for the parking stage.

[0103] When it is determined that an autonomous vehicle needs to enter the parking phase, the longitudinal velocity can be planned using the local trajectory planning strategy corresponding to the parking phase. When an autonomous vehicle enters the precise parking phase, in addition to focusing on whether it can park precisely at the parking point, it is also necessary to consider vehicle stability and passenger comfort requirements.

[0104] Therefore, in designing the precise stopping speed, this application adopts a single braking rate for precise stopping to maintain passenger comfort. The single braking rate refers to maintaining a constant braking acceleration during the precise stopping process. Let the braking acceleration be a2, where a2 is an empirical value. To ensure stopping accuracy, the speed decreases from v0 to 0, and the distance from the front of the vehicle to the stopping point is s3-s2. Then, according to Newtonian physics, the reference speed v during the single braking phase is... ref for:

[0105]

[0106] In one embodiment of this application, the current driving stage is the starting stage. The step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using a local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes: obtaining planning parameters for the starting stage, the planning parameters for the starting stage including a first acceleration and a second acceleration, wherein the first acceleration is the maximum acceleration of the autonomous vehicle, and the second acceleration is the acceleration generated by the change in impact rate during the operation of the autonomous vehicle; and performing local trajectory planning for the starting stage according to the global path planning result and the planning parameters for the starting stage to obtain the local trajectory planning result for the starting stage.

[0107] This application embodiment plans the longitudinal speed during the initial acceleration phase. The initial acceleration phase can be considered as a phase from a standstill to maximum speed (0-v0). Considering the requirements of the vehicle's maximum acceleration performance and passenger comfort, the vehicle's requirement during the initial acceleration phase is smoothness and comfort. Therefore, the speed during the initial acceleration phase can be mainly uniform acceleration. Let the magnitude of the uniform acceleration be a1, then:

[0108] a1 = min(a2, a3), (5)

[0109] Where a2 is the maximum acceleration of the vehicle, and a3 is the vehicle acceleration considering passenger comfort, with the following values:

[0110] a3=a jerk (6)

[0111] Among them, a jerk The acceleration is mainly caused by the change in the impact rate when the vehicle is running. The greater the impact rate when the vehicle is moving, the worse the passenger's riding experience.

[0112] Therefore, the acceleration during the initial stage designed in this embodiment is mainly limited by the maximum acceleration of the aforementioned autonomous vehicle and the acceleration caused by changes in the impact rate during vehicle operation, thereby ensuring passenger comfort during the initial stage. Of course, those skilled in the art can flexibly set other influencing factors according to actual needs, which will not be listed here.

[0113] In one embodiment of this application, the current driving stage is the cruise stage. The step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using a local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes: obtaining planning parameters for the cruise stage, the planning parameters for the cruise stage including the maximum speed limit of the autonomous vehicle, the maximum speed limit of the road where the autonomous vehicle is located, the safe speed of the autonomous vehicle relative to the obstacle ahead, and a delay factor; and performing local trajectory planning for the cruise stage according to the global path planning result and the planning parameters for the cruise stage to obtain the local trajectory planning result for the cruise stage.

[0114] This application embodiment plans the longitudinal speed during the cruise phase. During the cruise phase, the autonomous vehicle can mainly travel at a constant speed. The driving speed is mainly affected by the vehicle speed limit v1 caused by obstacles in front of the vehicle, the maximum speed limit v2 of the autonomous driving platform, and the maximum speed limit v3 of the road where the vehicle is located. The vehicle's driving speed during the cruise phase cannot exceed the above three speed limits, so the minimum value of the three speed limits can be taken:

[0115] v0 = min(v1, v2, v3), (7)

[0116] Among them, v2 and v3 are obtained from external conditions, while v1 is greatly affected by the movement state of the obstacle in front of the vehicle. When the obstacle in front is close to the vehicle, it is safer to keep the vehicle speed low. When the obstacle is far from the vehicle, the vehicle speed is less affected by the obstacle in front. Therefore, a safe speed can be determined based on the safe distance between the vehicle and the obstacle in front.

[0117] Although autonomous vehicles reduce braking reaction time due to autonomous driving, unavoidable mechanical delays exist in the transmission of commands to the vehicle due to mechanical backlash, leading to safety hazards. Therefore, in designing the maximum speed during the cruise phase, this embodiment of the application can incorporate a constant factor v4 to account for the impact of the delay. Thus, the final cruise speed can be expressed as:

[0118] v0 = min(v1,v2,v3) - v4, (8)

[0119]

[0120] In one embodiment of this application, the safe speed of the autonomous vehicle relative to the obstacle ahead is determined by: obtaining the current speed of the autonomous vehicle; determining the safe distance between the autonomous vehicle and the obstacle ahead based on the current speed of the autonomous vehicle and a safety margin constant; and determining the safe speed of the autonomous vehicle relative to the obstacle ahead based on the safe distance between the autonomous vehicle and the obstacle ahead and the maximum deceleration of the autonomous vehicle.

[0121] In determining the safe speed of an autonomous vehicle relative to an obstacle ahead, this application embodiment employs a headway strategy to maintain a safe following distance in order to ensure the autonomous vehicle does not collide with the obstacle. This can be expressed as:

[0122] s safety =t*v+s0, (10)

[0123]

[0124] Among them, s safety Let be the safe distance between the autonomous vehicle and the obstacle in front, a0 be the maximum deceleration of the autonomous vehicle, v be the current speed of the autonomous vehicle, and s0 be the safety margin constant.

[0125] In one embodiment of this application, the longitudinal speed control for each driving stage can be based on a dual-closed-loop PID (Proportional-Integral-Differential) algorithm to follow the reference speed, such as... Figure 6 As shown, a schematic diagram of the control flow of a dual closed-loop PID algorithm in an embodiment of this application is provided.

[0126] The position loop PID inputs are the reference position and the vehicle's actual longitudinal position. The speed deviation compensation, vbias, is calculated based on the position deviation. The speed loop inputs are the reference speed, the vehicle's actual speed, and the speed deviation compensation vbias calculated by the position loop. The speed loop calculates the acceleration command compensation value Abias. The final acceleration command equals the reference acceleration plus Abias. Then, based on the current vehicle speed and calibration table, the corresponding throttle or brake pedal opening value is retrieved, driving the vehicle to travel at the reference speed. Specific PID control algorithms can be found in classical control theory; the embodiments in this application will not be elaborated upon here.

[0127] In addition to longitudinal speed following control, the embodiments of this application can also perform lateral control. For example, a vehicle dynamics model can be used to solve for the optimal lateral steering angle using a quadratic programming solver to keep the vehicle from deviating from the lane centerline.

[0128] In one embodiment of this application, in order to ensure the smooth execution of the planning task of the autonomous vehicle, a self-check task of the autonomous driving system can be performed before obtaining the global path planning result of the autonomous vehicle, so as to determine whether the various functions of the autonomous driving system are normal based on the self-check result.

[0129] like Figure 7 The diagram illustrates a self-test process of an autonomous driving system according to an embodiment of this application. Before starting operation, the autonomous driving system needs to check whether various hardware systems, software systems, communication systems, and operating systems are functioning properly. These systems are interdependent; without any part, the autonomous vehicle cannot independently complete unmanned autonomous driving operations.

[0130] The hardware system mainly includes a GPS positioning module, a camera and radar perception module, a 5G communication module, and a domain controller module. The hardware modules are responsible for data acquisition and algorithm processing, serving as the underlying driving modules for autonomous driving. Based on these underlying modules, the autonomous driving operating system runs in the domain controller. In this embodiment, the open-source operating system ROS (Robot Operation System) can be used as the operating system for the autonomous vehicle. During high-speed vehicle operation, the ROS system can couple multiple modules, offering flexible use and meeting the stability and real-time requirements of autonomous vehicles at low speeds (less than 50 km / h), making it a relatively good open-source operating system. After the vehicle is powered on and started, the subsequent planning work can only proceed after checking whether the hardware modules have initialized successfully, whether 5G communication is connected, and whether the software operating system is running normally.

[0131] This application also provides a trajectory planning device 800 for autonomous vehicles, such as... Figure 8The diagram shows a schematic representation of a trajectory planning device for an autonomous vehicle according to an embodiment of this application. The device 800 includes: a first acquisition unit 810, a second acquisition unit 820, a determination unit 830, and a planning unit 840, wherein:

[0132] The first acquisition unit 810 is used to acquire the global path planning result of the autonomous vehicle, the global path planning result including the global lane centerline;

[0133] The second acquisition unit 820 is used to acquire the current driving status information of the autonomous vehicle, the current driving status information including the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle;

[0134] The determining unit 830 is used to determine the current driving stage of the autonomous vehicle based on the current driving state information of the autonomous vehicle, wherein the current driving stage includes a starting stage, a cruising stage, and a parking stage.

[0135] The planning unit 840 is used to perform local trajectory planning for the autonomous vehicle based on the global path planning result and using the local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle, so as to control the driving of the autonomous vehicle according to the local trajectory planning result. The local trajectory planning result includes the longitudinal speed planning result corresponding to the current driving stage.

[0136] In one embodiment of this application, the determining unit 830 is specifically used to: determine the trigger speed of the parking phase based on the current driving status information of the autonomous vehicle; and determine whether the autonomous vehicle needs to enter the parking phase based on the current driving speed of the autonomous vehicle and the trigger speed of the parking phase.

[0137] In one embodiment of this application, the determining unit 830 is specifically used to: determine the trigger acceleration of the parking phase based on the current driving speed of the autonomous vehicle; and determine the trigger speed of the parking phase based on the current distance between the autonomous vehicle and the parking point and the trigger acceleration of the parking phase.

[0138] In one embodiment of this application, the determining unit 830 is specifically configured to: if the current driving speed of the autonomous vehicle is not less than the trigger speed of the parking phase, then determine that the autonomous vehicle needs to enter the parking phase; otherwise, determine that the autonomous vehicle does not need to enter the parking phase.

[0139] In one embodiment of this application, the current driving stage is the parking stage, and the planning unit 840 is specifically used to: obtain planning parameters for the parking stage, the planning parameters for the parking stage including a single braking rate; perform local trajectory planning for the parking stage based on the global path planning result and the planning parameters for the parking stage, and obtain the local trajectory planning result for the parking stage.

[0140] In one embodiment of this application, the current driving stage is the starting stage, and the planning unit 840 is specifically used to: obtain planning parameters for the starting stage, the planning parameters for the starting stage including a first acceleration and a second acceleration, wherein the first acceleration is the maximum acceleration of the autonomous vehicle, and the second acceleration is the acceleration generated by the change in the impact rate during the operation of the autonomous vehicle; perform local trajectory planning for the starting stage based on the global path planning result and the planning parameters for the starting stage, and obtain the local trajectory planning result for the starting stage.

[0141] In one embodiment of this application, the current driving stage is the cruise stage, and the planning unit 840 is specifically used to: obtain planning parameters for the cruise stage, the planning parameters for the cruise stage including the maximum speed limit of the autonomous vehicle, the maximum speed limit corresponding to the road where the autonomous vehicle is located, the safe speed of the autonomous vehicle relative to the obstacle in front, and a delay factor; perform local trajectory planning for the cruise stage based on the global path planning result and the planning parameters for the cruise stage, and obtain the local trajectory planning result for the cruise stage.

[0142] In one embodiment of this application, the safe speed of the autonomous vehicle relative to the obstacle ahead is determined by: obtaining the current speed of the autonomous vehicle; determining the safe distance between the autonomous vehicle and the obstacle ahead based on the current speed of the autonomous vehicle and a safety margin constant; and determining the safe speed of the autonomous vehicle relative to the obstacle ahead based on the safe distance between the autonomous vehicle and the obstacle ahead and the maximum deceleration of the autonomous vehicle.

[0143] It is understood that the trajectory planning device for autonomous vehicles described above can implement each step of the trajectory planning method for autonomous vehicles provided in the foregoing embodiments. The relevant explanations of the trajectory planning method for autonomous vehicles are applicable to the trajectory planning device for autonomous vehicles, and will not be repeated here.

[0144] Figure 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 9At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0145] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0146] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0147] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming the trajectory planning device for the autonomous vehicle at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0148] Obtain the global path planning results for autonomous vehicles, including global lane centerlines;

[0149] Obtain the current driving status information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle;

[0150] The current driving stage of the autonomous vehicle is determined based on the current driving status information of the autonomous vehicle. The current driving stage includes the starting stage, the cruising stage, and the parking stage.

[0151] Based on the global path planning results, the autonomous vehicle is used to perform local trajectory planning using a local trajectory planning strategy corresponding to the current driving stage, so as to control the autonomous vehicle's driving according to the local trajectory planning results. The local trajectory planning results include the longitudinal speed planning results corresponding to the current driving stage.

[0152] The above is as stated in this application. Figure 2 The method for trajectory planning of an autonomous vehicle disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0153] The electronic device can also perform Figure 2 A method for executing the trajectory planning device of an autonomous vehicle, and to realize the trajectory planning device of an autonomous vehicle in... Figure 2 The functions of the embodiments shown are not described in detail here.

[0154] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 2The method executed by the trajectory planning device of the autonomous vehicle in the illustrated embodiment is specifically used to perform:

[0155] Obtain the global path planning results for autonomous vehicles, including global lane centerlines;

[0156] Obtain the current driving status information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle;

[0157] The current driving stage of the autonomous vehicle is determined based on the current driving status information of the autonomous vehicle. The current driving stage includes the starting stage, the cruising stage, and the parking stage.

[0158] Based on the global path planning results, the autonomous vehicle is used to perform local trajectory planning using a local trajectory planning strategy corresponding to the current driving stage, so as to control the autonomous vehicle's driving according to the local trajectory planning results. The local trajectory planning results include the longitudinal speed planning results corresponding to the current driving stage.

[0159] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0160] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0161] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0162] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0163] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0164] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0165] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0166] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0167] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0168] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A trajectory planning method for an autonomous vehicle, wherein, The method includes: Obtain the global path planning results for autonomous vehicles, including global lane centerlines; Obtain the current driving status information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle; The current driving stage of the autonomous vehicle is determined based on the current driving status information of the autonomous vehicle. The current driving stage includes the starting stage, the cruising stage, and the parking stage. Based on the global path planning results, the autonomous vehicle is used to perform local trajectory planning using the local trajectory planning strategy corresponding to the current driving stage, so as to control the driving of the autonomous vehicle according to the local trajectory planning results. The local trajectory planning results include the longitudinal speed planning results corresponding to the current driving stage. Determining the current driving stage of the autonomous vehicle based on its current driving status information includes: The trigger speed for the parking phase is determined based on the current driving status information of the autonomous vehicle. Based on the current driving speed of the autonomous vehicle and the trigger speed of the parking phase, determine whether the autonomous vehicle needs to enter the parking phase; Determining the trigger speed for the parking phase based on the current driving status information of the autonomous vehicle includes: The trigger acceleration for the parking phase is determined based on the current driving speed of the autonomous vehicle. Based on the current distance between the autonomous vehicle and the parking point and the trigger acceleration of the parking phase, the trigger speed of the parking phase is determined using the displacement calculation formula. The trigger speed is used to automatically determine the appropriate time for the autonomous vehicle to enter the parking phase.

2. The method as described in claim 1, wherein, Determining whether the autonomous vehicle needs to enter the parking phase based on the current driving speed of the autonomous vehicle and the trigger speed of the parking phase includes: If the current driving speed of the autonomous vehicle is not less than the trigger speed of the parking phase, then it is determined that the autonomous vehicle needs to enter the parking phase. Otherwise, it is determined that the autonomous vehicle does not need to enter the parking phase.

3. The method as described in claim 1, wherein, The current driving stage is the parking stage. The step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using a local trajectory planning strategy corresponding to the current driving stage includes: Obtain the planning parameters for the parking phase, including the first braking rate; Based on the global path planning results and the planning parameters of the parking stage, local trajectory planning for the parking stage is performed to obtain the local trajectory planning results for the parking stage.

4. The method as described in claim 1, wherein, The current driving stage is the starting stage, and the step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using the local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes: The planning parameters for the initial stage are obtained, including a first acceleration and a second acceleration, wherein the first acceleration is the maximum acceleration of the autonomous vehicle, and the second acceleration is the acceleration caused by the change in the impact rate during the operation of the autonomous vehicle. Based on the global path planning results and the planning parameters of the initial stage, local trajectory planning for the initial stage is performed to obtain the local trajectory planning results for the initial stage.

5. The method as described in claim 1, wherein, The current driving stage is the cruising stage, and the step of performing local trajectory planning for the autonomous vehicle based on the global path planning result and using the local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle includes: The planning parameters for the cruise phase are obtained, including the maximum speed limit of the autonomous vehicle, the maximum speed limit of the road where the autonomous vehicle is located, the safe speed of the autonomous vehicle relative to the obstacle in front, and the delay factor. Based on the global path planning results and the planning parameters of the cruise phase, local trajectory planning for the cruise phase is performed to obtain the local trajectory planning results for the cruise phase.

6. The method of claim 5, wherein, The safe speed of the autonomous vehicle relative to the obstacle ahead is determined in the following manner: Obtain the current speed of the autonomous vehicle; The safe distance between the autonomous vehicle and the obstacle ahead is determined based on the current speed of the autonomous vehicle and the safety margin constant. The safe speed of the autonomous vehicle relative to the obstacle ahead is determined based on the safe distance between the autonomous vehicle and the obstacle ahead and the maximum deceleration of the autonomous vehicle.

7. A trajectory planning device for an autonomous vehicle, wherein, The device includes: The first acquisition unit is used to acquire the global path planning result of the autonomous vehicle, the global path planning result including the global lane centerline; The second acquisition unit is used to acquire the current driving status information of the autonomous vehicle, which includes the current distance between the autonomous vehicle and the parking point and the current driving speed of the autonomous vehicle. The determining unit is configured to determine the current driving stage of the autonomous vehicle based on the current driving state information of the autonomous vehicle, wherein the current driving stage includes a starting stage, a cruising stage, and a parking stage. The planning unit is used to perform local trajectory planning for the autonomous vehicle based on the global path planning result and using the local trajectory planning strategy corresponding to the current driving stage of the autonomous vehicle, so as to control the driving of the autonomous vehicle according to the local trajectory planning result. The local trajectory planning result includes the longitudinal speed planning result corresponding to the current driving stage. The determining unit is specifically used for: The trigger speed for the parking phase is determined based on the current driving status information of the autonomous vehicle. Based on the current driving speed of the autonomous vehicle and the trigger speed of the parking phase, determine whether the autonomous vehicle needs to enter the parking phase; The determining unit is specifically used for: The trigger acceleration for the parking phase is determined based on the current driving speed of the autonomous vehicle. Based on the current distance between the autonomous vehicle and the parking point and the trigger acceleration of the parking phase, the trigger speed of the parking phase is determined using the displacement calculation formula. The trigger speed is used to automatically determine the appropriate time for the autonomous vehicle to enter the parking phase.

8. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 6.

Images