Trajectory planning method and device, equipment and storage medium

Abstract

The application discloses a trajectory planning method and device, equipment and storage medium, and belongs to the technical field of vehicle navigation auxiliary driving or automatic driving. The application obtains a sampling trajectory cluster, determines actual motion trajectories of vehicles corresponding to each sampling trajectory in the sampling trajectory cluster, and screens a target trajectory from the sampling trajectory cluster according to the actual motion trajectories, so that the optimal trajectory is screened from the sampling trajectory cluster again based on the actual motion trajectories of the vehicles after the actual motion trajectories of the vehicles corresponding to each sampling trajectory are determined. In the above manner, it can be ensured that the optimal cost trajectory selected is the optimal selection when the vehicle is actually executed, and the safety and comfort of the navigation auxiliary driving system are improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle navigation-assisted driving or autonomous driving technology, and in particular to a trajectory planning method, device, equipment and storage medium. Background Technology

[0002] The current trajectory planning method involves sampling the cluster of available trajectories, combining driving path information and surrounding obstacle information to calculate the cost of each available trajectory, and selecting the trajectory with the optimal cost as the final planned trajectory for the control system to follow.

[0003] However, due to the inherent error in the control system's ability to follow the planned trajectory, and factors such as driving comfort filtering and execution system response delay, the actual trajectory of the vehicle is not entirely consistent with the planned trajectory. The trajectory chosen with the lowest cost may not be optimal in actual vehicle execution. Therefore, the current trajectory planning method cannot guarantee that the vehicle will execute the optimal trajectory in actual situations, thus reducing the safety and comfort of the navigation-assisted driving system.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a trajectory planning method, apparatus, device, and storage medium, which aims to solve the technical problem that current trajectory planning methods cannot guarantee that vehicles can follow the optimal trajectory in actual situations.

[0006] To achieve the above objectives, the present invention provides a trajectory planning method, which includes the following steps:

[0007] Obtain the sampling trajectory cluster;

[0008] Determine the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster;

[0009] The target trajectory is selected from the sampled trajectory cluster based on the actual motion trajectory.

[0010] Optionally, determining the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster includes:

[0011] Obtain the acceleration and direction / rotation requests of each sampled trajectory in the current sampling trajectory cluster;

[0012] Calculate the vehicle's acceleration and steering angle based on the acceleration request and the steering angle request;

[0013] The actual trajectory of the vehicle is determined based on its acceleration and steering angle.

[0014] Optionally, the acceleration and the steering angle are the acceleration and steering angle of the vehicle at the current moment;

[0015] Determining the actual trajectory of the vehicle based on its acceleration and steering angle includes:

[0016] The vehicle's pose state at the next moment is determined based on the vehicle's acceleration and directional angle at the current moment;

[0017] After obtaining the vehicle's pose state at the next moment, continue to obtain the acceleration request and direction angle request of each sampled trajectory in the sampled trajectory cluster at the next moment;

[0018] Calculate the vehicle's acceleration and steering angle at the next moment based on the acceleration request and the steering angle request;

[0019] The vehicle's pose state at the next moment is determined based on the acceleration and directional angle at the next moment, and the process returns to the step of continuing to obtain the acceleration request and directional angle request of each sampled trajectory in the sampled trajectory cluster at the next moment, so as to obtain the vehicle's pose state at multiple different moments.

[0020] The actual trajectory of the vehicle is determined based on its position and posture at multiple different times.

[0021] Optionally, before determining the actual trajectory of the vehicle based on its pose at multiple different times, the method further includes:

[0022] Calculate the time interval between the current time and the initial time.

[0023] Determine whether the time length has reached the preset time series length;

[0024] If not, return to the step of continuing to obtain the acceleration request and direction angle request of each sampled trajectory in the sampled trajectory cluster at the next moment;

[0025] If so, then the step of determining the actual motion trajectory of the vehicle based on the vehicle's pose state at multiple different times is performed.

[0026] Optionally, the step of filtering the target trajectory from the sampled trajectory cluster based on the actual motion trajectory includes:

[0027] Calculate the trajectory cost corresponding to each actual motion trajectory;

[0028] The target trajectory is selected from the sampled trajectory cluster based on the trajectory value.

[0029] Optionally, the step of filtering the target trajectory from the sampled trajectory cluster based on the trajectory cost value includes:

[0030] Based on the trajectory cost value, the actual motion trajectory with the smallest trajectory cost value is selected from all actual motion trajectories;

[0031] The sampled trajectory corresponding to the actual motion trajectory with the minimum trajectory value in the sampled trajectory cluster is determined, and the sampled trajectory is taken as the target trajectory.

[0032] Furthermore, to achieve the above objectives, the present invention also proposes a trajectory planning device, the trajectory planning device comprising:

[0033] The acquisition module is used to acquire sampling trajectory clusters;

[0034] The calculation module is used to determine the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster;

[0035] The filtering module is used to filter out the target trajectory from the sampled trajectory cluster based on the actual motion trajectory.

[0036] Furthermore, to achieve the above objectives, the present invention also proposes a trajectory planning device, the trajectory planning device comprising: a memory, a processor, and a trajectory planning program stored in the memory and running on the processor, the trajectory planning program being configured to implement the trajectory planning method as described above.

[0037] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a trajectory planning program, which, when executed by a processor, implements the trajectory planning method as described above.

[0038] This invention acquires a cluster of sampled trajectories; determines the actual motion trajectory of the vehicle corresponding to each sampled trajectory in the cluster; and filters out a target trajectory from the cluster based on the actual motion trajectory. By determining the actual motion trajectory of the vehicle corresponding to each sampled trajectory and then filtering out the optimal trajectory from the cluster based on the actual motion trajectory of the vehicle, this invention ensures that the selected optimal cost trajectory is the optimal choice when the vehicle is actually executing, thereby improving the safety and comfort of the navigation-assisted driving system. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the trajectory planning device in the hardware operating environment involved in the embodiments of the present invention;

[0040] Figure 2 This is a flowchart illustrating the first embodiment of the trajectory planning method of the present invention;

[0041] Figure 3 This is a schematic diagram of the overall scheme flow in one embodiment of the trajectory planning method of the present invention;

[0042] Figure 4 This is a flowchart illustrating the second embodiment of the trajectory planning method of the present invention;

[0043] Figure 5 This is a flowchart illustrating the third embodiment of the trajectory planning method of the present invention;

[0044] Figure 6 This is a structural block diagram of the first embodiment of the trajectory planning device of the present invention.

[0045] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0046] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0047] Reference Figure 1 , Figure 1 This is a schematic diagram of the trajectory planning device structure of the hardware operating environment involved in the embodiment of the present invention.

[0048] like Figure 1 As shown, the trajectory planning device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0049] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the trajectory planning device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0050] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a trajectory planning program.

[0051] exist Figure 1 In the trajectory planning device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the trajectory planning device of the present invention can be set in the trajectory planning device, and the trajectory planning device calls the trajectory planning program stored in the memory 1005 through the processor 1001 and executes the trajectory planning method provided in the embodiment of the present invention.

[0052] This invention provides a trajectory planning method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating a first embodiment of a trajectory planning method according to the present invention.

[0053] In this embodiment, the trajectory planning method includes the following steps:

[0054] Step S10: Obtain the sampling trajectory cluster.

[0055] In this embodiment, the execution entity is the trajectory planning device, which has functions such as data acquisition, data communication, and program execution. Of course, other devices with similar functions can also be used; this embodiment does not limit this, and a trajectory planning device is used as an example for illustration.

[0056] It should be noted that the current trajectory planning method involves sampling a cluster of possible trajectories, combining driving path information and surrounding obstacle information to calculate the cost of each possible trajectory, and selecting the trajectory with the lowest cost as the final planned trajectory for the control system to follow. However, due to the inherent error in the control system's following of the planned trajectory, and factors such as driving comfort filtering and system response delays, the actual trajectory of the vehicle may not perfectly match the planned trajectory. Therefore, the selected trajectory with the lowest cost may not be the optimal one in actual vehicle execution. Consequently, the current trajectory planning method cannot guarantee that the vehicle will follow the optimal trajectory in real-world conditions, thus reducing the safety and comfort of the navigation-assisted driving system.

[0057] In this embodiment, to address the aforementioned issues, a sampled trajectory cluster is acquired; the actual vehicle motion trajectory corresponding to each sampled trajectory in the cluster is determined; and a target trajectory is selected from the sampled trajectory cluster based on the actual motion trajectory. By determining the actual vehicle motion trajectory corresponding to each sampled trajectory, and then selecting the optimal trajectory from the sampled trajectory cluster based on the actual vehicle motion trajectory, this method ensures that the selected optimal cost trajectory is the optimal choice during actual vehicle execution, improving the safety and comfort of the navigation-assisted driving system. Specifically, for example, the control system is invoked to calculate the acceleration and steering angle requests corresponding to each trajectory for each trajectory in the sampled trajectory cluster, and the vehicle execution system is used. The response transfer function calculates the vehicle's actual acceleration and steering angle. Using the calculated actual acceleration and steering angle, the vehicle's pose state at the next moment is calculated. Then, the control system is called to calculate the acceleration and steering angle requests corresponding to each trajectory at the next moment. Through these steps, the sequence of the vehicle's actual acceleration, steering angle, and pose state over a period of time corresponding to each trajectory in the sampled trajectory cluster is obtained, thus obtaining the actual vehicle motion trajectory corresponding to each trajectory in the sampled trajectory cluster. Finally, the actual vehicle motion trajectory corresponding to each trajectory in the sampled trajectory cluster is used to calculate the cost of each trajectory. The original trajectory corresponding to the trajectory with the optimal cost is selected as the final planned trajectory and handed over to the control system for following.

[0058] In this embodiment, first according to Figure 3 Taking an example, the overall process of this technical solution will be illustrated. (Refer to...) Figure 3First, it is necessary to obtain samples of the selectable trajectory clusters. Then, the control system is invoked to calculate the acceleration and steering angle requests for each trajectory. Specifically, this can be done by calling the control algorithm module within the control system. After obtaining the acceleration and steering angle requests, the actual acceleration and steering angle of the vehicle are calculated using the vehicle execution system response transfer function. The vehicle execution system response transfer function is established through pre-calibration. Specifically, after path planning, the vehicle is controlled to drive according to the planned path, and the actual acceleration and steering angle during the driving process are recorded. Then, the parameters of the response transfer function are gradually adjusted based on the recorded data. Through numerous calibration experiments, the final vehicle execution system response transfer function can be established. Furthermore, after calculating the actual acceleration and steering angle of the vehicle, the vehicle's pose state can be further determined based on these actual acceleration and steering angles. It should be noted that the above calculations yield the vehicle's actual acceleration and steering angle at the current moment. The vehicle's pose at the next moment is determined based on these current acceleration and steering angles. Repeating this process yields the vehicle's pose at different moments, and the actual trajectory can be determined based on these poses. For example, after calculating the actual acceleration and steering angle at time T, the vehicle's pose at time T+1 can be determined. Then, repeating the above steps, calculate the acceleration and steering angle requests at time T+1, and then calculate the actual acceleration and steering angle at time T+1 again. The vehicle's pose at time T+2 can be obtained based on these values. Finally, the actual trajectory can be determined based on the pose at each moment (T, T+1, ..., T+n).

[0059] In this specific implementation, it is necessary to first obtain a sampling trajectory cluster, which is a set of multiple optional sampling trajectories. This set of optional sampling trajectories can be input by the user, or it can be obtained through other means. This embodiment does not impose any restrictions on this.

[0060] Step S20: Determine the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster.

[0061] In practice, each selectable sampling trajectory in the sampling trajectory cluster can be used for vehicle trajectory planning. However, since the actual movement trajectory of the vehicle is not completely consistent with the planned trajectory, this embodiment will further determine the corresponding actual movement trajectory of the vehicle for each selectable sampling trajectory.

[0062] Step S30: Select the target trajectory from the sampled trajectory cluster based on the actual motion trajectory.

[0063] In specific implementation, after determining the actual trajectory of the vehicle, this embodiment can select the actual trajectory with the best trajectory cost from the actual trajectory of the vehicle. Finally, based on the correspondence between the actual trajectory of the vehicle and each sampled trajectory in the sampled trajectory cluster, the sampled trajectory corresponding to the actual trajectory with the best trajectory cost is selected from the sampled trajectory cluster as the target trajectory.

[0064] This embodiment acquires a sample trajectory cluster; determines the actual motion trajectory of the vehicle corresponding to each sample trajectory in the sample trajectory cluster; and filters out the target trajectory from the sample trajectory cluster based on the actual motion trajectory. By determining the actual motion trajectory of the vehicle corresponding to each sample trajectory, and then filtering out the optimal trajectory from the sample trajectory cluster based on the actual motion trajectory of the vehicle, the above method can ensure that the selected optimal cost trajectory is the optimal choice when the vehicle is actually executing, thereby improving the safety and comfort of the navigation-assisted driving system.

[0065] refer to Figure 4 , Figure 4 This is a flowchart illustrating a second embodiment of a trajectory planning method according to the present invention.

[0066] Based on the first embodiment described above, a second embodiment of the trajectory planning method of the present invention is proposed.

[0067] In this embodiment, the trajectory planning method specifically includes step S20 as follows:

[0068] Step S201: Obtain the acceleration request and direction rotation angle request of each sampling trajectory in the sampling trajectory cluster at the current moment.

[0069] In specific implementation, after obtaining the sampled trajectory cluster, this embodiment further obtains the acceleration request and direction angle request of each sampled trajectory at the current moment. Specifically, the acceleration request and direction angle request of each trajectory can be calculated by calling the control algorithm module inside the control system.

[0070] Step S202: Calculate the vehicle's acceleration and steering angle based on the acceleration request and the steering angle request.

[0071] In practice, after receiving acceleration and steering angle requests, the vehicle's acceleration and steering angle can be calculated using these requests. Specifically, the actual acceleration and steering angle of the vehicle can be calculated using the vehicle execution system response transfer function. This function is established through pre-calibration. The process involves planning the vehicle's path, controlling the vehicle to travel along the planned path, and recording the actual acceleration and steering angle during the journey. Then, the parameters of the response transfer function are gradually adjusted based on the recorded data. Through numerous calibration experiments, the final vehicle execution system response transfer function can be established.

[0072] Step S203: Determine the actual trajectory of the vehicle based on its acceleration and steering angle.

[0073] In practical implementation, when determining the actual trajectory of a vehicle based on its acceleration and steering angle, it is necessary to first determine the vehicle's pose state based on its acceleration and steering angle. It should be noted that in this embodiment, the vehicle's pose state at the next moment is determined based on the current acceleration and steering angle. Then, the above steps are repeated to obtain the acceleration and steering angle requests for the next moment, calculate the vehicle's acceleration and steering angle for the next moment, and obtain the vehicle's pose state at the moment after that based on the acceleration and steering angle of the next moment. Finally, the vehicle's pose state at multiple different moments can be obtained.

[0074] Furthermore, this embodiment also calculates the time length between the current time and the initial time. For example, starting from time T0 (i.e., the initial time), the vehicle's acceleration and directional angle are calculated to obtain the vehicle's pose state at time T0+1. When determining the vehicle's pose state at time T0+2, the current time becomes time T0+1. Assuming the current time is T0+n, it is necessary to calculate the time length between time T0+n and time T0, which is n. Then, n is compared with the preset time series length. If the time series length is reached, it is considered that the vehicle's pose state at each time has been obtained. The actual trajectory of the vehicle can be determined based on the multiple vehicle pose states obtained from time T0 to time T0+n. Otherwise, if the time series length is not reached, the vehicle's pose state at time T0+n+1 is obtained based on time T0+n. The preset time series length can be set to 8s, that is, the vehicle's pose state at each time within 8s is obtained in this embodiment. The preset time series length can be adjusted according to actual needs, and this embodiment does not impose any restrictions on it.

[0075] This embodiment obtains the acceleration and direction angle requests of each sampled trajectory in the current sampling trajectory cluster; calculates the vehicle's acceleration and direction angle based on the acceleration and direction angle requests; determines the vehicle's pose state at the next moment based on the vehicle's acceleration and direction angle at the current moment; after obtaining the vehicle's pose state at the next moment, it continues to obtain the acceleration and direction angle requests of each sampled trajectory in the sampling trajectory cluster at the next moment; calculates the vehicle's acceleration and direction angle at the next moment based on the acceleration and direction angle requests; determines the vehicle's pose state at the moment after the next moment based on the acceleration and direction angle at the next moment, and returns to execute the step of continuing to obtain the acceleration and direction angle requests of each sampled trajectory in the sampling trajectory cluster at the next moment, so as to obtain the vehicle's pose state at multiple different moments; and determines the vehicle's actual motion trajectory based on the vehicle's pose state at multiple different moments. Through the above method, the vehicle's actual motion trajectory can be accurately obtained.

[0076] refer to Figure 5 , Figure 5 This is a flowchart illustrating a third embodiment of a trajectory planning method according to the present invention.

[0077] Based on the first embodiment described above, a third embodiment of the trajectory planning method of the present invention is proposed.

[0078] In this embodiment, the trajectory planning method specifically includes step S30 as follows:

[0079] Step S301: Calculate the trajectory cost corresponding to each actual motion trajectory.

[0080] In specific implementation, after determining the actual movement trajectory of the vehicle, this embodiment needs to further calculate the trajectory value corresponding to each actual movement trajectory. The method of calculating the trajectory value can be selected according to actual needs, and this embodiment does not impose any restrictions on it.

[0081] Step S302: Select the target trajectory from the sampled trajectory cluster according to the trajectory value.

[0082] In specific implementation, after determining the trajectory cost value corresponding to each actual motion trajectory, this embodiment first selects the actual motion trajectory with the smallest trajectory cost value from each actual motion trajectory based on the trajectory cost value. Then, based on the correspondence between the actual motion trajectory and the sampled trajectory, the sampled trajectory corresponding to the actual motion trajectory with the smallest trajectory cost value is selected from the sampled trajectory cluster, which is the target trajectory.

[0083] This embodiment calculates the trajectory cost value corresponding to each actual motion trajectory; selects the actual motion trajectory with the smallest trajectory cost value from each actual motion trajectory based on the trajectory cost value; determines the sampled trajectory in the sampled trajectory cluster that corresponds to the actual motion trajectory with the smallest trajectory cost value, and uses the sampled trajectory as the target trajectory. Through the above method, it can be ensured that the selected optimal cost trajectory is the optimal choice when the vehicle is actually executing, thereby improving the safety and comfort of the navigation-assisted driving system.

[0084] Furthermore, this embodiment of the invention also proposes a storage medium storing a trajectory planning program, which, when executed by a processor, implements the steps of the trajectory planning method described above.

[0085] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0086] Reference Figure 6 , Figure 6 This is a structural block diagram of the first embodiment of the trajectory planning device of the present invention.

[0087] like Figure 6 As shown, the trajectory planning device proposed in this embodiment of the invention includes:

[0088] Acquisition module 10 is used to acquire sampling trajectory clusters.

[0089] The calculation module 20 is used to determine the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster.

[0090] The filtering module 30 is used to filter out the target trajectory from the sampled trajectory cluster based on the actual motion trajectory.

[0091] This embodiment acquires a sample trajectory cluster; determines the actual motion trajectory of the vehicle corresponding to each sample trajectory in the sample trajectory cluster; and filters out the target trajectory from the sample trajectory cluster based on the actual motion trajectory. By determining the actual motion trajectory of the vehicle corresponding to each sample trajectory, and then filtering out the optimal trajectory from the sample trajectory cluster based on the actual motion trajectory of the vehicle, the above method can ensure that the selected optimal cost trajectory is the optimal choice when the vehicle is actually executing, thereby improving the safety and comfort of the navigation-assisted driving system.

[0092] In one embodiment, the calculation module 20 is further configured to obtain the acceleration request and direction angle request of each sampled trajectory in the sampled trajectory cluster at the current time; calculate the vehicle's acceleration and direction angle based on the acceleration request and the direction angle request; and determine the vehicle's actual motion trajectory based on the vehicle's acceleration and direction angle.

[0093] In one embodiment, the acceleration and the steering angle are the acceleration and steering angle of the vehicle at the current moment;

[0094] The calculation module 20 is further configured to: determine the vehicle's pose state at the next moment based on the vehicle's acceleration and directional angle at the current moment; after obtaining the vehicle's pose state at the next moment, continue to obtain the acceleration request and directional angle request of each sampled trajectory in the sampled trajectory cluster at the next moment; calculate the vehicle's acceleration and directional angle at the next moment based on the acceleration request and the directional angle request; determine the vehicle's pose state at the next moment after that based on the acceleration and directional angle at the next moment, and return to execute the step of continuing to obtain the acceleration request and directional angle request of each sampled trajectory in the sampled trajectory cluster at the next moment, so as to obtain the vehicle's pose state at multiple different moments; and determine the vehicle's actual motion trajectory based on the vehicle's pose state at multiple different moments.

[0095] In one embodiment, the calculation module 20 is further configured to calculate the time length between the current moment and the initial moment; determine whether the time length reaches the preset time sequence length; if not, return to the step of continuing to obtain the acceleration request and direction angle request of each sampled trajectory in the sampled trajectory cluster at the next moment; if yes, execute the step of determining the actual motion trajectory of the vehicle based on the vehicle's pose state at multiple different moments.

[0096] In one embodiment, the filtering module 30 is further configured to calculate the trajectory cost value corresponding to each actual motion trajectory; and to filter out the target trajectory from the sampled trajectory cluster based on the trajectory cost value.

[0097] In one embodiment, the filtering module 30 is further configured to filter out the actual motion trajectory with the smallest trajectory value from each actual motion trajectory based on the trajectory value; determine the sampling trajectory in the sampling trajectory cluster that corresponds to the actual motion trajectory with the smallest trajectory value, and use the sampling trajectory as the target trajectory.

[0098] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0099] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0100] In addition, for technical details not described in detail in this embodiment, please refer to the trajectory planning method provided in any embodiment of the present invention, which will not be repeated here.

[0101] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system 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 system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0102] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0103] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0104] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A trajectory planning method, characterized in that, The trajectory planning method includes: Obtain the sampling trajectory cluster; Determine the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster; The target trajectory is selected from the sampled trajectory cluster based on the actual motion trajectory, wherein the target trajectory is obtained by filtering based on the trajectory cost of the actual motion trajectory; Determining the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster includes: Obtain the acceleration and direction / rotation requests of each sampled trajectory in the current sampling trajectory cluster; Calculate the vehicle's acceleration and steering angle based on the acceleration request and the steering angle request; The actual trajectory of the vehicle is determined based on its acceleration and steering angle. The acceleration and the steering angle are the acceleration and steering angle of the vehicle at the current moment; Determining the actual trajectory of the vehicle based on its acceleration and steering angle includes: The vehicle's pose state at the next moment is determined based on the vehicle's acceleration and directional angle at the current moment; After obtaining the vehicle's pose state at the next moment, the system continues to obtain the acceleration request and direction angle request of each sampled trajectory in the sampled trajectory cluster at subsequent moments; The acceleration and direction angle of the vehicle at subsequent time steps are calculated based on the acceleration and direction angle requests of each sampled trajectory in the sampled trajectory cluster at subsequent time steps. The vehicle's pose state at the next moment is determined based on the acceleration and directional angle at the subsequent moment, and the process returns to the step of continuing to obtain the acceleration request and directional angle request of each sampled trajectory in the sampled trajectory cluster at the subsequent moment, so as to obtain the vehicle's pose state at multiple different moments. The actual trajectory of the vehicle is determined based on the vehicle's position and posture at multiple different times. Before determining the actual trajectory of the vehicle based on its pose at multiple different times, the method further includes: Calculate the time interval between the current time and the initial time. Determine whether the time length has reached the preset time series length; If not, return to the step of continuing to obtain the acceleration request and direction angle request of each sampled trajectory in the sampled trajectory cluster at subsequent time points; If so, then the step of determining the actual motion trajectory of the vehicle based on the vehicle's pose state at multiple different times is performed.

2. The trajectory planning method as described in claim 1, characterized in that, The step of filtering the target trajectory from the sampled trajectory cluster based on the actual motion trajectory includes: Calculate the trajectory cost corresponding to each actual motion trajectory; The target trajectory is selected from the sampled trajectory cluster based on the trajectory value.

3. The trajectory planning method as described in claim 2, characterized in that, The step of filtering the target trajectory from the sampled trajectory cluster based on the trajectory cost value includes: Based on the trajectory cost value, the actual motion trajectory with the smallest trajectory cost value is selected from all actual motion trajectories; The sampled trajectory corresponding to the actual motion trajectory with the minimum trajectory value in the sampled trajectory cluster is determined, and the sampled trajectory is taken as the target trajectory.

4. A trajectory planning device, characterized in that, The trajectory planning device includes: The acquisition module is used to acquire sampling trajectory clusters; The calculation module is used to determine the actual motion trajectory of the vehicle corresponding to each sampling trajectory in the sampling trajectory cluster; The filtering module is used to filter out the target trajectory from the sampled trajectory cluster based on the actual motion trajectory; The calculation module is further configured to: acquire the acceleration request and direction angle request of each sampled trajectory in the current sampling trajectory cluster; calculate the vehicle's acceleration and direction angle based on the acceleration request and direction angle request; determine the vehicle's actual motion trajectory based on the vehicle's acceleration and direction angle; the acceleration and direction angle are the vehicle's acceleration and direction angle at the current moment; determine the vehicle's pose state at the next moment based on the vehicle's acceleration and direction angle at the current moment; after acquiring the vehicle's pose state at the next moment, continue to acquire the acceleration request and direction angle request of each sampled trajectory in the sampling trajectory cluster at subsequent moments; calculate the vehicle's subsequent motion trajectory based on the acceleration request and direction angle request of each sampled trajectory in the sampling trajectory cluster at subsequent moments. The system retrieves the acceleration and directional rotation angles at subsequent time points; determines the vehicle's pose state at the next time point based on the acceleration and directional rotation angles at subsequent time points, and returns to the step of continuing to acquire the acceleration and directional rotation angle requests of each sampled trajectory in the sampled trajectory cluster at subsequent time points to obtain the vehicle's pose state at multiple different time points; determines the vehicle's actual motion trajectory based on the vehicle's pose state at multiple different time points; calculates the time length between the current time point and the initial time point; determines whether the time length reaches the preset time sequence length; if not, returns to the step of continuing to acquire the acceleration and directional rotation angle requests of each sampled trajectory in the sampled trajectory cluster at subsequent time points; if yes, executes the step of determining the vehicle's actual motion trajectory based on the vehicle's pose state at multiple different time points.

5. A trajectory planning device, characterized in that, The trajectory planning device includes: a memory, a processor, and a trajectory planning program stored in the memory and running on the processor, the trajectory planning program being configured to implement the trajectory planning method as described in any one of claims 1 to 3.

6. A storage medium, characterized in that, The storage medium stores a trajectory planning program, which, when executed by a processor, implements the trajectory planning method as described in any one of claims 1 to 3.

Images