Equipment control method and device and storage medium

Abstract

The embodiment of the invention provides an equipment control method and device and a storage medium, and relates to the technical field of automatic control. The equipment control method comprises the steps that control parameters of the movable equipment are determined according to a first planning track of the movable equipment at a first moment, and the control parameters comprise at least one of a target speed, a target acceleration and a target course angle used for controlling the movable equipment to run; at a second moment after the first moment, according to the position of the movable equipment and the first planning track, generating a second planning track of the movable equipment, the second planning track at least comprising a specified track overlapped with the first planning track in the longitudinal direction, the transverse deviation of the specified track and the first planned track is smaller than or equal to a preset transverse deviation threshold value, and the longitudinal direction is the driving direction of the movable equipment; updating control parameters of the mobile equipment according to the second planning track; and controlling the mobile device to travel based on the control parameters.

Description

Technical Field

[0001] The present disclosure relates to the field of automatic control technology, and more particularly, to a device control method, apparatus, and storage medium. Background Art

[0002] For a movable device such as a vehicle, it can automatically plan and generate a driving trajectory based on the state of the device itself and surrounding environment information, and automatically control the movement of the movable device according to the planned trajectory. In a dynamically changing environment, the movable device can dynamically plan the driving trajectory according to the environment information. However, in related technologies, the generated driving trajectory may mutate in scenarios such as lane change or obstacle avoidance, affecting the vehicle control stability and the user's riding experience. Summary of the Invention

[0003] In view of this, embodiments of the present disclosure propose a new technical solution for device control.

[0004] According to a first aspect of embodiments of the present disclosure, there is provided a device control method, the method comprising:

[0005] Determining control parameters of the movable device according to a first planned trajectory of the movable device at a first moment; wherein, the control parameters include at least one of a target speed, a target acceleration, and a target heading angle for controlling the movement of the movable device;

[0006] At a second moment after the first moment, generating a second planned trajectory of the movable device according to the position of the movable device and the first planned trajectory; wherein, the second planned trajectory at least includes a specified trajectory overlapping with the first planned trajectory in the longitudinal direction, and the lateral offset between the specified trajectory and the first planned trajectory is less than or equal to a preset lateral offset threshold, and the longitudinal direction is the driving direction of the movable device;

[0007] Updating the control parameters of the movable device according to the second planned trajectory;

[0008] Controlling the movement of the movable device based on the control parameters.

[0009] Optionally, the specified trajectory of the second planned trajectory at least includes a first partial trajectory line, and the first partial trajectory line is a trajectory line on the first planned trajectory between a first trajectory point and a second trajectory point; the first trajectory point is a trajectory point on the first planned trajectory having the same longitudinal coordinate as the position of the movable device at the second moment, and the second trajectory point is a trajectory point determined according to the curvature parameter of the first planned trajectory.

[0010] Optionally, the trajectory length of the first partial trajectory line is a second trajectory length, and the second trajectory length is a length determined according to a third trajectory length from the first trajectory point to a third trajectory point in the first planned trajectory, where the third trajectory point is the trajectory point with the largest curvature between the first trajectory point and the trajectory end point of the first planned trajectory.

[0011] Optionally, when the sum value of the third trajectory length and a specified length is less than or equal to a preset minimum inheritance length, the second trajectory length is the preset minimum inheritance length, where the specified length is a length by which the first partial trajectory line extends after covering the third trajectory point; or,

[0012] when the sum value of the third trajectory length and the specified length is greater than the preset minimum inheritance length and less than or equal to a preset maximum inheritance length, the second trajectory length is equal to the sum value of the third trajectory length and the specified length; or,

[0013] when the sum value of the third trajectory length and the specified length is greater than the preset maximum inheritance length, the second trajectory length is the preset maximum inheritance length.

[0014] Optionally, the specified trajectory of the second planned trajectory further includes at least a second partial trajectory line, which is planned and generated starting from the second trajectory point, and the lateral offset between the second partial trajectory line and the first planned trajectory is less than or equal to a preset lateral offset threshold.

[0015] Optionally, the cost function used when planning and generating the second partial trajectory line includes at least a first consistency cost function, and the first consistency cost function is a cost function determined based on a first lateral offset and a second lateral offset between the second partial trajectory line and the first planned trajectory, where the first lateral offset is used to represent the lateral offset between the end point of the second partial trajectory line and the end point of the first planned trajectory, and the second lateral offset is used to represent the lateral offset between each trajectory point of the second partial trajectory line and the first planned trajectory.

[0016] Optionally, the lateral offset between each trajectory point of the second partial trajectory line and the first planned trajectory is determined by Gaussian convolution calculation.

[0017] Optionally, the specified trajectory of the second planned trajectory is a trajectory planned and generated starting from a first trajectory point, where the first trajectory point is a trajectory point on the first planned trajectory that has the same longitudinal coordinate as the position of the movable device at the second moment; the cost function used when planning and generating the specified trajectory includes at least a second consistency cost function, and the second consistency cost function is a cost function determined based on a third lateral offset and a fourth lateral offset between the specified trajectory and the first planned trajectory. The third lateral offset is used to characterize the lateral offset between the end point of the specified trajectory and the end point of the first planned trajectory, and the fourth lateral offset is used to characterize the lateral offset between each trajectory point of the specified trajectory and the first planned trajectory.

[0018] According to a second aspect of the embodiments of the present disclosure, there is provided a device control device, including a memory and a processor. The memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method as described in the first aspect.

[0019] According to a third aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method as described in the first aspect.

[0020] Based on the device control method provided by the embodiments of the present disclosure, the lateral offset between the specified trajectory of the second planned trajectory generated at the second moment and the first planned trajectory generated at the first moment is less than or equal to a preset lateral offset threshold, which can enhance the consistency of the planned trajectories at the first moment and the second moment. Since the control parameters are generated based on the planned trajectories, the updated control parameters and the control parameters before the update also have a certain degree of consistency, thereby improving the continuity and stability of trajectory planning in a dynamic environment and also improving the stability of device control.

[0021] Through the following detailed description of the exemplary embodiments of the present disclosure with reference to the accompanying drawings, other features and advantages of the present disclosure will become clear. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings incorporated in and constituting a part of this specification illustrate embodiments of the present disclosure and, together with the description, are used to explain the principles of the present disclosure.

[0023] Figure 1 is a schematic diagram of an intelligent networked system to which the method provided by the embodiments of the present disclosure can be applied.

[0024] Figure 2 is according to Figure 1 a schematic diagram of a movable device provided by the shown embodiment.

[0025] Figure 3It is a schematic flowchart of a device control method provided by an embodiment of the present disclosure.

[0026] Figure 4 It is a schematic diagram of a first planned trajectory and a second planned trajectory in the related art.

[0027] Figure 5 It is a schematic diagram of a first planned trajectory and a second planned trajectory provided by an embodiment of the present disclosure.

[0028] Figure 6 It is a schematic flowchart of a trajectory planning method provided by an embodiment of the present disclosure.

[0029] Figure 7 It is a schematic structural diagram of a device control device provided by an embodiment of the present disclosure. Detailed Embodiments

[0030] Now, various exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure.

[0031] The following description of at least one exemplary embodiment is merely illustrative and in no way limits the present disclosure, its application, or its use.

[0032] Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the above technologies, methods, and devices should be regarded as part of the specification.

[0033] In all the examples shown and discussed here, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0034] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0035] The elements involved in the embodiments of the present disclosure may represent part or all of the elements. For example, the elements involved in the embodiments of the present disclosure may be at least part of the elements or all of the elements.

[0036] The elements involved in the embodiments of the present disclosure may be one or more. For example, "a", "the", "above", "said", "aforementioned", etc. are used to indicate that the corresponding elements are mentioned for the first time or are mentioned again, and do not have the meaning of limiting the quantity.

[0037] It should be noted that actions such as data collection, storage, use, processing, transmission, provision, disclosure, and deletion involved in this disclosure are carried out on the premise of complying with relevant data protection regulations and policies of the country or region where it is located and with the full authorization of the corresponding data owners.

[0038] First, the application scenarios of the embodiments of this disclosure will be described.

[0039] Figure 1 It is a schematic diagram of an intelligent connected system 100 to which the method provided by the embodiments of this disclosure can be applied. As Figure 1 shown, the intelligent connected system 100 may include: a movable device 101, a server 102, and a user terminal 103.

[0040] In some examples, the movable device 101 may be a movable device such as a vehicle, a robot, a ship, etc., such as a vehicle with an autonomous driving function, a robot that can move autonomously, etc. Among them, autonomous driving is also known as driverless or intelligent driving. A vehicle with an autonomous driving function can perform driving tasks such as environmental perception, decision-making and planning, and control execution. The levels of autonomous driving can refer to the automotive intelligent grading standard formulated by the Society of Automotive Engineers (SAE). For example, the L0 level is manual driving, L1 is assisted driving, L2 is partial autonomous driving, L3 is conditional autonomous driving, L4 is highly autonomous driving, and L5 is fully autonomous driving. The above division methods for the levels of autonomous driving are only for illustration, and the embodiments of this disclosure do not limit the division criteria and levels of autonomous driving.

[0041] In some examples, the server 102 may be a single server or a distributed server cluster composed of multiple servers, and its deployment method may include a local server or a cloud server. The server 102 can communicate with the movable device 101 and / or the user terminal 103 based on a communication network and provide various services for the movable device 101 and / or the user terminal 103. For example, the server can receive the perception data sent by the movable device and provide services such as high-precision maps, data analysis, and decision-making and planning for the movable device. Another example is that the server can receive query instructions or control instructions sent by the user terminal and provide corresponding services for the user.

[0042] In some examples, the user terminal 103 can be any form of electronic device that provides services to users, such as a personal computer, a laptop, a smart tablet, a smart phone, a smart wearable device, etc. The user can interact with the movable device or the server through the human-computer interaction terminal configured by the movable device 101, or can also interact with the movable device or the server through the user terminal 103. For example, the user can query the status and / or parameters of the movable device through the user terminal, or control the movable device to execute a set task and / or modify configuration parameters, etc.; wherein, the user terminal runs an application program based on the intelligent networked system to realize the interaction with the movable device or the server. The application program can be a local application, a web application or a mini program, etc., which is not limited herein.

[0043] In some examples, the above application program running on the user terminal can provide authentication or authorization services for users. Users who are successfully authenticated and granted corresponding permissions can query and / or control the movable device within the granted permissions.

[0044] The movable device 101, the server 102 and the user terminal 103 can communicate through the communication link provided by the communication network 104. The communication network 104 can include one or more networks of any type. For example, the communication network 104 can include the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a public switched telephone network (PSTN), a satellite communication network, Wi-Fi, 2G, 3G, 4G, 5G, 6G, NB-IoT, eMTC, infrared, Bluetooth, NFC and other networks that provide communication, or a combination of the above multiple networks. The communication networks between the movable device 101 and the server 102, between the user terminal 103 and the server 102, and between the user terminal 103 and the movable device 101 can be the same or different.

[0045] It should be noted that Figure 1 the structure of the intelligent networked system 100 shown in

[0046] Figure 2 is only schematic. The intelligent networked system in the embodiments of the present disclosure is not limited to the above structure, and may include more or fewer devices as needed, or the devices may be combined or split. For example, the intelligent networked system may not include a user terminal and / or a server; for another example, the user terminal and the server can be combined and deployed. Figure 1 is a schematic diagram of a movable device 101 provided according to the Figure 2As shown, the mobile device 101 may include a sensing component 1011, a computing platform 1012, an execution component 1013, etc. Among them, the sensing component 1011, the computing platform 1012, and the execution component 1013 may be connected through a bus or other means.

[0047] In some examples, the sensing component 1011 may be used to collect information about the mobile device itself or the outside. The sensing component 1011 may include at least one of a vision sensing unit, a radar, a positioning and navigation unit, an inertial measurement unit (IMU), or other sensing units. Among them, the vision sensor unit may include one or more cameras, and the radar may include at least one of a lidar, a millimeter wave radar, an ultrasonic radar, or other radars. The positioning and navigation unit may include at least one of a GPS system, a Beidou system, or other global positioning systems.

[0048] In some examples, the computing platform 1012 may include a device with computing capabilities for processing the sensing information collected by the sensing component 1011 to obtain control information and sending corresponding control instructions to the execution component 1013, so that the execution component 1013 performs corresponding actions, thereby realizing the control of the movable device 101. Exemplarily, the computing platform 1012 may perform one or more of the behaviors such as simultaneous localization and mapping (SLAM), information collection and processing, decision-making, planning, and control on the movable device, thereby realizing the autonomous control of the movable device. The computing platform 1012 may include at least one processor and at least one memory. Each processor may execute the instructions stored in the memory alone or jointly to implement the method provided by the embodiments of the present disclosure. The processor in the embodiments of the present disclosure may include at least one of a central processing unit (CPU), a graphic processing unit (GPU), a neural-network processing unit (NPU), a tensor processing unit (TPU), a data processing unit (DPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), a micro controller unit (MCU), or other processors. The memory may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. In addition to storing instructions, the memory may also store data, such as high-precision maps, path information, the position, direction, speed, etc. of the movable device. The data stored in the memory may be acquired and used by the processor.

[0049] In some examples, the computing platform of the movable device may execute computing tasks independently or communicate with a server to complete computing tasks. For example, the computing platform of the movable device may cooperate with the server to complete corresponding computing tasks.

[0050] The computing platform 1012 can be set in the mobile device 101, and part or all of the computing platform 1012 can also be set in the server corresponding to the mobile device. For example, functions with higher real-time requirements in the computing platform 1012 are set in the mobile device, and functions with lower real-time requirements are set in the server corresponding to the mobile device.

[0051] In some examples, the execution component 1013 is used to perform corresponding actions based on the control of the computing platform 1012, so that the mobile device 101 completes the movement task. The execution component 1013 can include, for example, a power component, a braking component, a transmission component, a steering component, etc.

[0052] It should be noted that Figure 2 The structure of the mobile device 101 shown in is only schematic. The mobile device in the embodiments of the present disclosure is not limited to the above structure, and may include more or fewer components according to needs, and the device may also be combined or split. For example, the mobile device may not include the above computing platform. For another example, the mobile device may further include a communication component, an interface component, a multimedia component, an input component, an output component, etc.

[0053] The embodiments of the present disclosure can be applied to the device control scenario, especially the scenario of trajectory planning for a mobile device to control its driving. In a dynamically changing environment, the mobile device can dynamically plan its driving trajectory according to the environmental information. However, in related technologies, the generated driving trajectory will mutate in scenarios such as lane changing or obstacle avoidance, affecting the stability of device control.

[0054] The mobile device can perform trajectory planning periodically based on its own state and surrounding environmental information. For example, the mobile device can perform trajectory planning every N seconds, and each time it generates a planned trajectory of M seconds, where M is greater than N. For example, N can be 1 and M can be 8. The starting point of the trajectory planned in each cycle of the mobile device is the current position of the mobile device, and the trajectory of this cycle starting from the current position is planned based on device state information such as the current direction angle, speed, and acceleration. This planning method has a high probability of a large difference in the trajectories planned in the previous and subsequent cycles in transient scenarios such as lane changing or obstacle avoidance, which may lead to problems such as discontinuous trajectories and device control jitter.

[0055] In view of the problems of related technologies, embodiments of the present disclosure provide a device control method. When performing trajectory planning for a movable device, the device control method introduces trajectory splicing and a consistency cost function to comprehensively optimize the safety, smoothness, and real-time performance of the trajectory, solves the problems of discontinuous trajectories and control jitter in lane-changing and obstacle-avoiding scenarios in traditional trajectory planning, improves the continuity and stability of trajectory planning in a dynamic environment, and also improves the stability of device control.

[0056] Figure 3 It is a schematic flowchart of a device control method provided by an embodiment of the present disclosure. This device control method can be executed by Figure 1 the movable device and / or server shown. As Figure 3 shown, the device control method of this embodiment may include the following steps S310 to S340.

[0057] Step S310, determine the control parameters of the movable device according to the first planned trajectory of the movable device at the first moment.

[0058] The control parameters may include at least one of a target speed, a target acceleration, and a target heading angle for controlling the movement of the movable device. For example, the control parameters may only include the target speed and the target heading angle, the target parameters may also only include the target acceleration and the target heading angle, the control parameters may also only include the target speed or the target acceleration (such as a straight-line driving with a constant heading angle), and the control parameters may also only include the target heading angle (such as a uniform motion with a constant speed and zero acceleration).

[0059] In some examples, the planned trajectory of the movable device (such as the above-mentioned first planned trajectory) has time and space attributes. Based on the first planned trajectory, it is possible to predict at what moment the movable device will reach what spatial position, so that it is possible to determine what control parameters the movable device needs to use for driving, that is, at least one of the target speed, the target acceleration, and the target heading angle that meets the requirements of the first planned trajectory can be determined.

[0060] Step S320, at a second moment after the first moment, generate a second planned trajectory of the movable device according to the position of the movable device and the first planned trajectory.

[0061] The second planned trajectory may at least include a specified trajectory that overlaps with the first planned trajectory in the longitudinal direction, and the lateral offset between the specified trajectory and the first planned trajectory is less than or equal to a preset lateral offset threshold. The preset lateral offset threshold can be used to characterize the consistency between the specified trajectory and the first planned trajectory, and a lateral offset less than or equal to the preset lateral offset threshold can indicate that the consistency between the specified trajectory and the first planned trajectory is higher than the threshold. Exemplarily, the preset lateral offset threshold can be any pre-set value to meet different consistency requirements. Exemplarily, the preset lateral offset threshold can be 0.5 meters or 1 meter, or it can be half of the vehicle body width.

[0062] In some examples, the above longitudinal direction can be the driving direction of the movable device, and the driving direction is the extension direction of the navigation reference line or the road center line. The navigation reference line can be the global reference path from the current position of the movable device to the target position, and the target position can be the destination that the movable device expects to drive to. The navigation reference line can be planned and generated by the movable device or the server based on the navigation map. Exemplarily, taking the center point of the movable device as the coordinate origin, the driving direction of the movable device (i.e., the extension direction of the navigation reference line) as the longitudinal direction, and the direction perpendicular to the longitudinal direction as the lateral direction, a two-dimensional device coordinate system of the movable device is established to determine the above two mutually perpendicular longitudinal and lateral directions. Optionally, the positive direction of the longitudinal direction is the driving direction of the movable device, and the positive direction of the lateral direction can be the right hand side perpendicular to the longitudinal direction.

[0063] The above preset lateral offset threshold can be a pre-set threshold or a value determined after sorting the offsets of multiple candidate trajectories. For example, if multiple candidate trajectories that meet the safety and smooth line conditions are planned, the minimum value of the offsets of the multiple candidate trajectories can be used as the preset lateral offset threshold, so as to obtain a planned trajectory with the smallest lateral offset.

[0064] In some examples, the time difference between the first moment and the second moment can be the trajectory planning period of the movable device. The first moment and the second moment can be the starting moments of two adjacent trajectory planning periods (i.e., the moments when trajectory planning is executed). For example, the first moment can be the moment when the first trajectory planning is executed, and the second moment can be the moment when the second trajectory planning is executed. Exemplarily, the movable device can execute trajectory planning every N seconds, and each planning generates a planned trajectory of M seconds, where M is greater than N. For example, N can be 1 and M can be 8. The time difference between the first moment and the second moment can be N seconds. The first moment and the second moment can be the starting moments of any two adjacent periods of the movable device's trajectory planning.

[0065] In some examples, the first planned trajectory at the first moment can be referred to as the planned trajectory of the previous cycle, and the second planned trajectory at the second moment can be referred to as the planned trajectory of the current cycle.

[0066] In some examples, the first planned trajectory and the second planned trajectory can be displayed on a display component. For example, they can be displayed on the display component of a movable device or a server so that the user can intuitively observe the situation of the planned trajectory.

[0067] Step S330: Update the control parameters of the movable device according to the second planned trajectory.

[0068] Exemplarily, based on the second planned trajectory, it can be expected at what moment the movable device will reach what spatial position, so that it can be determined what control parameters the movable device needs to adopt for driving, that is, at least one of the target speed, target acceleration, and target heading angle that meets the requirements of the second planned trajectory can be determined.

[0069] It should be noted that the control parameters updated according to the second planned trajectory in step S330 may be the same as or different from the control parameters determined according to the first planned trajectory in step S310.

[0070] Step S340: Control the driving of the movable device based on the control parameters.

[0071] Exemplarily, at least one of the target speed, target acceleration, or target heading angle of the movable device can be controlled based on the control parameters so that the movable device drives based on the second planned trajectory.

[0072] In some examples, between the first moment and the second moment, the control parameters of the movable device can be determined according to the first planned trajectory, and the movable device can be controlled to drive based on the control parameters; after the second moment and until a new planned trajectory is generated, the control parameters of the movable device can be determined or updated according to the second planned trajectory, and the movable device can be controlled to drive based on the control parameters.

[0073] By adopting this method, since the lateral offset between the specified trajectory of the second planned trajectory and the first planned trajectory is less than or equal to the preset lateral offset threshold, the consistency of the planned trajectories at the first moment and the second moment can be enhanced. And since the control parameters are generated based on the planned trajectories, the updated control parameters and the control parameters before the update also have a certain degree of consistency. Thus, the continuity and stability of trajectory planning in a dynamic environment can be improved, and the stability of device control can also be improved.

[0074] To more clearly illustrate the device control method provided by the embodiments of the present disclosure, the first planned trajectory and the second planned trajectory will be described in detail below.

[0075] Figure 4 It is a schematic diagram of a first planned trajectory and a second planned trajectory provided in the related art. As Figure 4 shown, the longitudinal direction can be the driving direction of the movable device 101, for example, the extension direction of the navigation reference line or the center line of the road. The positive direction of the longitudinal direction is the front of the driving direction of the movable device; the transverse direction is the direction perpendicular to the longitudinal direction, and the positive direction of the transverse direction can be the right hand side perpendicular to the longitudinal direction. The moment when the movable device 101 is located at the position point 40 shown in the figure is the first moment. At the first moment, the movable device plans the first planned trajectory 411 shown in gray in the figure. At the second moment after the first moment, the movable device is located at the position point 41 shown in the figure. The movable device plans the planned trajectory 413 shown in blue in the figure at the second moment. In the related art, the consistency of the two planned trajectories before and after is not considered. Under the influence of the front obstacle Q, the first planned trajectory 411 generated at the first moment bypasses from the right side of the obstacle Q, and the planned trajectory 413 generated at the second moment bypasses from the right side of the obstacle Q. The lateral offsets of the two planned trajectories are very large, resulting in discontinuous trajectories and large changes in control parameters, which affects the stability of the control of the movable device.

[0076] Figure 5 It is a schematic diagram of a first planned trajectory and a second planned trajectory provided in an embodiment of the present disclosure. As Figure 5 shown, by using the method provided in the embodiment of the present disclosure, the moment when the movable device 101 is located at the position point 40 shown in the figure is the first moment. At the first moment, the movable device plans the first planned trajectory 411 shown in gray in the figure. At the second moment after the first moment, the movable device is located at the position point 41 shown in the figure. The movable device plans the second planned trajectory 412 shown in red in the figure at the second moment. Due to considering the consistency of the two planned trajectories before and after, even if there is an obstacle Q in the front, both the first planned trajectory and the second planned trajectory bypass from the right side of the obstacle Q, so that the second planned trajectory at least includes a specified trajectory overlapping with the first planned trajectory in the longitudinal direction, and the lateral offset of the specified trajectory from the first planned trajectory is less than or equal to a preset lateral offset threshold, which improves the continuity of the planned trajectory, and the change in the control parameter determined based on the planned trajectory is small, thereby improving the stability of the control of the movable device.

[0077] The above figure takes the case where the position of the movable device at the second moment is at a certain trajectory point on the first planned trajectory as an example for illustration. It can be understood that if the position of the movable device at the second moment deviates from the first planned trajectory, the above position point 41 can be the trajectory point on the first planned trajectory with the same longitudinal coordinate as the position of the movable device at the second moment, that is, the position point 41 is also the first trajectory point 41 on the first planned trajectory.

[0078] In some examples, the first planned trajectory may include at least one of a trajectory starting point 40, a first trajectory point 41, a second trajectory point 42, a third trajectory point 43, and a trajectory end point 48. The trajectory starting point 40 and the trajectory end point 48 may be the starting point and the end point of the trajectory planned for the movable device at the first moment; the first trajectory point 41 may be a trajectory point on the first planned trajectory having the same longitudinal coordinate as the position of the movable device at the second moment; and the second trajectory point 42 and the third trajectory point 43 may be trajectory points determined based on a curvature parameter of the first planned trajectory.

[0079] For example, the third trajectory point 43 can be a trajectory point with the largest curvature among the multiple trajectory points between the first trajectory point 41 and the trajectory end point 48 of the first planned trajectory. Curvature is a geometric parameter used to measure the degree of curvature of the planned trajectory. The curvature corresponding to the trajectory point on the planned trajectory can characterize the rate of change of the tangent direction angle (the angle between the tangent and the reference direction) of the trajectory point to the arc length, which can be calculated by numerical differentiation or geometric fitting. The larger the curvature, the more drastic the change in the tangent direction angle per unit arc length, and the higher the curvature of the curve. When the vehicle passes through a trajectory point with a larger curvature, it means that a larger steering angle or a lower driving speed is required to meet the vehicle dynamics constraints. Therefore, the part with the largest curvature in the first planned trajectory is often the part where the control parameters and driving state of the movable device are the most unstable, and the steering angle and speed need to be changed and controlled accordingly.

[0080] Furthermore, the second trajectory point 42 can be a trajectory point determined based on the third trajectory point 43, and is used to generate a second planned trajectory at the second moment. For example, the second trajectory point 42 can be a trajectory point after the third trajectory point 43, and the trajectory length distance between the second trajectory point and the third trajectory point is greater than or equal to the specified length. In this way, the second planned trajectory generated based on the second trajectory point can retain the part with the largest curvature in the previous first planned trajectory, and the consistency of this part of the high curvature trajectory is retained in the two plans, which can also make the control parameters determined based on the planned trajectory remain stable, thereby improving the stability of the equipment control. On the contrary, if the second planned trajectory generated by the second trajectory point cannot retain the part with the largest curvature in the previous first planned trajectory, it will cause the curvature of the two planned trajectories to change significantly, and the control parameters determined based on the planned trajectory will also change significantly, which will affect the stability of the equipment control and even cause jitter problems during the equipment driving process.

[0081] Continue as Figure 5 As shown, the second planned trajectory 412 of this embodiment at least includes a designated trajectory that overlaps with the first planned trajectory 411 in the longitudinal direction. The designated trajectory can be as follows: Figure 5The red trajectory line between the longitudinal coordinates S1 and S2 as shown, and the lateral offset between the specified trajectory and the first planned trajectory can be less than or equal to a preset lateral offset threshold.

[0082] In some examples, the specified trajectory of the second planned trajectory can include at least one of a first partial trajectory line and a second partial trajectory line. As Figure 5 shown, the first partial trajectory line can be the red-schemed trajectory line between the first trajectory point 41 and the second trajectory point 42, that is, the red trajectory line between the longitudinal coordinates S1 and S4; the second partial trajectory line can be the red-schemed trajectory line between the second trajectory point 42 and the fourth trajectory point 44, that is, the red trajectory line between the longitudinal coordinates S4 and S2.

[0083] Further, the trajectory end point of the second planned trajectory can be Figure 5 the trajectory point 49 as shown, that is to say, the second planned trajectory can include a first partial trajectory line, a second partial trajectory line, and a third partial trajectory line between the fourth trajectory point 44 and the trajectory point 49, and the third partial trajectory line is the red trajectory line between the longitudinal coordinates S2 and S3.

[0084] The above-mentioned first partial trajectory line can also be called a splicing line, and this splicing line can directly inherit a part of the first planned trajectory, that is, the lateral offset from the first planned trajectory is zero. The second partial trajectory line and the third partial trajectory line can be called strong planned trajectory lines, and these strong planned trajectory lines can be trajectory lines re-planned at the second moment. During the process of planning the second partial trajectory line and the third partial trajectory line, consistency constraint conditions can be introduced so that the planned trajectory line has a lateral offset from the first planned trajectory less than or equal to the preset lateral offset threshold, improving the consistency of trajectory planning.

[0085] In some examples, as Figure 5 shown, the specified trajectory of the above-mentioned second planned trajectory at least includes the first partial trajectory line, and this first partial trajectory line can be the trajectory line on the first planned trajectory between the first trajectory point 41 and the second trajectory point 42, that is, the first partial trajectory line starts from the first trajectory point 41 and ends at the second trajectory point 42. Among them, the first trajectory point can be the trajectory point on the first planned trajectory with the same longitudinal coordinate as the position of the movable device at the second moment.

[0086] In this way, the lateral offset between the first partial trajectory and the first planned trajectory is zero, that is, the first partial trajectory directly inherits a part of the first planned trajectory, thereby ensuring the consistency between the initial partial trajectory of the second planned trajectory and the first planned trajectory, and improving the stability of the control parameters determined based on the planned trajectory.

[0087] The above-mentioned second trajectory point can be determined in any of the following ways:

[0088] In one implementation, the second trajectory point can be a trajectory point determined based on a preset inheritance length. For example, a trajectory point located after the first trajectory point and at a distance of the preset inheritance length from the first trajectory point can be used as the second trajectory point. The preset inheritance length is the trajectory length that the movable device can travel within a preset time, and the preset time can be a preset time, such as 1 second, 2 seconds, or 5 seconds.

[0089] In another implementation, the second trajectory point can be a trajectory point determined according to the curvature parameter of the first planned trajectory. Exemplarily, a third trajectory point with the maximum curvature between the first trajectory point and the trajectory end point of the first planned trajectory can be determined according to the curvature parameter of the first planned trajectory, and then the second trajectory point can be determined based on the third trajectory point. For example, a trajectory point at a specified length in front of the third trajectory point can be used as the second trajectory point.

[0090] In another implementation, since the first trajectory point is the starting point of the first part of the trajectory line and the second trajectory point is the end point of the first part of the trajectory line, the position of the second trajectory point can be determined after determining the trajectory length of the first part of the trajectory line. Exemplarily, the trajectory length of the first part of the trajectory line is the second trajectory length, and the second trajectory length can be a length determined according to the third trajectory length from the first trajectory point to the third trajectory point in the first planned trajectory. The third trajectory point is the trajectory point with the maximum curvature between the first trajectory point and the trajectory end point of the first planned trajectory. For example Figure 5 the third trajectory point 43 shown.

[0091] In some examples, the second trajectory length can be equal to the sum value of the third trajectory length and a specified length. The specified length can be the length that the first part of the trajectory line extends after the third trajectory point as preset, and the specified length can also be called a compensation length. Through this specified length, the first part of the trajectory line can inherit enough high-curvature regions of the first planned trajectory. The specified length can be any preset length. For example, the specified length can be 0 meters, 1 meter, or 2 meters, or it can also be the distance that the movable device can travel within a specified duration according to the specified duration. The specified duration can be 0 seconds, 0.1 seconds, or 0.5 seconds. In this way, the sum value of the third trajectory length and the specified length can be used as the trajectory length of the first part of the trajectory line, so that the first part of the trajectory line of the second planned trajectory includes the third trajectory point with the maximum curvature on the first planned trajectory and covers enough high-curvature regions.

[0092] In some other examples, the second trajectory length can be determined according to the third trajectory length and a preset maximum inheritance length. For example, when the third trajectory length is less than or equal to the preset maximum inheritance length, the second trajectory length can be equal to or greater than the third trajectory length, so that the first partial trajectory line includes at least the third trajectory point with the maximum curvature. For another example, when the third trajectory length is greater than the preset maximum inheritance length, the second trajectory length can be equal to the preset maximum inheritance length, so as to avoid an excessive inheritance of the length of the first planned trajectory by the second planned trajectory and improve the flexibility of trajectory planning.

[0093] In some other examples, the second trajectory length can be determined according to the third trajectory length, a specified length, a preset minimum inheritance length, and a preset maximum inheritance length. Exemplarily, the method for determining the second trajectory length can include one or more of the following:

[0094] Method 1: When the sum of the third trajectory length and the specified length is less than or equal to the preset minimum inheritance length, the second trajectory length is the preset minimum inheritance length, and the specified length can be the length that the first partial trajectory line of the second planned trajectory extends after the third trajectory point. In this way, it can not only make the first partial trajectory line of the second planned trajectory contain the third trajectory point with the maximum curvature on the first planned trajectory, but also enable the second planned trajectory to inherit a sufficient trajectory length from the first planned trajectory, avoiding an overly small inheritance length that affects trajectory consistency.

[0095] Method 2: When the sum of the third trajectory length and the specified length is greater than the preset minimum inheritance length and less than or equal to the preset maximum inheritance length, the second trajectory length is equal to the sum of the third trajectory length and the specified length. In this way, it can make the first partial trajectory line of the second planned trajectory contain the third trajectory point with the maximum curvature on the first planned trajectory and cover a sufficient number of high-curvature regions.

[0096] Method 3: When the sum of the third trajectory length and the specified length is greater than the preset maximum inheritance length, the second trajectory length is the preset maximum inheritance length. In this way, it can avoid an excessive inheritance of the length of the first planned trajectory by the second planned trajectory and improve the flexibility of trajectory planning.

[0097] The above-mentioned specified length, preset minimum inheritance length, and preset maximum inheritance length can all be preset values, and their magnitude relationships can be: the specified length is less than the preset minimum inheritance length, and the preset minimum inheritance length is less than the preset maximum inheritance length. Optionally, the above lengths can be determined according to the length of the second planned trajectory (i.e., the trajectory length that needs to be planned for each cycle). For example, 1 / 8 of the second planned trajectory length can be used as the preset minimum inheritance length, 1 / 4 of the second planned trajectory length can be used as the preset minimum inheritance length, and 1 / 16 of the second planned trajectory length can be used as the specified length.

[0098] In the above - mentioned manner, based on curvature, specified length, preset minimum inheritance length, and preset maximum inheritance length, the trajectory length of the first - part trajectory line (i.e., the splicing line) can be flexibly determined, enabling the second planned trajectory generated at a later second moment to inherit the high - curvature trajectory interval of the first planned trajectory generated at a previous first moment to the greatest extent. This can avoid sudden changes or frequent adjustments of control parameters caused by excessive differences in curvature before and after, reduce equipment jitter, and improve the stability of equipment control. Further, since the control algorithms for high - curvature trajectories are often more complex, retaining high - curvature trajectories can also reduce the adjustment of control algorithms and improve equipment control efficiency.

[0099] In some examples, the trajectory length of the first - part trajectory line (i.e., the second trajectory length) can be represented by the trajectory duration. Based on this trajectory duration, the spatial length of the trajectory that the movable device can travel within this trajectory duration can be determined. The trajectory duration can be determined by the following formula (1):

[0100]

[0101] where, ΔT trim represents the trajectory duration of the first - part trajectory line, that is, the duration from the first - moment - planned first planned trajectory spliced to the second - moment - planned second planned trajectory. Based on this trajectory duration, the second trajectory length can be determined. T max,κ represents the time corresponding to the third trajectory point with the maximum curvature (κ) in the first planned trajectory, which can be used to determine the time point with the most drastic change in trajectory curvature. Δt represents the specified duration, that is, the compensation time, which is used to ensure that the spliced trajectory covers enough high - curvature regions. T1 represents the preset minimum inheritance duration, which can determine the preset minimum inheritance length, and T2 represents the preset maximum inheritance duration, which can determine the preset maximum inheritance length. By different value conditions of T1 and T2, the splicing duration can be restricted within a reasonable range to ensure the continuity and stability of the trajectory. In some examples, the preset minimum inheritance duration can be 1 / 8 of the total planned duration of the cycle, and the preset maximum inheritance duration can be 1 / 4 of the total planned duration of the cycle. For example, if the trajectory is planned for 8 seconds in each cycle, then the preset minimum inheritance duration can be 1 second, that is, the preset minimum inheritance length is the distance that the movable device travels within the preset minimum inheritance duration (1 second); the preset maximum inheritance duration can be 2 seconds, that is, the preset maximum inheritance length is the distance that the movable device travels within the preset maximum inheritance duration (2 seconds).

[0102] Based on the above formula, if condition one ((T max,κ +Δt)<T1) is satisfied, then the trajectory duration of the first - part trajectory line is T1; if condition two (T1<(T max,κ +Δt)≤T2) is satisfied, then the trajectory duration of the first - part trajectory line is T max,κ+Δt; If the condition three ((T max,κ +Δt)>T2) is satisfied, the trajectory duration of the first part of the trajectory line is T2.

[0103] Using the above method to determine the trajectory length of the first part of the trajectory line (i.e., the splicing line), it is possible to intercept a part of the trajectory from the first planned trajectory as the first part of the trajectory line of the second planned trajectory based on the curvature parameter, ensuring the consistency between the first part of the trajectory line and the first planned trajectory and reducing the discontinuity problem during the trajectory switching.

[0104] In some embodiments of the present disclosure, the designated trajectory of the second planned trajectory at least further includes a second part of the trajectory line, that is, the designated trajectory of the second planned trajectory includes the first part of the trajectory line and the second part of the trajectory line. Continuing as Figure 5 shown, the first part of the trajectory line is the trajectory line between the first trajectory point 41 and the second trajectory point 42. The second part of the trajectory line can be planned and generated starting from the second trajectory point 42. For example, the second part of the trajectory line can be the red-schemed trajectory line between the second trajectory point 42 and the fourth trajectory point 44, and the lateral offset of the second part of the trajectory line from the first planned trajectory is less than or equal to the preset lateral offset threshold.

[0105] In some examples, the generation method of the second part of the trajectory line may include the following steps S11 and S12.

[0106] Step S11: Starting from the second trajectory point, generate a plurality of candidate trajectories based on a preset polynomial plan.

[0107] Wherein, the second trajectory point is the end point of the first part of the trajectory line.

[0108] Exemplarily, starting from the second trajectory point, a plurality of horizontal and vertical trajectories can be generated based on a preset polynomial plan, so as to obtain a plurality of candidate trajectories, and different candidate trajectories can correspond to different target position points.

[0109] In some examples, the preset polynomial may be a cubic polynomial or a quintic polynomial. Exemplarily, candidate trajectories can be generated based on the following formula (2) quintic polynomial.

[0110] l(s) = c0 + c1s + c2s 2 + c3s 3 + c4s 4 + c5s 5 (2)

[0111] Wherein, s represents the longitudinal displacement of the trajectory point, and the longitudinal direction can be the driving direction of the movable device, such as the extension direction of the navigation reference line or the road center line. l(s) represents the lateral displacement of the trajectory point. The coefficients c0, c1, c2, c3, c4, and c5 represent the coefficients of the fifth-degree polynomial, which can be calculated based on the current state (such as position, speed, acceleration, heading angle, etc.) and the target state of the movable device to ensure the smoothness of the trajectory. The fifth-degree polynomial has sufficient degrees of freedom to satisfy the continuity constraints of the initial and target states.

[0112] The candidate trajectory may include the second partial trajectory line of the second planned trajectory, and the candidate trajectory may also include the second partial trajectory line and the third partial trajectory line. Among them, the second partial trajectory line may be, for example, Figure 5 the trajectory line between the longitudinal coordinates S4 and S2 as shown, and the third partial trajectory line may be, for example, Figure 5 the trajectory line between the longitudinal coordinates S2 and S3 as shown. The longitudinal coordinate S4 may be the planned starting coordinate of the second partial trajectory line, that is, the ending coordinate of the first partial trajectory line. The longitudinal coordinate S2 may be the ending coordinate of the first planned trajectory, and the longitudinal coordinate S3 may be the ending coordinate of the second planned trajectory.

[0113] In some examples, feasibility verification can be performed on the candidate trajectory, and the candidate trajectories that fail the feasibility verification are excluded as invalid trajectories. The conditions for failing the feasibility verification may include at least one of the following: the candidate trajectory collides with an obstacle or the collision probability is greater than a preset collision threshold, there are trajectory points in the candidate trajectory with a curvature greater than the preset maximum curvature of the movable device, there are trajectory points in the candidate trajectory with a speed greater than the preset maximum speed of the movable device, and there are trajectory points in the candidate trajectory with an acceleration greater than the preset maximum acceleration of the movable device. The above preset maximum curvature, preset maximum speed, and preset maximum acceleration can all be determined based on the specifications of the movable device.

[0114] Step S12, determining the second partial trajectory line according to multiple candidate trajectories.

[0115] Exemplarily, the second partial trajectory line can be determined from multiple candidate trajectories based on the objective cost function. For example, the objective cost of each candidate trajectory can be calculated based on the objective cost function, and the candidate trajectory with the minimum objective cost is selected as the second partial trajectory line.

[0116] The objective cost function used when determining the second partial trajectory line may include one or more of a safety cost function, a smoothness cost function, and a consistency cost function. The smoothness cost function may include a longitudinal smoothness cost function and a lateral smoothness cost function.

[0117] Exemplarily, the objective cost function can be determined based on the following formula (3):

[0118] Cost total =W sl (Cost s +Cost l )+W col Cost col +W con Cost icon (3)

[0119] Among them, Cost total represents the target cost; Cost s represents the vertical smoothness cost; Cost i represents the horizontal smoothness cost; Cost col represents the safety cost, and this safety cost can be the collision risk cost, reflecting the proximity of the trajectory to the obstacle; Cost icon represents the consistency cost, reflecting the similarity between the candidate trajectory and the first planned trajectory in the previous cycle; W sl , W col , W con are the weight coefficients corresponding to the smoothness cost, the safety cost, and the consistency cost respectively, used to balance the influence of different costs on the trajectory planning.

[0120] In some examples, such as in the obstacle avoidance scenario, the weight of the consistency cost can be greater than the weights of the smoothness cost and the safety cost to improve the continuity of the trajectory.

[0121] It should be noted that when determining the second part of the trajectory line from multiple candidate trajectories based on the target cost function, the target cost function can be calculated only for each candidate trajectory, or the target cost function can be calculated overall after merging each candidate trajectory with the first part of the trajectory line.

[0122] In some examples, the cost function used when planning and generating the second part of the trajectory line can include a first consistency cost function, and this first consistency cost function is a cost function determined based on the first lateral offset and / or the second lateral offset between the second part of the trajectory line and the first planned trajectory, where:

[0123] This first lateral offset can be used to characterize the lateral offset between the end point of the second part of the trajectory line and the end point of the first planned trajectory.

[0124] The second lateral offset can be used to characterize the lateral offsets between the respective trajectory points of the second part of the trajectory line and the first planned trajectory. Exemplarily, the lateral offsets between the respective trajectory points of the second part of the trajectory line and the first planned trajectory can be determined separately, and then the average value, weighted average value or integral value of the lateral offsets of the respective trajectory points can be calculated as part of the first consistency cost function. Optionally, the lateral offsets between the respective trajectory points of the second part of the trajectory line and the first planned trajectory can be determined by Gaussian convolution calculation, and the standard deviation of the Gaussian distribution used for the Gaussian convolution calculation can be a preset value, such as 0.5 or 0.6.

[0125] In some examples, the first consistency cost function may only include the first lateral offset. For example, the square of the first lateral offset can be calculated as the consistency cost.

[0126] In some other examples, the first consistency cost function may only include the second lateral offset. For example, the square of the second lateral offset can be calculated as the consistency cost.

[0127] In still some other examples, the first consistency cost function may include the first lateral offset and the second lateral offset. Exemplarily, the first consistency cost function of the candidate trajectory can be the following formula (4):

[0128]

[0129] where, Cost icon represents the consistency cost between the candidate trajectory and the first planned trajectory. The larger the offset, the larger the value of this consistency cost and the lower the consistency; ΔD represents the first lateral offset, that is, the lateral offset between the end point of the candidate trajectory and the end point of the first planned trajectory; J icon represents the consistency convolution value determined based on the Gaussian convolution of the second lateral offset. For example, it can be the convolution value of the lateral offsets between the respective trajectory points of the candidate trajectory and the first planned trajectory. The larger this consistency convolution value, the higher the consistency. To avoid the cost function from failing due to the consistency convolution value being 0, the calculation method of adding 1 to the consistency convolution value is adopted in this formula.

[0130] In this way, the consistency cost function magnifies the proportion of the influence of the lateral offset at the end point through the square term, and can better reflect the consistency of the trajectory.

[0131] Furthermore, the above-mentioned consistency convolution value can be calculated based on the following formulas (5) and (6):

[0132]

[0133] where, J icon represents the consistency convolution value; N represents the number of sampled trajectory points on the candidate trajectory; Indicates whether the lateral offset between the j-th trajectory point of the candidate trajectory and the trajectory point with the same longitudinal coordinate on the first planned trajectory is less than a preset threshold (i.e., whether the lateral coordinates are the same). The lateral offset between the j-th trajectory point and the first planned trajectory can be the lateral offset amount between the j-th trajectory point of the candidate trajectory and the k-th trajectory point of the first planned trajectory. The longitudinal coordinates of the j-th trajectory point of the candidate trajectory and the k-th trajectory point of the first planned trajectory are the same. The value can be 0 or 1. 0 indicates that the lateral offset is less than the preset threshold, that is, the lateral coordinates are basically the same. 1 indicates that the lateral offset is not less than the preset threshold, that is, the lateral coordinates are not the same; G(j) represents a Gaussian convolution kernel, which is used to calculate the lateral offset similarity between adjacent trajectories (the candidate trajectory and the first planned trajectory). For example, G(j) can obtain the convolution value of the lateral offset between the j-th trajectory point of the candidate trajectory and the first planned trajectory through the Gaussian convolution kernel.

[0134] Among them, the specific implementation of the Gaussian convolution kernel can be shown in the following formula (6):

[0135]

[0136] Among them, G(j) represents a Gaussian convolution kernel; σ represents the standard deviation of the Gaussian distribution, which can be used to adjust the influence range of trajectory consistency. The larger σ is, the wider the Gaussian function is, the larger the influence range is, and the stronger the correlation between trajectory points is; the smaller σ is, the narrower the Gaussian function is, the smaller the influence range is, and the stronger the correlation between trajectory points is. Optionally, σ can be a set value, such as 0.5; Δd lat (j) represents the lateral offset amount between the j-th trajectory point of the candidate trajectory and the first planned trajectory. For example, it can be the lateral offset amount between the j-th trajectory point of the candidate trajectory and the k-th trajectory point of the first planned trajectory. The longitudinal coordinates of the j-th trajectory point of the candidate trajectory and the k-th trajectory point of the first planned trajectory are the same.

[0137] In this way, by using the above method, the second part of the trajectory line of the second planned trajectory can be planned and generated based on the first consistency cost function, which can further improve the consistency between the second planned trajectory and the first planned trajectory, and also make the control parameters determined based on the planned trajectory remain stable, improving the stability of equipment control.

[0138] In some embodiments of the present disclosure, the specified trajectory of the second planned trajectory can be a trajectory directly planned and generated with the first trajectory point as the starting point. The first trajectory point is the trajectory point on the first planned trajectory with the same longitudinal coordinate as the position of the movable device at the second moment. For example Figure 5 the first trajectory point 41 shown.

[0139] In some examples, the cost function used when planning to generate the specified trajectory may include one or more of a safety cost function, a smoothness cost function, and a consistency cost function. The smoothness cost function may include a longitudinal smoothness cost function and a lateral smoothness cost function.

[0140] Exemplarily, the cost function used when planning to generate the specified trajectory may include a second consistency cost function, and the second consistency cost function may be a cost function determined based on a third lateral offset and a fourth lateral offset between the specified trajectory and the first planned trajectory, where:

[0141] The third lateral offset is used to characterize the lateral offset between the end point of the specified trajectory and the end point of the first planned trajectory.

[0142] The fourth lateral offset is used to characterize the lateral offset between each trajectory point of the specified trajectory and the first planned trajectory. Exemplarily, the lateral offset between each trajectory point of the specified trajectory and the first planned trajectory may be determined respectively, and then the average value, weighted average value or integral value of the lateral offsets of each trajectory point may be calculated as the fourth lateral offset. Optionally, the fourth lateral offset may be a lateral offset determined based on Gaussian convolution.

[0143] It should be noted that for the implementation manner of the second consistency cost function, reference may be made to the specific implementation manner of the first consistency cost function described in the foregoing embodiments of the present disclosure, and details are not described herein again.

[0144] By adopting this method, based on the second consistency cost function, it is also possible to make the lateral offset between the specified trajectory of the second planned trajectory and the first planned trajectory less than or equal to a preset lateral offset threshold, thereby enhancing the consistency of the planned trajectories at the first moment and the second moment.

[0145] In some examples, Figure 3 In step S320 of the illustrated embodiment, at a second moment after the first moment, the method for generating a second planned trajectory of the movable device according to the position of the movable device and the first planned trajectory may include the following steps S321 to S323.

[0146] Step S321, generating a first partial trajectory line according to the first planned trajectory.

[0147] Wherein, the first partial trajectory line may also be referred to as a splicing trajectory. In some examples, a partial trajectory line may be intercepted from the first planned trajectory according to the position of the movable device at the second moment as the first partial trajectory line to ensure the time consistency between the first partial trajectory line and the first planned trajectory.

[0148] The trajectory length of the first part of the trajectory line can be determined according to the curvature parameter of the first planned trajectory and can be dynamically adjusted at different times.

[0149] For the specific implementation of the first part of the trajectory line, reference can be made to the description in the foregoing embodiments of the present disclosure, and details will not be elaborated here.

[0150] Step S322: Generate a second part of the trajectory line based on the first part of the trajectory line and the first planned trajectory.

[0151] Among them, the first part of the trajectory line can also be referred to as a strong planned trajectory. Exemplarily, the end point of the first part of the trajectory line (such as Figure 5 the second trajectory point shown) can be used as the planning starting point, and multiple candidate trajectories are planned and generated; the second part of the trajectory line is determined according to the multiple candidate trajectories.

[0152] For the specific implementation of the second part of the trajectory line, reference can be made to the description in the foregoing embodiments of the present disclosure, and details will not be elaborated here.

[0153] Step S323: Generate a second planned trajectory according to the first part of the trajectory line and the second part of the trajectory line.

[0154] Exemplarily, the first part of the trajectory line and the second part of the trajectory line can be merged to obtain the second planned trajectory.

[0155] By adopting this method, the second planned trajectory of the movable device is generated according to the position of the movable device and the first planned trajectory, which can enhance the consistency between the second planned trajectory generated at the second moment and the first planned trajectory generated at the first moment.

[0156] Figure 6 It is a schematic flowchart of a trajectory planning method provided by an embodiment of the present disclosure. As Figure 6 shown, the method may include the following steps S610 to step S620.

[0157] Step S610: Obtain the first planned trajectory planned by the movable device at the first moment.

[0158] Step S620: At a second moment after the first moment, generate a second planned trajectory of the movable device according to the position of the movable device and the first planned trajectory.

[0159] Among them, the second planned trajectory may include a specified trajectory that overlaps with the first planned trajectory in the longitudinal direction, and the lateral offset between the specified trajectory and the first planned trajectory is less than or equal to a preset lateral offset threshold, and the longitudinal direction is the driving direction of the movable device.

[0160] It should be noted that the specific implementation manners of the second planned trajectory and the first planned trajectory may refer to the descriptions in the foregoing embodiments of the present disclosure, and will not be elaborated herein.

[0161] In some examples, between the first moment and the second moment, control parameters of the movable device may be determined according to the first planned trajectory, and the movable device may be controlled to travel based on the control parameters. Among them, the control parameters include at least one of a target speed, a target acceleration, and a target heading angle for controlling the travel of the movable device; after the second moment and until a new planned trajectory is generated, the control parameters of the movable device may be determined or updated according to the second planned trajectory, and the movable device may be controlled to travel based on the control parameters.

[0162] By adopting this method, the consistency between the second planned trajectory generated at the second moment and the first planned trajectory generated at the first moment can be enhanced.

[0163] Figure 7 It is a schematic structural diagram of a device control device provided by an embodiment of the present disclosure. As Figure 7 shown, the device control device 1000 may include a memory 1010 and a processor 1020. The memory 1010 may be used to store computer instructions, and the processor 1020 may be used to call the computer instructions from the memory 1010 to execute all or part of the steps of any method in the foregoing embodiments of the present disclosure. Among them, the processor may be one or more, and the one or more processors may execute instructions alone or jointly. The memory may also be one or more, and the one or more memories may store the above computer instructions alone or jointly.

[0164] In some examples, the device control device may be Figure 1 a server and / or a movable device among them. In other examples, the device control device may also be any electronic device, such as a controller of the movable device or a user terminal.

[0165] An embodiment of the present disclosure also provides a movable device. The movable device may include a memory and a processor. The memory may be used to store computer instructions, and the processor may be used to call the computer instructions from the memory to execute all or part of the steps of any method in the foregoing embodiments of the present disclosure. Among them, the processor may be one or more, and the one or more processors may execute instructions alone or jointly. The memory may also be one or more, and the one or more memories may store the above computer instructions alone or jointly.

[0166] In some examples, the movable device can be a vehicle, which can be an electric vehicle, a hybrid vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle can be an autonomous vehicle or a non-autonomous vehicle. Exemplarily, the movable device provided in this embodiment can be Figure 1 or Figure 2 the movable device shown.

[0167] The embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the methods in the foregoing embodiments of the present disclosure. Optionally, the computer-readable storage medium can be a non-transitory storage medium, but is not limited thereto, and it can also be a transitory storage medium.

[0168] The embodiments of the present disclosure also provide a chip, which can include a processing unit, and the processing unit can be used to execute all or part of the steps of any one of the methods in the foregoing embodiments of the present disclosure. The chip can be in the form of an application-specific integrated circuit (ASIC), a system-on-chip (SOC), a field-programmable gate array (FPGA), etc., and this embodiment does not make any limitations thereto. Optionally, the chip can further include a storage unit, and the storage unit can be used to store computer instructions. The processing unit can be used to call the computer instructions from the storage unit to execute all or part of the steps of any one of the methods in the foregoing embodiments of the present disclosure.

[0169] The embodiments of the present disclosure also provide a computer program product, which can include a computer program. When the computer program is executed by a processor, it can implement any one of the methods in the foregoing embodiments of the present disclosure.

[0170] The present disclosure can be a system, a method, and / or a computer program product. The computer program product can include a computer-readable storage medium, on which computer-readable program instructions for causing a processor to implement any one of the methods in the foregoing embodiments of the present disclosure are uploaded.

[0171] A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example -- but not limited to -- an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punched card or raised structures in grooves having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not construed as being a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0172] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0173] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, which may include object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via an Internet service provider through the Internet). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0174] Aspects of the present disclosure are described herein with reference to the flowchart and / or block diagram of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart and / or block diagram, and the combinations of blocks in the flowchart and / or block diagram, can be implemented by computer - readable program instructions.

[0175] These computer - readable program instructions can be provided to a processor of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data - processing apparatus, result in an apparatus that implements the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner, so that the computer - readable medium storing the instructions includes a manufacture, which includes instructions for implementing various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0176] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0177] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions. It should be noted that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

[0178] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art in the field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, the practical application, or the improvement of the technology in the market, or to enable other ordinary skilled persons in the art in the field to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. A device control method, characterized in that, The method includes: Determining control parameters of the movable device according to a first planned trajectory of the movable device at a first moment; wherein, the control parameters include at least one of a target speed, a target acceleration, and a target heading angle for controlling the movement of the movable device; At a second moment after the first moment, generating a second planned trajectory of the movable device according to the position of the movable device and the first planned trajectory; wherein, the second planned trajectory at least includes a specified trajectory overlapping with the first planned trajectory in the longitudinal direction, and the lateral offset between the specified trajectory and the first planned trajectory is less than or equal to a preset lateral offset threshold, and the longitudinal direction is the moving direction of the movable device; Updating the control parameters of the movable device according to the second planned trajectory; Controlling the movement of the movable device based on the control parameters.

2. The method according to claim 1, wherein The specified trajectory of the second planned trajectory at least includes a first partial trajectory line, and the first partial trajectory line is a trajectory line on the first planned trajectory between a first trajectory point and a second trajectory point; the first trajectory point is a trajectory point on the first planned trajectory having the same longitudinal coordinate as the position of the movable device at the second moment, and the second trajectory point is a trajectory point determined according to the curvature parameter of the first planned trajectory.

3. The method according to claim 2, wherein The trajectory length of the first partial trajectory line is a second trajectory length, and the second trajectory length is a length determined according to a third trajectory length from the first trajectory point to a third trajectory point on the first planned trajectory, and the third trajectory point is the trajectory point with the largest curvature between the first trajectory point and the trajectory end point of the first planned trajectory.

4. The method according to claim 3, wherein When the sum of the third trajectory length and a specified length is less than or equal to a preset minimum inheritance length, the second trajectory length is the preset minimum inheritance length, and the specified length is a length by which the first partial trajectory line continues to extend after covering the third trajectory point; or, When the sum of the third trajectory length and the specified length is greater than the preset minimum inheritance length and less than or equal to a preset maximum inheritance length, the second trajectory length is equal to the sum of the third trajectory length and the specified length; or, When the sum of the third trajectory length and the specified length is greater than the preset maximum inheritance length, the second trajectory length is the preset maximum inheritance length.

5. The method according to any one of claims 2 to 4, characterized in that The specified trajectory of the second planned trajectory at least further includes a second partial trajectory line, and the second partial trajectory line is planned and generated starting from the second trajectory point, and the lateral offset between the second partial trajectory line and the first planned trajectory is less than or equal to the preset lateral offset threshold.

6. The method according to claim 5, wherein The cost function used when planning and generating the second part of the trajectory line at least includes a first consistency cost function, and the first consistency cost function is a cost function determined based on a first lateral offset and a second lateral offset between the second part of the trajectory line and the first planned trajectory. The first lateral offset is used to characterize the lateral offset between the end point of the second part of the trajectory line and the end point of the first planned trajectory, and the second lateral offset is used to characterize the lateral offset between each trajectory point of the second part of the trajectory line and the first planned trajectory.

7. The method according to claim 6, wherein The lateral offset between each trajectory point of the second part of the trajectory line and the first planned trajectory is determined by Gaussian convolution calculation.

8. The method according to claim 1, wherein The specified trajectory of the second planned trajectory is a trajectory planned and generated starting from a first trajectory point, and the first trajectory point is the trajectory point on the first planned trajectory with the same longitudinal coordinate as the position of the movable device at the second moment; the cost function used when planning and generating the specified trajectory at least includes a second consistency cost function, and the second consistency cost function is a cost function determined based on a third lateral offset and a fourth lateral offset between the specified trajectory and the first planned trajectory. The third lateral offset is used to characterize the lateral offset between the end point of the specified trajectory and the end point of the first planned trajectory, and the fourth lateral offset is used to characterize the lateral offset between each trajectory point of the specified trajectory and the first planned trajectory.

9. A device control device, characterized in that, It includes a memory and a processor. The memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program realizes the method according to any one of claims 1 to 8 when executed by a processor.

Images