Track planning method and device and storage medium

Abstract

The embodiment of the invention provides a trajectory planning method and device and a storage medium, and relates to the technical field of automatic driving. The trajectory planning method comprises the following steps: determining a search area for generating a local path according to environment information detected by a mobile device and a global navigation path planned for the mobile device; searching in the search area to generate a local path of the mobile device; according to the local path and the environment information, determining a target obstacle in the search area and a target label of the mobile device relative to the target obstacle; and according to the local path, the target obstacle and the target label, generating a planned trajectory of the mobile device. Wherein the target label is used for assisting in generating a planning track of the mobile equipment.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and more particularly, to a trajectory planning method, apparatus, and storage medium. Background Art

[0002] With the continuous development of autonomous driving technology, movable devices such as vehicles and robots can autonomously perform trajectory planning to achieve autonomous movement of the movable devices. Exemplarily, the movable device can collect information such as lane lines, perform trajectory planning based on traffic rules, and control the movable device to travel based on the planned trajectory. However, the trajectory planning in related technologies overly relies on lane line information on the road. For scenarios such as underground garages, campuses, and rural roads where there are no clear lane divisions and traffic rules and the road conditions are complex and changeable, the reliability of trajectory planning is severely affected. Summary of the Invention

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

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

[0005] Determining a search area for generating a local path according to the environmental information detected by the movable device and the global navigation path planned for the movable device;

[0006] Searching within the search area to generate a local path of the movable device;

[0007] Determining a target obstacle within the search area and a target label of the movable device relative to the target obstacle according to the local path and the environmental information; wherein the target label is used to assist in generating a planned trajectory of the movable device to avoid the movable device colliding with the target obstacle;

[0008] Generating a planned trajectory of the movable device according to the local path, the target obstacle, and the target label.

[0009] Optionally, the environmental information includes static obstacles of a preset type, the search area does not include static obstacles of the preset type, and the search boundary of the search area includes boundary points on both sides of the extending direction of the global navigation path, and the distance between the boundary points and the static obstacles of the preset type is greater than or equal to a preset minimum safety distance.

[0010] Optionally, searching for and generating a local path of the movable device within the search area includes: determining a search reference line within the search area; wherein, a search boundary of the search area includes a first side search boundary located on a specified driving side of the global navigation path and a second side search boundary located on a side opposite to the specified driving side of the global navigation path, and a first distance between the search reference line and the first side search boundary is less than a second distance between the search reference line and the second side search boundary; searching for and generating the local path within the search area according to the search reference line.

[0011] Optionally, searching for and generating a local path of the movable device within the search area includes: performing two searches within the search area to generate the local path; wherein, a first search of the two searches is performed based on static obstacles within the search area to obtain a specified position point, and a second search of the two searches is performed based on specified obstacles located between the current position of the movable device and the specified position point to obtain the local path, and the specified position point is the farthest position point that the movable device can drive through when the first search fails, or the search end position point when the first search is successful.

[0012] Optionally, the target label includes a lateral label and / or a longitudinal label; wherein:

[0013] The lateral label is used to indicate that when there is a position point with the same longitudinal coordinate as the target obstacle among the position points of the local path, the movable device bypasses the target obstacle from the left or right side based on the local path;

[0014] The longitudinal label is used to indicate the sequence relationship between the movable device and the target obstacle entering an overlapping area when there is an overlapping area between the local path and the predicted path of the target obstacle.

[0015] Optionally, the target label includes the longitudinal label, the environmental information includes dynamic obstacles detected by the movable device, and the target obstacle includes a longitudinal target obstacle; determining the target obstacle within the search area and the target label of the movable device relative to the target obstacle according to the local path and the environmental information includes:

[0016] Determining interaction information between the dynamic obstacle and the movable device according to the predicted path of the dynamic obstacle and the local path; wherein, the interaction information includes at least one of interaction position information, interaction time information, and interaction course angle information when the dynamic obstacle and the movable device respectively drive through the overlapping area.

[0017] Determine the interaction type between the movable device and the dynamic obstacle according to the interaction information; wherein, the interaction type includes crossing, cutting in, merging, leading or meeting;

[0018] Determine the longitudinal target obstacle from the dynamic obstacles according to the interaction information and the interaction type;

[0019] Determine the longitudinal label of the longitudinal target obstacle according to the interaction type.

[0020] Optionally, the determining the longitudinal label of the longitudinal target obstacle according to the interaction type includes: forming an obstacle node exploration set by arranging the obstacles with the interaction types of crossing, cutting in or merging in the longitudinal target obstacle from near to far according to the distance between the obstacle and the movable device, and each obstacle node corresponds to a longitudinal target obstacle; exploring the target label combinations of each obstacle node in the obstacle node exploration set to obtain the decision costs of different target label combinations; wherein, the target label combination includes the combination of setting the longitudinal labels of each obstacle node to go first or give way respectively, the go first indicates that the movable device passes through the overlapping area before the longitudinal target obstacle, and the give way indicates that the movable device passes through the overlapping area after the longitudinal target obstacle; determine the longitudinal labels of each longitudinal target obstacle according to the target label combination with the minimum decision cost.

[0021] Optionally, the interaction position information includes the first starting position where the movable device enters the overlapping area and the first ending position where the movable device leaves the overlapping area; the interaction time information includes the interaction starting time when the movable device enters the overlapping area and the interaction ending time when the movable device leaves the overlapping area; the interaction course angle information includes the interaction course angle difference, and the interaction course angle difference includes the interaction starting course angle difference and / or the interaction ending course angle difference. The interaction starting course angle difference is the absolute value of the difference between the course angle when the dynamic obstacle enters the overlapping area and the course angle when the movable device enters the overlapping area, and the interaction ending course angle difference is the absolute value of the difference between the course angle when the dynamic obstacle leaves the overlapping area and the course angle when the movable device leaves the overlapping area;

[0022] Determining the interaction type between the movable device and the dynamic obstacle according to the interaction information includes: when the distance between the first end position and the first starting position is less than a second preset distance threshold and the difference in interaction course angles is greater than or equal to a first preset course angle threshold, determining that the interaction type is an encounter; or, when the dynamic obstacle is in front of the movable device, the interaction start time is less than a first preset time threshold, and the difference in interaction course angles is less than a second preset course angle threshold, determining that the interaction type is leading; or, when the dynamic obstacle is behind the movable device, the left-right movement direction determined by the movable device based on the local path is in the direction of the dynamic obstacle, and the difference in interaction course angles is less than a second preset course angle threshold, determining that the interaction type is merging; or, when the dynamic obstacle is in front of the movable device, the distance between the first end position and the first starting position is greater than the device length of the movable device, and the difference in interaction course angles is less than a second preset course angle threshold, determining that the interaction type is cutting in; or, when the difference in interaction course angles is greater than or equal to the second preset course angle threshold and less than the first preset course angle threshold, determining that the interaction type is crossing.

[0023] According to a second aspect of the embodiments of the present disclosure, there is provided a trajectory planning 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.

[0024] 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.

[0025] Based on the trajectory planning method provided by the embodiments of the present disclosure, trajectory planning can be achieved without the assistance of lane lines, thereby improving the reliability and planning efficiency of trajectory planning under irregular roads.

[0026] 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

[0027] The drawings incorporated in the specification and constituting a part of the specification illustrate embodiments of the present disclosure, and together with the description are used to explain the principles of the present disclosure.

[0028] 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.

[0029] Figure 2 is a schematic diagram of a movable device provided according to Figure 1 the embodiment shown.

[0030] Figure 3 is a schematic flowchart of a trajectory planning method provided by an embodiment of the present disclosure.

[0031] Figure 4 is according to Figure 3 the embodiment shown, a schematic flowchart of a method for determining a search area.

[0032] Figure 5 is according to Figure 3 the embodiment shown, a schematic flowchart of a method for generating a local path.

[0033] Figure 6 is according to Figure 3 the embodiment shown, a schematic flowchart of a method for determining a target obstacle and a target label.

[0034] Figure 7 is according to Figure 3 the embodiment shown, a schematic flowchart of another method for determining a target obstacle and a target label.

[0035] Figure 8A is a schematic diagram of a search area provided by an embodiment of the present disclosure.

[0036] Figure 8B is a schematic diagram of multiple regions corresponding to a movable device provided by an embodiment of the present disclosure.

[0037] Figure 8C is a schematic diagram of the interaction position information between a movable device and a target obstacle provided by an embodiment of the present disclosure.

[0038] Figure 8D is a schematic diagram of the interaction type between a movable device and a target obstacle provided by an embodiment of the present disclosure.

[0039] Figure 8E is a schematic diagram of a decision tree of multiple longitudinal target obstacles provided by an embodiment of the present disclosure.

[0040] Figure 9 is a schematic flowchart of a device control method provided by an embodiment of the present disclosure.

[0041] Figure 10 is a schematic structural diagram of a trajectory planning device provided by an embodiment of the present disclosure. Detailed implementation manners

[0042] Various exemplary embodiments of the present disclosure will now 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.

[0043] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way a limitation on the present disclosure or its application or use.

[0044] 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.

[0045] In all examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

[0046] It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, further discussion thereof in subsequent drawings is not required.

[0047] 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 may be all of the elements.

[0048] 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 element is mentioned for the first time or is mentioned again, and do not have the meaning of limiting the quantity.

[0049] It should be noted that actions such as data collection, storage, use, processing, transmission, provision, disclosure, deletion, etc. involved in the present 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.

[0050] First, the application scenarios of the embodiments of the present disclosure will be described.

[0051] Figure 1 is a schematic diagram of an intelligent networked system 100 to which the method provided by the embodiments of the present disclosure can be applied. As Figure 1 shown, the intelligent networked system 100 may include: a mobile device 101, a server 102, and a user terminal 103.

[0052] 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 classification methods for autonomous driving levels are only for illustration, and the embodiments of the present disclosure do not limit the classification criteria and levels of autonomous driving.

[0053] 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.

[0054] In some examples, the user terminal 103 may be any form of electronic device that provides services for 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 on the movable device 101, or can also interact with the movable device or the server through the user terminal 103. For example, query the status and / or parameters of the movable device through the user terminal, or control the movable device to execute set tasks and / or modify configuration parameters, etc.; among them, 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 small program, etc., which is not limited herein.

[0055] In some examples, the above application program running on the user terminal can provide authentication or authorization services for users. Users who have successfully authenticated and been granted corresponding permissions can query and / or control the movable device within the granted permissions.

[0056] Between the mobile device 101, the server 102, and the user terminal 103, communication can be carried out through the communication links provided by the communication network 104. The communication network 104 may include one or more networks of any type. For example, the communication network 104 may include the Internet, local area network (LAN), wide area network (WAN), virtual private network (VPN), public switched telephone network (PSTN), satellite communication network, Wi-Fi, 2G, 3G, 4G, 5G, 6G, NB-IoT, eMTC, infrared, Bluetooth, NFC, etc. Networks that provide communication, or a combination of the above multiple networks. The communication networks between the mobile device 101 and the server 102, between the user terminal 103 and the server 102, and between the user terminal 103 and the mobile device 101 may be the same or different.

[0057] It should be noted that Figure 1 The structure of the intelligent networked system 100 shown in

[0058] Figure 2 is provided according to Figure 1 the schematic diagram of a mobile device 101 shown in the embodiment. As Figure 2 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.

[0059] 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.

[0060] In some examples, the computing platform 1012 may include a device with computing capabilities for processing the sensed 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, control, etc. 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.

[0061] In some examples, the computing platform of the movable device may execute computing tasks independently or communicate with the server to complete computing tasks. For example, the computing platform of the movable device may cooperate with the server to complete corresponding computing tasks.

[0062] The computing platform 1012 can be set in the mobile device 101. 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.

[0063] 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 moving task. The execution component 1013 can include, for example, a power component, a braking component, a transmission component, a steering component, etc.

[0064] 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.

[0065] The embodiments of the present disclosure can be applied to the trajectory planning scenario of mobile devices, especially the trajectory planning under non-regular roads. Currently, the algorithm frameworks related to trajectory planning in the field of autonomous driving, such as decision-making algorithms and planning algorithms, are mainly based on the premise of clear lanes and clear road rights, such as highways, urban expressways, urban ordinary roads, etc. The behaviors of the vehicle and other traffic participants are mostly within their own lanes or adjacent lanes in most cases, and trajectory planning can be carried out based on lane lines and traffic rules. For non-regular roads, such as underground garages, industrial parks, rural roads, etc., due to the lack of clear lane division and traffic rules, the degrees of freedom of traffic participants are higher, their motion modes are difficult to accurately predict, and the road conditions are complex and changeable, which brings great challenges to the decision-making and planning of autonomous vehicles.

[0066] In view of the problems of the related art, the embodiments of the present disclosure provide a new trajectory planning method to improve the reliability of trajectory planning under non-regular roads.

[0067] Figure 3 is a schematic flowchart of a trajectory planning method provided by the embodiments of the present disclosure. This trajectory planning method can be executed by Figure 1 the mobile device and / or server shown in. As Figure 3 shown, the trajectory planning method of this embodiment can include the following steps S310 to step S340.

[0068] Step S310: Determine a search area for generating a local path based on the environmental information detected by the movable device and the global navigation path planned for the movable device.

[0069] The environmental information may be the environmental information obtained by the movable device detecting the external environment. For example, the environmental information can be obtained by analyzing and processing the data collected by the sensors of the movable device, and the sensors may include visual sensors and / or radar sensors.

[0070] In some examples, the environmental information may include obstacles in the external environment, and the obstacles may include at least one of static obstacles and dynamic obstacles. The static obstacles may include at least one of obstacles such as pillars, walls, curbs, isolation piers, guardrails, signboards, cone barrels, traffic lights, etc. The dynamic obstacles may include at least one of obstacles such as moving vehicles, pedestrians, animals, etc. The obstacles can be used to determine the search area or to generate a local path.

[0071] In some examples, the environmental information may include static obstacles of a preset type, and the static obstacles of the preset type may include static obstacles such as pillars, walls, curbs, etc. The static obstacles of the preset type can be used to determine the search boundary of the search area.

[0072] In some examples, the global navigation path may be a global reference path between the current position of the movable device and the target position, and the target position may be the destination that the movable device expects to travel to. The global navigation path can be generated by the movable device or the server based on the navigation map. The global navigation path can also be referred to as a navigation reference line.

[0073] Step S320: Search within the search area to generate a local path for the movable device.

[0074] In some examples, the search area may include search boundaries, and the locally generated path can be located within the search boundaries and can avoid obstacles within the search area. The distance between the end point of the local path and the current position of the movable device can be a preset maximum search distance, which can be any preset value, such as 10 meters, 15 meters, or 20 meters, etc. The preset maximum search distance can also be the maximum distance that the movable device can travel within a preset duration determined according to the traveling speed and acceleration of the movable device. The preset duration can be any preset value, such as 5 seconds, 8 seconds, or 10 seconds, etc. It should be noted that the distance between two position points can be the Euclidean distance between the two position points, or the path distance obtained by projecting the two position points onto the global navigation path respectively, and this path distance can be used to represent the length of the actual drivable path. The local path can also be referred to as a rough path (Path).

[0075] In some examples, based on a preset search target, a local path that meets the search target can be searched for in the search area. Among them, the search target can include at least one of a path safety target, a path length target, a path smoothness target, a device motion parameter constraint target, and a search algorithm. For example, the search target can include searching for the shortest path from the current position to the target position; for another example, the search target can include searching for the shortest path that meets the safety requirements, and the safety requirements can be determined based on the probability of the movable device colliding with an obstacle; for another example, the search target can include searching for the shortest path that meets the smoothness requirements; for another example, the search target can include the preset path search algorithm used and the constraint conditions of the preset path search algorithm.

[0076] In some examples, the position points within the search area can be used as nodes to be searched, and a local path that meets the search target can be searched for among the nodes to be searched based on a preset path search algorithm. The preset path search algorithm can be a heuristic path search algorithm, such as the A* search algorithm, the Dijkstra algorithm, the BFS (Breadth-First Search) algorithm, etc.

[0077] Step S330, according to the local path and environmental information, determine the target obstacles within the search area and the target labels of the movable device relative to the target obstacles.

[0078] In some examples, the target label can be used to assist in generating the planned trajectory of the movable device.

[0079] In some examples, the planned trajectory generated with the assistance of the target label can avoid the collision between the movable device and the target obstacle. It should be noted that avoiding the collision between the movable device and the target obstacle can mean that there is no collision between the movable device and the target obstacle, or it can mean that the collision probability between the movable device and the target obstacle is less than or equal to a preset collision probability threshold, and the preset collision probability threshold can be any value set in advance, such as 0%, 0.1%, or 1%. It should be noted that the collision probability between the movable device and the target obstacle can be obtained by solving based on a pre-trained collision prediction model, or can be obtained by solving based on a prediction algorithm in related technologies.

[0080] In some examples, the target label can include a lateral label and / or a longitudinal label. The lateral and longitudinal directions in this embodiment can be determined based on the device coordinate system, which can be a coordinate system with the center of the movable device as the origin and the driving direction of the movable device as the longitudinal direction, and the driving direction can be the direction in which the head of the movable device faces. That is, the longitudinal direction is the driving direction of the movable device, and the lateral direction is the direction perpendicular to the driving direction. Among them, the meanings of front, back, left, and right can include: the front is the driving direction of the movable device, the back is the direction opposite to the driving direction, the left is the direction on the left hand side when looking from the driving direction; the right is the direction on the right hand side when looking from the driving direction.

[0081] The lateral label can be used to indicate that when there is a position point with the same longitudinal coordinate as the target obstacle among the position points on the local path, the movable device bypasses from the left or right side of the target obstacle based on the local path. The lateral label can also be called the lateral type, lateral decision label, or lateral decision type. Exemplarily, the lateral label of the movable device relative to the target obstacle can include bypassing from the left side, bypassing from the right side, or ignoring, where:

[0082] Bypassing from the left side can be used to represent that the movable device bypasses from the left side of the target obstacle. For example, when the longitudinal coordinates of the movable device and the target obstacle are the same (i.e., longitudinally parallel), the movable device is located on the left side of the target obstacle;

[0083] Bypassing from the right side can be used to represent that the movable device bypasses from the right side of the target obstacle. For example, when the longitudinal coordinates of the movable device and the target obstacle are the same (i.e., longitudinally parallel), the movable device is located on the right side of the target obstacle;

[0084] Ignoring can be used to represent that the target obstacle does not affect the lateral position movement of the movable device, so the position of the target obstacle does not need to be considered during lateral decision-making and planning.

[0085] The longitudinal label can be used to indicate the sequence relationship between the movable device and the target obstacle when there is an overlapping area between the local path and the predicted path of the target obstacle. The overlapping area can be a region obtained by expanding a specific distance in four directions, namely, forward, backward, left, and right, from the intersection center position point of the local path and the predicted path. The specific distance can be determined according to the device length of the movable device and the obstacle length of the target obstacle. For example, the specific distance can be greater than or equal to the maximum value of the device length and the obstacle length. The longitudinal label can also be referred to as the longitudinal type, longitudinal decision label, or longitudinal decision type. Exemplarily, the longitudinal label of the movable device relative to the target obstacle can include at least one of going first, yielding, following, or ignoring, where:

[0086] Going first can be used to represent that the movable device passes through the overlapping area before the target obstacle. For example, when the target obstacle and the movable device cross through an intersection, if it is determined that the movable device can pass through the intersection before the target obstacle, the longitudinal label of the movable device relative to the target obstacle is going first;

[0087] Yielding can be used to represent that the movable device passes through the overlapping area after the target obstacle. For example, when the target obstacle and the movable device cross through an intersection, if it is determined that the movable device can pass through the intersection after the target obstacle, the longitudinal label of the movable device relative to the target obstacle is yielding;

[0088] Following can be used to represent that the movable device continuously follows the target obstacle through the overlapping area. For example, if the target obstacle is in front of the movable device and the speed of the target obstacle is greater than the speed of the movable device, a following strategy can be adopted, that is, it is determined that the longitudinal label of the movable device relative to the target obstacle is following;

[0089] Ignoring can be used to represent that the target obstacle does not affect the longitudinal position movement of the movable device, and the position of this obstacle does not need to be considered during longitudinal decision-making and planning. For example, if there is no overlapping area between the predicted path of the target obstacle and the local path of the movable device, the longitudinal label of this target obstacle can be ignoring.

[0090] The target label of the same obstacle can include at least one of the lateral label and the longitudinal label. For example, some obstacles in the search area may only include the lateral label or the longitudinal label, and some obstacles may have both the lateral label and the longitudinal label.

[0091] Step S340, generate a planned trajectory of the movable device according to the local path, the target obstacle, and the target label.

[0092] It should be noted that the local path in this embodiment can be used to represent the route of the movable device in space. Based on this local path, it can be determined which position points the movable device passes through in space, but it is impossible to determine at what time these position points are passed through. The planned trajectory can represent the spatio-temporal actions of the movable device. Based on this planned trajectory, it can be determined at what time the movable device passes through a certain position point of the planned trajectory. The spatial position of the planned trajectory may be the same as or different from the local path. For example, the planned trajectory can be obtained by adjusting and correcting the local path.

[0093] In some examples, the movable device may include a decision-making module and a planning module. Among them, the decision-making module can execute the above steps S310 to S330, determine the local path, the target obstacle, and the target label based on the environmental information and the global navigation path, and output them to the planning module; the planning module can execute the above step S340, and generate the planned trajectory of the movable device according to the local path, the target obstacle, and the target label.

[0094] In some examples, the movable device may further include a Human Machine Interface (HMI). One or more of the above global navigation path, search area, target obstacle, target label, local path, and planned trajectory may be displayed through the human-machine interface so that the user can intuitively obtain the above information.

[0095] Using the above method, according to the environmental information detected by the movable device and the global navigation path planned for the movable device, determine the search area for generating the local path; search for and generate the local path of the movable device within the search area; according to the local path and the environmental information, determine the target obstacle within the search area and the target label of the movable device relative to the target obstacle; generate the planned trajectory of the movable device according to the local path, the target obstacle, and the target label. Among them, the target label is used to assist in generating the planned trajectory of the movable device. In this way, trajectory planning can be achieved without the assistance of lane lines, thereby improving the reliability and planning efficiency of trajectory planning under irregular roads.

[0096] To more clearly illustrate the trajectory planning method provided by the embodiments of the present disclosure, the following will introduce separately Figure 3 the specific implementation manners of each step in the illustrated embodiments.

[0097] In some examples, the search area determined in step S310 above may not include static obstacles of the above preset type. The search boundary of the search area includes boundary points on both sides of the extension direction of the global navigation path, and the distance between the boundary points and the static obstacles of the preset type is greater than or equal to a preset minimum safety distance. Wherein, the preset minimum safety distance can be any value set in advance, such as 0 meters, 0.5 meters or 1 meter. Optionally, the preset minimum safety distance can be greater than or equal to half of the width of the movable device. For example, if the width of the movable device is 1 meter, the preset minimum safety distance can be set to any value greater than or equal to 0.5 meters.

[0098] Exemplarily, the search boundary of the search area may include a first-side search boundary on the first side of the extension direction of the global navigation path and a second-side search boundary on the second side of the extension direction of the global navigation path. The first side and the second side can be the left side or the right side respectively.

[0099] Figure 4 is according to Figure 3 The flowchart of a method for determining a search area provided by the shown embodiment. As Figure 4 shown, the method for determining the search area in step S310 above may include the following steps S311 to S313.

[0100] Step S311, determine a set of navigation points according to the global navigation path.

[0101] Wherein, the distance between adjacent navigation points in the set of navigation points can be less than or equal to a first preset distance threshold. The first preset distance threshold can be a value set in advance. For example, the first preset distance threshold can be less than or equal to the length of the movable device, such as 3 meters or 5 meters.

[0102] In some examples, if the distance between two adjacent navigation points in the set of navigation points is greater than the first preset distance threshold, an interpolation densification operation can be performed on the set of navigation points to obtain a new set of navigation points to ensure that the distance between adjacent sets of navigation points is less than or equal to the first preset distance threshold.

[0103] Step S312, for each navigation point in the set of navigation points, perform position point detection respectively from the navigation point to the left and right sides perpendicular to the global navigation path until the detected position point coincides with a static obstacle of the preset type or reaches the maximum detection distance, and use the position point at the end of the detection as the boundary point corresponding to the navigation point.

[0104] Step S313, determine the search boundaries on both sides of the global navigation path according to the boundary points corresponding to each navigation point, and use the area within the search boundaries as the search area.

[0105] In some examples, the above environmental information may include static obstacles of a preset type, and the static obstacles of the preset type may include static obstacles such as columns, walls, and curbs. A static environment detector may be constructed based on the static obstacles of the preset type to detect whether each position point coincides with the static obstacles of the preset type. Optionally, the environmental information may further include a Grid Map, which divides the area around the movable device into small grids (cells), and the occupancy status of each cell may indicate whether there are static obstacles of the preset type at that position. Exemplarily, the occupancy rate of each cell may be used to represent the possibility that the cell is occupied by static obstacles of the preset type. For example, two thresholds may be set: an occupancy threshold (such as 0.65) and a free threshold (such as 0.25). If the occupancy rate of a cell is greater than the occupancy threshold, it is considered that there are static obstacles of the preset type in the cell; if it is less than the free threshold, it is considered that there are no static obstacles of the preset type.

[0106] In some examples, after determining the search area, the obstacles within the search area may be used as ROI (Region of Interest) obstacles, and the ROI obstacles may be used to generate a local path. The ROI obstacles may include static obstacles within the search area and dynamic obstacles of the predicted path within the search area.

[0107] In some examples, each navigation point may be moved along the left and right directions perpendicular to the global navigation path at a preset step size. Each time a position point is moved, it is placed in the static environment detector for detection. If a coincidence or collision is found, the detection in that direction is terminated. The position point at the end of the detection may be used as the boundary point corresponding to the navigation point. Based on the boundary points corresponding to each navigation point, a search boundary can be obtained, including a left boundary and a right boundary, and the area within the search boundary can be used as the search area. In an alternative implementation, if the distance between the detected position point and the navigation point is greater than or equal to the maximum detection distance, the detection in that direction may also be terminated. The maximum detection distance may be any preset value. For example, the maximum detection distance may be set according to the maximum detectable distance of the sensors of the movable device.

[0108] As Figure 8A shown, taking the parking lot scenario as an example, there are multiple parking spaces P in the parking lot, and there are also multiple static obstacles of the preset type such as multiple columns 85 and walls 86. The movable device 101 can determine the search boundaries on both sides of the global navigation path, including the left search boundary and the right search boundary, based on the detected environmental information and the global navigation path 81 (i.e., the line formed by connecting the red dots in the figure), and the area within the two search boundaries can be used as the search area.

[0109] In this way, without relying on lane lines, the search area can be determined according to the environmental information and the global navigation path, so as to search and generate the target path within the search area, avoid searching in invalid areas, and improve the efficiency and reliability of path generation.

[0110] In some examples of the present disclosure, an optional implementation manner of the above step S320 may include: performing two searches within the search area to generate a local path. Among them, the first search in the two searches may be based on static obstacles within the search area to obtain a specified position point, and the second search in the two searches may be based on specified obstacles located between the current position of the movable device and the specified position point to obtain a local path. The specified position point may be the farthest position point that the movable device can drive through when the first search fails, or the search end position point when the first search is successful. Optionally, the search algorithm used in the two searches may be a heuristic path search algorithm, such as the A* search algorithm, the Dijkstra algorithm, the BFS (Breadth-First Search) algorithm, etc.

[0111] Figure 5 is based on Figure 3 the flowchart of a method for generating a local path provided by the embodiment shown. As Figure 5 shown, the method for generating a local path in the above step S320 may include the following steps S321 to S322.

[0112] Step S321, determine the search reference line within the search area.

[0113] In some examples, the path of the global navigation path within the search area may be used as the search reference line.

[0114] In other examples, a search reference line biased towards the specified driving side may be determined according to the search boundary of the search area. The specified driving side may be the right side or the left side, which may be pre-specified according to the traffic rules of the country or region where the search area is located. For example, if the traffic rule is to drive on the right, the specified driving side may be the right side; if the traffic rule is to drive on the left, the specified driving side may be the left side.

[0115] Exemplarily, the search boundary of the search area includes a first-side search boundary located on the specified driving side of the global navigation path and a second-side search boundary located on the opposite side of the specified driving side of the global navigation path. The first distance between the search reference line and the first-side search boundary is less than the second distance between the search reference line and the second-side search boundary, that is, the search reference line is biased towards the specified driving side. Taking the specified driving side as the right side as an example, the first distance between the search reference line and the right boundary of the search area is less than the second distance between the search reference line and the right boundary of the search area, that is, the search reference line is biased towards the right boundary. Optionally, the distance between the search reference line and the first-side search boundary is greater than or equal to half of the width of the movable device to prevent the movable device from exceeding the boundary. A schematic diagram of a search reference line is as Figure 8A shown by the search reference line 82 on the right (i.e., the line formed by connecting the purple points in the figure).

[0116] In an alternative implementation, the search reference line may be parallel to the global navigation path. The first distance between the search reference line and the first-side search boundary may be the minimum or average value of the lateral distances between the boundary points with the same longitudinal coordinates on the first-side search boundary for each point on the search reference line. The second distance between the search reference line and the second-side search boundary may be the minimum or average value of the lateral distances between the boundary points with the same longitudinal coordinates on the second-side search boundary for each point on the search reference line.

[0117] In this way, based on the search reference line biased towards the specified driving side, the position of the local path generated by the search can be constrained, so that the local path is also biased towards the specified driving side. Thus, in the case of no lane lines, a local path that conforms to traffic rules can be generated, improving the driving safety and reliability of the movable device.

[0118] Step S322, search and generate a local path within the search area according to the search reference line.

[0119] In some examples, the implementation of step S322 may be: search within the search area according to the search reference line and all obstacles within the search area to generate the local path.

[0120] Exemplarily, a local path that meets the search target can be searched within the search area based on a preset path search algorithm. The preset path search algorithm may be a heuristic path search algorithm, such as the A* search algorithm, Dijkstra algorithm, BFS (Breadth-First Search) algorithm, etc.

[0121] In this way, a local path can be searched and generated based on the search reference line.

[0122] In some other examples, the implementation of step S322 may be as follows: Based on the search reference line and all obstacles within the search area, two searches are performed within the search area to generate the local path.

[0123] Exemplarily, step S322 may include the following steps S3221 to S3223.

[0124] Step S3221: Based on the search reference line and the static obstacles within the search area, a first search is performed within the search area to obtain a specified position point.

[0125] In some examples, the specified position point may be the farthest position point that the movable device can drive through when the first search fails. This specified position point may also be referred to as a blocked path point.

[0126] Exemplarily, a rough search method can be used to determine whether the road ahead is blocked and find the blocked path point. The preset maximum search time can be 10 ms. For example, all static obstacles within the search area can be added to the static environment detector, and a preset path search algorithm (such as the A* search algorithm or a similar heuristic algorithm) is used to explore forward N meters from the current position of the movable device. N can be a preset maximum search distance, for example, N can be greater than or equal to 15 meters. During the search process, multiple search nodes can be set within the search area, and each search node is judged by the static detector for collision (i.e., whether the position of the search node coincides with the position of the static obstacle). If there is a collision, it is directly pruned, and the collision information of each layer of search nodes is recorded. If a path of N meters cannot be searched within the preset maximum search time, it is determined that the first search fails, indicating that the road ahead is blocked. At this time, the layer where the generation of the next layer of search nodes fails for the first time can be determined, and this layer is the layer where the blocked path point is located. The search nodes of this layer can be used as the above-mentioned specified position point, that is, the blocked path point. This specified position point can be the farthest position point that the movable device can drive through.

[0127] In some other examples, the specified position point may be the search end position point when the first search is successful.

[0128] Step S3222: Determine the specified obstacle for the second search based on the specified position point.

[0129] Among them, the specified obstacle includes the static obstacles located between the current position of the movable device and the specified position point, and the dynamic obstacles located between the current position of the movable device and the specified position point at the search moment.

[0130] Exemplarily, the specified obstacle may be located within a specified area, which may be a subset or the entire set of the search area. For example, the four boundaries of the search area may be the first-side search boundary and the second-side search boundary of the search area, the third boundary perpendicular to the search reference line and passing through the current position of the movable device, and the fourth boundary perpendicular to the search reference line and passing through the specified position point. In this way, static obstacles within the specified area enclosed by the above four boundaries, as well as dynamic obstacles located in the specified area at the search moment, may constitute the specified obstacle.

[0131] Among them, the search moment may be determined according to the search layer, and the search moment of each layer may be different. For example, if there are n search layers, where n is greater than 1, and the planned travel time is m seconds, then the search moment interval of each layer is m / (n - 1) seconds. The search moment of the first layer is the 0th second, and the search moment of the xth layer is (x - 1)*m / (n - 1) seconds. Then, dynamic obstacles located between the current position of the movable device and the specified position point at the search moment of each layer may be determined as the specified obstacle based on the predicted path of the dynamic obstacle.

[0132] In some examples, obstacles after the specified position point are not used as the specified obstacle, that is, they are not used for the second search, that is, the distance between the specified obstacle and the movable device is less than or equal to the distance between the specified position point and the movable device.

[0133] Step S3223, according to the search reference line and the specified obstacle, perform a second search within the search area to obtain a local path.

[0134] The search algorithm used in the second search may be the same as or different from the search algorithm used in the first search.

[0135] In this way, it is possible to accurately determine whether a roadblock scenario occurs based on the search algorithm, and generate a reasonable path through the second search when a roadblock scenario occurs, rather than directly turning around in place, which improves the robustness of the path generated by the search in the roadblock scenario.

[0136] In some embodiments of the present disclosure, the target label may include a lateral label, the target obstacle may include a lateral target obstacle for lateral decision-making, and the environmental information may include static and dynamic obstacles detected by the movable device. As Figure 6 shown, the method for determining the lateral target obstacle and its lateral label in the above step S330 may include the following steps S331 to S332.

[0137] Step S331, determine the lateral target obstacle according to the relative position relationship between the obstacle position of the target obstacle and the current position of the movable device.

[0138] Exemplarily, the current position of the movable device may be the position where the tail of the movable device is located. As Figure 8B shown, taking the device body of the movable device ego as the center, a total of eight regions numbered 1-8 can be divided, respectively representing the regions in eight directions: the left front region 1, the front region 2, the right front region 3, the left region 4, the right region 5, the left rear region 6, the rear region 7, and the right rear region 8.

[0139] In some examples, the lateral target obstacle may be determined according to the obstacle type of the target obstacle and the relative position relationship with the current position of the movable device. For example, the lateral target obstacle may be an obstacle that satisfies the following condition 1 and condition 2:

[0140] Condition 1: The lateral target obstacle does not include obstacles after the specified position point, that is, the distance between the lateral target obstacle and the movable device is less than or equal to the distance between the specified position point and the movable device. The specified position point may be the farthest position point that the movable device can travel through when the first search fails, or the search end position point when the first search is successful;

[0141] Condition 2: If the lateral target obstacle is a static obstacle, the static obstacle is located in the left front region, the front region, the right front region, the left region or the right region of the movable device; or, if the lateral target obstacle is a dynamic obstacle, the dynamic obstacle is located in the left front region, the right front region, the left region or the right region of the movable device.

[0142] Step S332: Determine the lateral label of the movable device relative to the lateral target obstacle.

[0143] The lateral label of the movable device relative to the target obstacle may include detouring to the left or detouring to the right. The lateral label may be determined according to the relative position relationship between the target path of the movable device and the lateral target obstacle.

[0144] If the movable device detours to the left of the lateral target obstacle based on the target path, the lateral label is detouring to the left. For example, when the longitudinal coordinates of the movable device and the target obstacle are the same (i.e., longitudinally parallel), the movable device is located on the left side of the target obstacle, that is, detouring to the left;

[0145] If the movable device detours to the right of the lateral target obstacle based on the target path, the lateral label is detouring to the right. For example, when the longitudinal coordinates of the movable device and the target obstacle are the same (i.e., longitudinally parallel), the movable device is located on the right side of the target obstacle;

[0146] In some examples, the lateral label of the movable device relative to the target obstacle may further include "ignore". For other obstacles in the search area except the lateral target obstacle, their lateral labels can be set to "ignore". "Ignore" can be used to indicate that the target obstacle does not affect the lateral position movement of the movable device. Therefore, the position of the target obstacle does not need to be considered during lateral decision-making and planning.

[0147] In this way, the lateral target obstacle and its lateral label can be determined, so as to perform trajectory planning based on the lateral label during trajectory planning, generate a planned trajectory more efficiently, and avoid collisions with obstacles.

[0148] In some other embodiments of the present disclosure, the target label may include a longitudinal label, the target obstacle may include a longitudinal target obstacle for longitudinal decision-making, and the environmental information may include dynamic obstacles detected by the movable device. As Figure 7 shown, the method for determining the longitudinal target obstacle and its longitudinal label in step S330 above may include the following steps S335 to S338.

[0149] Step S335: Determine the interaction information between the dynamic obstacle and the movable device according to the predicted path and the local path of the dynamic obstacle.

[0150] In some examples, the dynamic obstacle may be all dynamic obstacles within the search area, such as all dynamic obstacles whose predicted paths overlap with the search area.

[0151] In some other examples, the dynamic obstacle may be a dynamic obstacle within the search area located between the current position of the movable device and the specified position point, that is, all or part of the predicted path of the dynamic obstacle is located between the current position of the movable device and the specified position point. Wherein, the specified position point may be the farthest position point that the movable device can travel through when the first search fails, or the search end position point when the first search is successful.

[0152] In some examples, the interaction information may include at least one of the interaction position information, interaction time information, and interaction heading angle information of the dynamic obstacle and the movable device passing through the overlapping area respectively.

[0153] Step S336: Determine the interaction type between the movable device and the dynamic obstacle according to the interaction information.

[0154] The interaction types may include crossing, cutting in, merging, leading, or meeting. Among them, the crossing type may characterize that the predicted path of a dynamic obstacle intersects the local path of the movable device at a right angle or an oblique angle, and there is an overlapping area at the intersection point, that is, there is a potential conflict point; the cutting-in type may characterize that the predicted path of the dynamic obstacle inserts laterally into the local path of the movable device to form an overlapping area; the merging type may characterize that the local path of the movable device inserts laterally into the predicted path of the dynamic obstacle to form an overlapping area; the leading type may characterize that the dynamic obstacle, as a leader, continuously stays in front of the movable device, and the movable device follows the dynamic obstacle (such as a vehicle ahead) to travel; the meeting type may characterize that the dynamic obstacle and the movable device move in opposite directions, and their trajectories separate after briefly overlapping in a limited space. Figure 8D It is a schematic diagram of an interaction type between a movable device and a target obstacle provided by an embodiment of the present disclosure. Figure 8D The interaction types between the movable device ego and the target obstacle obs shown in it include meeting 821, leading 822, crossing 823, merging 824, and cutting in 825.

[0155] Step S337, determine a longitudinal target obstacle from the dynamic obstacles according to the interaction information and the interaction type.

[0156] Step S338, determine the longitudinal label of the longitudinal target obstacle according to the interaction type.

[0157] Among them, the longitudinal label of the movable device relative to the longitudinal target obstacle may include at least one of going ahead, yielding, following, or ignoring.

[0158] In this way, the longitudinal label of the longitudinal target obstacle can be determined based on the interaction information and the interaction type.

[0159] In some examples, the above interaction position information may include a first starting position where the movable device travels into the overlapping area and a first ending position where it leaves the overlapping area. Optionally, the interaction position information may include a second starting position where the dynamic obstacle travels into the overlapping area and a second ending position where it leaves the overlapping area. Figure 8C It is a schematic diagram of the interaction position information between a movable device and a target obstacle provided by an embodiment of the present disclosure. As Figure 8C shown, there is an overlapping area where the target path of the movable device ego intersects the predicted path of the target obstacle obs. The figure shows the first starting position 811 where the movable device travels into the overlapping area, the first ending position 812 where it leaves the overlapping area, as well as the second starting position 813 where the dynamic obstacle travels into the overlapping area and the second ending position 814 where it leaves the overlapping area.

[0160] In some examples, the interaction time information may include an interaction start time when the movable device travels into the overlapping area and an interaction end time when it leaves the overlapping area.

[0161] In some examples, the interaction heading angle information may include an interaction heading angle difference, which may include an interaction start heading angle difference and / or an interaction end heading angle difference. The interaction start heading angle difference may be the absolute value of the difference between the heading angle of the dynamic obstacle when it travels into the overlapping area and the heading angle of the movable device when it travels into the overlapping area. The interaction end heading angle difference may be the absolute value of the difference between the heading angle of the dynamic obstacle when it leaves the overlapping area and the heading angle of the movable device when it leaves the overlapping area.

[0162] The above interaction information can characterize the interaction between the movable device and the dynamic obstacle.

[0163] In some examples, the method of determining the interaction type in step S336 above may include one or more of the following methods one to five.

[0164] Method one: When the distance between the first end position and the first start position is less than the second preset distance threshold and the interaction heading angle difference is greater than or equal to the first preset heading angle threshold, the interaction type can be determined as Meeting.

[0165] Method two: When the dynamic obstacle is in front of the movable device, the interaction start time is less than the first preset time threshold, and the interaction heading angle difference is less than the second preset heading angle threshold, the interaction type can be determined as Leading.

[0166] Method three: When the dynamic obstacle is behind the movable device, the left - right movement direction determined by the movable device based on the local path is towards the direction of the dynamic obstacle, and the interaction heading angle difference is less than the second preset heading angle threshold, the interaction type is determined as Merge.

[0167] Method four: When the dynamic obstacle is in front of the movable device, the distance between the first end position and the first start position is greater than the device length of the movable device, and the interaction heading angle difference is less than the second preset heading angle threshold, the interaction type is determined as CutIn.

[0168] Method five: When the interaction heading angle difference is greater than or equal to the second preset heading angle threshold and less than the first preset heading angle threshold, the interaction type is determined as Cross.

[0169] In this way, the interaction type between the movable device and the target obstacle can be determined.

[0170] In some examples, in the above step S337, all dynamic obstacles with interaction information and determined interaction types can be used as longitudinal target obstacles, that is, dynamic obstacles with non-empty interaction information are used as longitudinal target obstacles. Also, dynamic obstacles with overlapping regions between the predicted path and the local path can be used as longitudinal target obstacles.

[0171] In some other embodiments, in the above step S337, longitudinal target obstacles can be filtered out based on preset rules. Each interaction type can have its own independent preset rules. For example:

[0172] For a dynamic obstacle with an interaction type of leading, its preset rule can be the closest to the current position of the movable device. For example, if there are one or more dynamic obstacles with an interaction type of leading, select the dynamic obstacle closest to the current position of the movable device as the longitudinal target obstacle of the leading type. Further, after determining the longitudinal target obstacle of the leading type, the distance between the longitudinal target obstacle of the leading type and the movable device can be used as the specified distance threshold, and longitudinal target obstacles can be determined from other interaction type dynamic obstacles based on this specified distance threshold. For example, the above preset rule can include requiring that the distance between the first starting position and the current position of the movable device is less than or equal to this specified distance threshold, and the first starting position can be the starting position when the movable device enters the overlapping region with the predicted path of this longitudinal target obstacle.

[0173] For dynamic obstacles with interaction types of meeting or merging, its preset rules can include: the distance between the first starting position and the current position of the movable device is less than or equal to the above specified distance threshold, and it is the closest to the current position of the movable device. For example, if there are one or more dynamic obstacles with an interaction type of leading, select the dynamic obstacle closest to the current position of the movable device as the longitudinal target obstacle; if there are one or more dynamic obstacles with an interaction type of meeting, select the dynamic obstacle whose distance between the first starting position and the current position of the movable device is less than or equal to this specified distance threshold and is the closest to the current position of the movable device as the longitudinal target obstacle; if there are one or more dynamic obstacles with an interaction type of merging, select the dynamic obstacle whose distance between the first starting position and the current position of the movable device is less than or equal to this specified distance threshold and is the closest to the current position of the movable device as the longitudinal target obstacle.

[0174] For a dynamic obstacle with an interaction type of cutting in, its preset rules may include: the distance between the first starting position and the current position of the mobile device is less than or equal to the above-specified distance threshold, and the interaction start time is less than or equal to the second preset time threshold (such as 2 seconds, 5 seconds, or 10 seconds). For example, a dynamic obstacle with the distance between the first starting position and the current position of the mobile device being less than or equal to the specified distance threshold, the interaction start time being less than or equal to the second preset time threshold, and the interaction type being cutting in can be used as a longitudinal target obstacle.

[0175] For a dynamic obstacle with an interaction type of crossing, its preset rules may include that the distance between the first starting position and the current position of the mobile device is less than or equal to the above-specified distance threshold. For example, a dynamic obstacle with the distance between the first starting position and the current position of the mobile device being less than or equal to the specified distance threshold and the interaction type being crossing can be used as a longitudinal target obstacle. Optionally, the preset rules for the crossing-type dynamic obstacle may further include: the distance between the first starting position where the mobile device travels into the overlapping area and the current position of the mobile device is greater than or equal to the device length of the mobile device, or the distance between the first end position where the mobile device travels out of the overlapping area and the current position of the mobile device is greater than or equal to the device length of the mobile device.

[0176] In this way, multiple longitudinal target obstacles can be selected and determined from the dynamic obstacles based on the preset rules, and the longitudinal labels of the longitudinal target obstacles can be determined, without generating longitudinal labels for all the dynamic obstacles, thereby improving the efficiency of decision-making and planning. Exemplarily, there may be one leading-type longitudinal target obstacle, one merging-type longitudinal target obstacle, and one or more longitudinal target obstacles of other types respectively. It should be noted that not all types of longitudinal target obstacles exist, and some types of longitudinal target obstacles may also not exist. For example, the leading-type longitudinal target obstacle may not exist. At this time, the above-specified distance threshold may be a pre-set distance threshold, such as 2 meters, 5 meters, or 10 meters, and it may not be necessary to determine this specified distance threshold based on the leading-type longitudinal target obstacle.

[0177] In some examples, the method for determining the longitudinal label of the longitudinal target obstacle according to the interaction type in step S338 may include:

[0178] Step S3381: The obstacles with interaction types of crossing, cutting in, or merging in the longitudinal target obstacles are formed into an obstacle node exploration set in ascending order of the distance between the obstacles and the mobile device, and each obstacle node corresponds to a longitudinal target obstacle.

[0179] Step S3382: Explore the target label combinations of each obstacle node in the obstacle node exploration set to obtain the decision costs of different target label combinations.

[0180] Among them, the target label combination includes the combination of setting the longitudinal labels of each obstacle node to "go first" or "yield", where "go first" indicates that the movable device passes through the overlapping area before the longitudinal target obstacle, and "yield" indicates that the movable device passes through the overlapping area after the longitudinal target obstacle.

[0181] Exemplarily, the target label combination of each obstacle node can be explored based on a decision tree algorithm to obtain the decision cost of different target label combinations.

[0182] Step S3383: Determine the longitudinal labels of each longitudinal target obstacle according to the target label combination with the minimum decision cost.

[0183] Among them, the distance between the above obstacle and the movable device can be the distance between the first starting position corresponding to the longitudinal target obstacle and the current position of the movable device, and the first starting position can be the starting position when the movable device travels into the overlapping area with the predicted path of the longitudinal target obstacle.

[0184] Exemplarily, all longitudinal target obstacles with interaction types of crossing, cutting in or merging can be sorted according to the first starting position. A node is established for each longitudinal target obstacle and connected in the form of predecessors and successors. The longitudinal label of each stage can be set to two possible longitudinal labels of "go first" or "yield". If the total number of nodes is n, the maximum number of target label combinations can be 2 n combinations. The number of longitudinal target obstacles screened based on the preset rules in the above step S337 is small. For example, it generally does not exceed five. In this way, the number of target label combinations is limited, which can improve the exploration efficiency of the decision tree algorithm.

[0185] The above decision cost can include safety cost, efficiency cost, smoothness cost, etc. Exemplarily, the safety cost can represent the risk degree of collision between the movable device and the obstacle. The greater the collision risk, the greater the safety cost. If there is a collision between the movable device and the obstacle, the safety cost can be set to the maximum value; the efficiency cost can represent the driving efficiency of the movable device, and the driving efficiency can be determined based on the path length, driving time or energy consumption. For example, the longer the path length, the longer the driving time or the higher the energy consumption, the greater the efficiency cost; the smoothness cost can represent the smoothness of the driving path of the movable device, avoiding frequent steering or sudden acceleration / deceleration, and improving the riding comfort and control stability. The smoothness cost can be determined based on parameters such as path curvature and acceleration. For example, the greater the curvature or the greater the change in acceleration, the greater the smoothness cost. It should be noted that the decision cost in this embodiment can also be implemented based on the cost algorithm in related technologies.

[0186] In this way, based on the decision cost, the target label combination with the minimum decision cost can be obtained, and based on the target labels in the target label combination with the minimum decision cost, the longitudinal labels of each longitudinal target obstacle can be determined.

[0187] Furthermore, different target label combinations of the obstacle node exploration set can be evaluated based on multiple threads to obtain the target label combination with the minimum decision cost, thereby improving the decision-making efficiency.

[0188] Figure 8E It is a schematic diagram of a decision tree for multiple longitudinal target obstacles provided by an embodiment of the present disclosure. As Figure 8E shown, taking three sorted longitudinal target obstacles obs_1, obs_2, and obs_3 as an example, the longitudinal labels of the mobile device relative to each longitudinal target obstacle can both be two choices: pass or yield. Starting from obs_1, the longitudinal label of the mobile device relative to obs_1 can be pass or yield, that is, there are at least two possible paths to reach obs_2; the longitudinal label relative to obs_2 can also be pass or yield, then there are at least four possible paths to reach obs_3; after reaching obs_3, the longitudinal label relative to obs_3 can also be pass or yield. In this way, there are at least eight paths to bypass obs_3 and finally reach the planning focus Target, that is, there are eight different target label combinations.

[0189] In some examples, the method for determining the longitudinal label of the longitudinal target obstacle according to the interaction type in step S338 may further include: for the obstacle with the interaction type of piloting among the longitudinal target obstacles, setting the longitudinal label of the obstacle to follow; for the obstacles among the longitudinal target obstacles whose interaction types are not piloting, crossing, cutting in, and merging, setting the longitudinal label of the obstacle to ignore.

[0190] Optionally, the longitudinal labels of other obstacles in the search area except the longitudinal target obstacles can also be set to ignore. In this way, the longitudinal labels of each obstacle in the search area can be set to perform trajectory planning according to the longitudinal labels.

[0191] Figure 9 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 mobile device and / or server shown. As Figure 9 shown, the trajectory planning method of this embodiment may include:

[0192] Step S910, obtaining the planned trajectory corresponding to the mobile device.

[0193] Step S920, control the movable device to travel according to the planned trajectory.

[0194] Among them, the planned trajectory is generated in the following manner: Determine the search area for generating the local path according to the environmental information detected by the movable device and the global navigation path planned for the movable device; Search and generate the local path of the movable device within the search area; Determine the target obstacles within the search area and the target labels of the movable device relative to the target obstacles according to the local path and the environmental information, where the target labels are used to assist in generating the planned trajectory of the movable device; Generate the planned trajectory of the movable device according to the local path, the target obstacles, and the target labels.

[0195] The acquisition method of the planned trajectory in this embodiment can refer to the description in the foregoing embodiments of the present disclosure, and will not be elaborated here.

[0196] In this way, trajectory planning can be achieved without the assistance of lane lines, thereby improving the reliability and planning efficiency of trajectory planning under irregular roads, and improving the reliability of the movable device when traveling on irregular roads.

[0197] Figure 10 It is a schematic structural diagram of a trajectory planning device provided by an embodiment of the present disclosure. As Figure 10 shown, the trajectory planning 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 the 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.

[0198] In some examples, the trajectory planning device may be Figure 1 the server and / or the movable device in

[0199] An embodiment of the present disclosure also provides a movable device, which 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 the 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.

[0200] In some examples, the movable device may be a vehicle, which may be an electric vehicle, a hybrid vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle may be an autonomous vehicle or a non-autonomous vehicle. By way of example, the movable device provided in this embodiment may be Figure 1 or Figure 2 the movable device shown.

[0201] Embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, implements any one of the methods in the foregoing embodiments of the present disclosure. Optionally, the computer-readable storage medium may be a non-transitory storage medium, but is not limited thereto, and it may also be a transitory storage medium.

[0202] Embodiments of the present disclosure also provide a chip, which may include a processing unit, and the processing unit may 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 may 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 limitation thereto. Optionally, the chip may further include a storage unit, and the storage unit may be used to store computer instructions, and the processing unit may 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.

[0203] Embodiments of the present disclosure also provide a computer program product, which may include a computer program, and the computer program, when executed by a processor, may implement any one of the methods in the foregoing embodiments of the present disclosure.

[0204] The present disclosure may be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions thereon for causing a processor to implement any one of the methods in the foregoing embodiments of the present disclosure.

[0205] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. The computer-readable storage medium can 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 disk read-only memory (CD-ROM), a digital versatile disk (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 as 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.

[0206] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to respective computing / processing devices, or can be 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 can 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.

[0207] 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, alternatively, may be connected to an external computer (e.g., through the Internet using an Internet service provider). 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.

[0208] Aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer - readable program instructions.

[0209] 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, create a means for implementing 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 comprises 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.

[0210] 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.

[0211] 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.

[0212] 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 of the present technology 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 technical improvement of the technology in the market, or to enable other ordinary skilled persons in the field of the present technology to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. A trajectory planning method, characterized in that, The method includes: Determining a search area for generating a local path according to the environmental information detected by the movable device and the global navigation path planned for the movable device; Searching within the search area to generate the local path of the movable device; Determining a target obstacle within the search area and a target label of the movable device relative to the target obstacle according to the local path and the environmental information; wherein, the target label is used to assist in generating the planned trajectory of the movable device; Generating the planned trajectory of the movable device according to the local path, the target obstacle and the target label.

2. The method according to claim 1, wherein The environmental information includes static obstacles of a preset type, the search area does not include static obstacles of the preset type, the search boundary of the search area includes boundary points on both sides of the extension direction of the global navigation path, and the distance between the boundary points and the static obstacles of the preset type is greater than or equal to a preset minimum safety distance.

3. The method according to claim 1, wherein The searching within the search area to generate the local path of the movable device includes: Determining a search reference line within the search area; wherein, the search boundary of the search area includes a first-side search boundary on the designated driving side of the global navigation path and a second-side search boundary on the opposite side of the designated driving side of the global navigation path, and the first distance between the search reference line and the first-side search boundary is less than the second distance between the search reference line and the second-side search boundary; Searching within the search area according to the search reference line to generate the local path.

4. The method according to claim 1, wherein The searching within the search area to generate the local path of the movable device includes: Performing two searches within the search area to generate the local path; wherein, the first search in the two searches is based on static obstacles within the search area to search for a designated position point, and the second search in the two searches is based on a designated obstacle between the current position of the movable device and the designated position point to search for the local path, the designated position point is the farthest position point that the movable device can drive through when the first search fails, or the search end position point when the first search is successful.

5. The method according to any one of claims 1 to 4, characterized in that The target label includes a lateral label and / or a longitudinal label; wherein: The lateral label is used to indicate that when there is a position point with the same longitudinal coordinate as the target obstacle among the position points of the local path, the movable device bypasses from the left or right side of the target obstacle based on the local path; The longitudinal label is used to indicate the sequence relationship between the movable device and the target obstacle entering the overlapping area when there is an overlapping area between the local path and the predicted path of the target obstacle.

6. The method according to claim 5, characterized in that The target tag includes the longitudinal tag, the environmental information includes the dynamic obstacles detected by the mobile device, and the target obstacle includes the longitudinal target obstacle; the determining, according to the local path and the environmental information, the target obstacles within the search area and the target tag of the mobile device relative to the target obstacles includes: Determining interaction information between the dynamic obstacle and the mobile device according to the predicted path of the dynamic obstacle and the local path; wherein, the interaction information includes at least one of interaction position information, interaction time information, and interaction course angle information of the dynamic obstacle and the mobile device respectively passing through the overlapping area; Determining the interaction type between the mobile device and the dynamic obstacle according to the interaction information; wherein, the interaction type includes crossing, cutting in, merging, leading, or meeting; Determining the longitudinal target obstacle from the dynamic obstacles according to the interaction information and the interaction type; Determining the longitudinal tag of the longitudinal target obstacle according to the interaction type; 7. The method according to claim 6, wherein The determining the longitudinal tag of the longitudinal target obstacle according to the interaction type includes: Constructing an obstacle node exploration set from the obstacles with interaction types of crossing, cutting in, or merging in the longitudinal target obstacles in ascending order of the distance between the obstacles and the mobile device, and each obstacle node corresponds to a longitudinal target obstacle; Exploring the target tag combinations of each obstacle node in the obstacle node exploration set to obtain the decision costs of different target tag combinations; wherein, the target tag combination includes a combination of setting the longitudinal tags of each obstacle node to go first or give way, the go first indicates that the mobile device passes through the overlapping area before the longitudinal target obstacle, and the give way indicates that the mobile device passes through the overlapping area after the longitudinal target obstacle; Determining the longitudinal tags of each longitudinal target obstacle according to the target tag combination with the minimum decision cost; 8. The method according to claim 7, wherein The interaction position information includes the first starting position where the mobile device enters the overlapping area and the first ending position where the mobile device leaves the overlapping area; The interaction time information includes the interaction starting time when the mobile device enters the overlapping area and the interaction ending time when the mobile device leaves the overlapping area; The interaction course angle information includes an interaction course angle difference, and the interaction course angle difference includes an interaction starting course angle difference and / or an interaction ending course angle difference. The interaction starting course angle difference is the absolute value of the difference between the course angle when the dynamic obstacle enters the overlapping area and the course angle when the mobile device enters the overlapping area, and the interaction ending course angle difference is the absolute value of the difference between the course angle when the dynamic obstacle leaves the overlapping area and the course angle when the mobile device leaves the overlapping area; The determining the interaction type between the mobile device and the dynamic obstacle according to the interaction information includes: When the distance between the first end position and the first start position is less than a second preset distance threshold and the difference in the interactive heading angle is greater than or equal to a first preset heading angle threshold, determine that the interactive type is an encounter; or, When the dynamic obstacle is in front of the movable device, the interactive start time is less than a first preset time threshold, and the difference in the interactive heading angle is less than a second preset heading angle threshold, determine that the interactive type is leading; or, When the dynamic obstacle is behind the movable device, the left-right movement direction determined by the movable device based on the local path is in the direction towards the dynamic obstacle, and the difference in the interactive heading angle is less than a second preset heading angle threshold, determine that the interactive type is merging; or, When the dynamic obstacle is in front of the movable device, the distance between the first end position and the first start position is greater than the device length of the movable device, and the difference in the interactive heading angle is less than a second preset heading angle threshold, determine that the interactive type is cutting in; Or, When the difference in the interactive heading angle is greater than or equal to a second preset heading angle threshold and less than a first preset heading angle threshold, determine that the interactive type is crossing.

9. A trajectory planning device, characterized in that, Comprising a memory and a processor, the memory is used for storing computer instructions, and the processor is used for calling 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, Stored thereon is a computer program, which when executed by a processor implements: the method according to any one of claims 1 to 8.

Images