Driving method and vehicle

Abstract

The invention discloses a driving method and a vehicle, and relates to the technical field of auxiliary driving. The driving method comprises the following steps: if channel attribute information of a target traffic channel on which a target mobile device drives meets a preset condition, and a first object and a second object to be detoured exist in the driving direction of the target mobile device, determining a target detouring path; and based on the target bypass path, controlling the target moving device to run, so that the target moving device bypasses the first object and the second object in the running process in the target traffic channel, and avoiding collision with the first object and the second object, wherein the first object is in a static state, and the moving direction of the second object is different from that of the target moving device. The technical problem that the target moving device is poor in driving smoothness and safety in a complex traffic channel environment is solved.

Description

Technical Field

[0001] This application relates to the field of driver assistance technology, and more specifically, to a driving method and a vehicle. Background Technology

[0002] With the development of autonomous driving and assisted driving technologies, the driving control of mobile devices on well-maintained structured roads has become relatively mature. However, when mobile devices enter traffic channels with limited space and complex traffic participants, such as rural roads and narrow streets, achieving safe, continuous, and human-friendly autonomous driving remains a critical technical challenge. Existing driving control schemes are typically based on fixed lane keeping or simple obstacle avoidance logic. When faced with complex scenarios where multiple obstacles exist simultaneously, their decision-making logic is prone to contradictions between avoidance strategies for different obstacles, leading to inconsistent mobile device behavior. This reduces the smoothness, safety, and user experience of driving control.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a driving method and a vehicle to at least solve the technical problem of poor driving smoothness and safety of target mobile devices in complex traffic environments.

[0005] According to one aspect of the embodiments of this application, a driving method is provided, comprising: if the channel attribute information of the target traffic channel in which the target mobile device is traveling meets the preset conditions, and there is a first object and a second object to be detoured in the driving direction of the target mobile device, determining a target detour path; based on the target detour path, controlling the target mobile device to drive so that the target mobile device detours the first object and the second object during its travel in the target traffic channel, avoiding collision with the first object and the second object; wherein the first object is in a stationary state, the movement direction of the second object is different from the movement direction of the target mobile device, and the target detour path is determined based on the first position of the first object, the second position of the second object, and the movement information of the second object.

[0006] Optionally, the channel attribute information is used to describe the structural characteristics of the traffic channel, and the channel attribute information includes at least one of the following: channel size information, channel marking line type, and number of channel marking lines; preset conditions are used to determine whether the traffic channel belongs to a preset type based on the channel attribute information.

[0007] Optionally, the channel attribute information includes: channel size information, channel marking line type, and number of channel marking lines. The channel size information includes the channel width of the traffic channel. The preset conditions are determined based on the number of channel marking lines and the channel width. The preset conditions include: the number of channels is equal to 1 or 2, and the channel width is less than or equal to a first width threshold. The number of channels is determined based on the channel marking line type and the number of channel marking lines. Alternatively, the channel attribute information includes channel size information, which includes the channel width. The preset conditions are determined based on the channel width. The preset conditions include: the channel width is less than or equal to a second width threshold.

[0008] Optionally, the channel attribute information is obtained by performing preprocessing operations and feature analysis on the channel perception data corresponding to the target mobile device, provided that the accuracy conditions are met. The accuracy conditions are constructed based on the historical traffic channel classification data corresponding to the target mobile device, and the preprocessing operations include at least one of the following: removing abnormal line data and completing missing line data.

[0009] Optionally, the target detour path includes a detour offset path and a detour return path. The detour offset path is a path that controls the target mobile device to deviate from the original driving path based on the first position, the second position, the width of the target mobile device, and a first distance threshold. The detour return path is a path that controls the target mobile device to return to the original driving path when the return condition is met. The return condition is that there are no obstacles in the first orientation area corresponding to the first object, and the target mobile device has traveled to the second orientation area corresponding to the first object. The first orientation area is the area within a first preset distance in a first direction centered on the first position of the first object, and the first direction is the direction of the original driving path of the target mobile device. The second orientation area is the area within a second preset distance in a second direction centered on the first position of the first object, and the second direction is the direction of the current driving path of the target mobile device.

[0010] Optionally, the method for determining the detour offset path in the target detour path includes: determining the lateral offset direction based on the first position and the second position; determining the lateral offset amount based on the body width of the target mobile device and the first distance threshold; and determining the detour offset path according to the lateral offset direction and the lateral offset amount.

[0011] Optionally, the target detour path also includes a detour-maintaining path, which is between the detour offset path and the detour-righting path. The method further includes: if the second object is identified as being in motion and its speed is less than a first speed threshold based on the motion information of the second object, then the target mobile device is controlled to travel along the detour-maintaining path, wherein the detour-maintaining path is the section of road in which the target mobile device needs to maintain a lateral offset after completing the detour offset path.

[0012] Optionally, the method for determining the detour path in the target detour path includes: if the target mobile device is found to meet the return-to-center conditions, the target mobile device is controlled to return to the original driving path to determine the end of the detour path; if the target mobile device is found not to meet the return-to-center conditions, the detour path is updated, and the target mobile device is controlled to maintain the lateral offset and continue driving according to the updated detour path.

[0013] Optionally, the driving method further includes: when controlling the target mobile device to travel along the target detour path, if a collision risk between the target mobile device and the second object is identified based on the motion information of the second object, the driving speed of the target mobile device is reduced based on a second speed threshold, and / or, the target detour path of the target mobile device is updated based on the real-time distance and the real-time angle to obtain an updated target detour path; wherein, the updated target detour path is used to instruct the target mobile device to detour around the second object, the real-time distance is the real-time lateral distance between the target mobile device and the second object during driving, the real-time angle is the angle between the first tangent direction and the second tangent direction, the first tangent direction is the tangent direction corresponding to the real-time driving position of the target mobile device on the motion trajectory of the target mobile device, the second tangent direction is the tangent direction corresponding to the predicted position of the second object on the predicted trajectory of the second object, and during the process of the target mobile device traveling according to the updated target detour path, the real-time distance is greater than the second distance threshold, and the real-time angle is greater than a preset angle threshold.

[0014] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the driving method described above when it runs.

[0015] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the storage medium is located to perform any of the above-mentioned driving methods.

[0016] In this embodiment, if the channel attribute information of the target traffic channel traveled by the target mobile device meets preset conditions, and there are a first object and a second object to be detoured in the direction of travel of the target mobile device, a target detour path is determined. Based on the target detour path, the target mobile device is controlled to travel, so that the target mobile device detours around the first object and the second object during its travel within the target traffic channel, avoiding collisions with the first object and the second object. The first object is stationary, the movement direction of the second object is different from the movement direction of the target mobile device, and the target detour path is determined based on the first position of the first object, the second position of the second object, and the movement information of the second object. It is noteworthy that this embodiment generates the target detour path based on channel attribute information and the positions and movement information of stationary and moving objects, enabling the detours of the first and second objects to be planned and executed collaboratively within a unified path. This method enhances the overall integrity and coordination of path decision-making, helping the target mobile device to make more coherent and smooth driving movements in complex detour scenarios, thereby improving the smoothness and safety of the target mobile device's travel process.

[0017] As described above, the embodiments of this application achieve the goal of determining the detour path by fusing channel attribute information and information on the objects to be detoured, thereby enhancing the driving smoothness and safety of the target mobile device. This achieves the technical effect of improving the driving smoothness and safety of the target mobile device in complex traffic channel environments with multiple detour objects, and solves the technical problem of poor driving smoothness and safety of the target mobile device in complex traffic channel environments with multiple detour objects. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and provide related descriptions of those embodiments to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a hardware structure block diagram of an optional computing terminal for implementing a driving method according to an embodiment of this application;

[0020] Figure 2 This is a flowchart of a driving method according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of an optional method for determining the correction condition according to an embodiment of this application;

[0022] Figure 4 This is a schematic diagram of an optional detour path update method based on a second object according to an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of an optional vehicle assisted driving control process according to an embodiment of this application;

[0024] Figure 6 This is a schematic diagram of an optional detour prediction trajectory according to an embodiment of this application;

[0025] Figure 7 This is a structural block diagram of a vehicle driver assistance device according to an embodiment of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] According to an embodiment of this application, a method embodiment of a driving method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, steps shown or described may be executed in a different order than that shown here.

[0029] First, the operating environment of the above method embodiments will be described by way of example. Figure 1 This is a hardware structure block diagram of an optional computing terminal for implementing a driving method according to an embodiment of this application, such as... Figure 1As shown, the computing terminal 10 (e.g., a computer terminal, a mobile smart terminal, a vehicle terminal, or a cloud computing virtual terminal) may include: one or more processors 102, a memory 104 for storing data, and a transmission device 106 for implementing communication functions. Each processor 102 may include, but is not limited to, a processing component such as a microprocessor (MCU) or a field programmable gate array (FPGA).

[0030] The aforementioned computing terminal 10 may further include: a display device 110, an input / output device 108, a Universal Serial Bus (USB) port (which can be used as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure), and a camera (not shown in the figure). Those skilled in the art will understand that... Figure 1 The structure of the computing terminal 10 shown is for illustrative purposes only and does not impose strict limitations on the structure of the computing terminal 10 described above. For example, the computing terminal 10 may also include components that are larger than... Figure 1 The more or fewer components shown, or the computing terminal 10 may have the same Figure 1 The components are shown in different categories.

[0031] It should be noted that one or more processors 102 and / or other data processing circuits in the aforementioned computing terminal 10 may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be wholly or partially integrated into any other element in the vehicle terminal 10 (or mobile device).

[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the driving method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned driving method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the vehicle terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0033] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the vehicle terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0034] Under the above operating environment, the embodiments of this application provide the following: Figure 2 The driving method shown Figure 2 This is a flowchart of a driving method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following implementation steps S201 to S202.

[0035] Step S201: If the channel attribute information of the target traffic channel traveled by the target mobile device meets the preset conditions, and there is a first object and a second object to be detoured in the direction of travel of the target mobile device, a target detour path is determined. The first object is stationary, the direction of movement of the second object is different from the direction of movement of the target mobile device, and the target detour path is determined based on the first position of the first object, the second position of the second object, and the movement information of the second object.

[0036] The target mobile device in step S201 of this application can be a device or carrier that performs mobile functions based on environmental perception and decision-making instructions. For example, the target mobile device can include, but is not limited to, vehicles, ships, drones, and robots. Specifically, the aforementioned vehicles can be passenger cars, commercial vehicles, etc., equipped with an autonomous driving system. The aforementioned ships can be cargo ships or passenger ships equipped with an autonomous driving system. The aforementioned drones can be logistics drones or inspection drones equipped with an autonomous driving system. The aforementioned robots can be service robots or delivery robots equipped with an autonomous navigation system.

[0037] The aforementioned target mobile device can travel on the target traffic channel in the application scenario. The aforementioned target traffic channel can be the traffic channel where the target mobile device is currently located. The aforementioned traffic channel refers to a physical or virtual path that allows the target mobile device to move within it. For example, if the target mobile device is a vehicle, the aforementioned target traffic channel can be a road or lane; if the target mobile device is a ship, the aforementioned target traffic channel can be a waterway; if the target mobile device is a drone, the aforementioned target traffic channel can be a pre-planned flight path; if the target mobile device is a robot, the aforementioned target traffic channel can be an indoor corridor, a sidewalk, or a planned operating path.

[0038] It should be noted that the target traffic channels involved in the driving methods provided in this application may include multiple levels and / or multiple types of channels. For example, target traffic channels may include highways, urban arterial roads, urban streets, rural roads, alleyways, underground parking garage lanes, and unstructured driving areas. Different levels or types of target traffic channels may have different channel attribute information; for example, the width corresponding to highways is different from the width corresponding to rural roads, and the number of marking lines corresponding to urban arterial roads is different from the number of marking lines corresponding to alleyways.

[0039] The aforementioned channel attribute information of the target traffic corridor can be used to describe the structural and spatial characteristics of the target traffic corridor. Specifically, the channel attribute information may include, but is not limited to: corridor size information, corridor boundary identification information, and corridor topology information. In application scenarios, the aforementioned channel attribute information can be obtained through the sensing components of the target mobile device. For example, the aforementioned sensing components may include, but are not limited to: cameras, LiDAR, millimeter-wave radar, ultrasonic sensors, and communication modules for receiving high-precision map data.

[0040] The aforementioned preset conditions can be a set of one or more judgment rules set based on channel attribute information. These preset conditions are used to determine whether a target traffic channel belongs to a specific category based on the channel attribute information. While the target mobile device is traveling on the target traffic channel, its automatic driving system will continuously monitor whether the channel attribute information of the target traffic channel meets the preset conditions.

[0041] It should be noted that in one application scenario, specific "preset conditions" can be set to determine whether the target mobile device is currently in a specific type of traffic channel requiring special detour planning. For example, when the channel attribute information of the target traffic channel meets the preset conditions, it can be determined that the target traffic channel is a narrow road, a road with incomplete lane markings, or a road with limited passage space. These preset conditions enable the autonomous driving system to distinguish between regular traffic scenarios and specific scenarios that require more cautious trajectory planning.

[0042] The travel direction of the target mobile device can be its current direction of travel along its path on the target traffic channel. During the travel of the target mobile device, it can obtain information about at least one obstacle present in the aforementioned travel direction by communicating with the cloud. For example, the types of the aforementioned at least one obstacle may include, but are not limited to, static obstacles and dynamic obstacles.

[0043] The aforementioned first object is one of at least one type of obstacle. For example, the first object may be a stationary obstacle. During the movement of the target mobile device, the target mobile device detects a stationary obstacle in its direction of travel using sensing components, or it detects a stationary obstacle in its direction of travel based on information returned from the cloud, thereby determining that a first object exists in the direction of travel of the target mobile device. Specifically, when the target mobile device determines that a stationary obstacle is located in front of the target traffic lane where the target mobile device is currently located or constitutes a spatial encroachment on the target traffic lane, the target mobile device's autonomous driving system will determine that a first object exists in the aforementioned direction of travel.

[0044] It should be noted that the first object may include, but is not limited to, the following specific forms: vehicles temporarily parked beside the target traffic lane, vehicles stopped in the target traffic lane due to malfunction, static objects placed in the target traffic lane (such as construction signs, fallen goods), and pedestrians stationary in the target traffic lane. The common feature of the above different first objects is that the first object is stationary relative to the surface of the target traffic lane.

[0045] The aforementioned second object can be another obstacle among at least one type of obstacle. For example, the second object can be an obstacle in motion whose direction of movement is different from that of the target mobile device. During the movement of the target mobile device, the target mobile device detects a moving obstacle in its direction of travel through sensing components, or it detects a moving obstacle in its direction of travel based on information returned from the cloud, and the direction of movement of the obstacle is inconsistent with the direction of travel of the target mobile device (e.g., opposite or at an angle). Therefore, the autonomous driving system determines that a second object exists in the direction of travel of the target mobile device. Specifically, when the target mobile device determines that the moving obstacle is located in front of the target traffic lane where the target mobile device is currently located, or that the predicted trajectory of the moving obstacle will encroach on the target traffic lane, the autonomous driving system of the target mobile device determines that a second object exists in the aforementioned direction of travel.

[0046] It should be noted that the aforementioned second object may include, but is not limited to, the following specific forms: vehicles moving in the opposite direction to the target mobile device in the target traffic channel (i.e., oncoming vehicles), vehicles or pedestrians crossing laterally in the target traffic channel, and non-motorized vehicles or pedestrians traveling in the same direction to the side or rear of the target traffic channel but whose trajectories may encroach on the path of the target mobile device. The common characteristic of these different second objects is that the second object is in motion, and its direction of motion is different from that of the target mobile device.

[0047] While the target mobile device is traveling on the target traffic lane, its autonomous driving system will continuously monitor whether there are first and second objects to be detoured in the direction of travel. When the autonomous driving system detects the presence of first and second objects in the direction of travel, and the first and second objects are located within the area that the target mobile device needs to detour, the autonomous driving system determines that there are first and second objects to be detoured in the direction of travel.

[0048] For example, in one application scenario, the target mobile device is a vehicle, and the target traffic channel is a target lane. While the vehicle is traveling in the target lane, its autonomous driving system continuously monitors whether the "channel attribute information of the target traffic channel meets preset conditions" and whether the "first object and second object to be detoured exist in the direction of travel of the target mobile device" are true. When the vehicle's autonomous driving system detects that the channel attribute information of the target traffic channel meets the preset conditions and that the first object and second object to be detoured exist in the direction of travel of the target mobile device, the autonomous driving system will trigger the process of determining the target detour path.

[0049] It should be noted that the above conditions include an AND condition. In other words, if the condition that "the channel attribute information of the target traffic channel in which the target mobile device travels meets the preset conditions" is not met, or if the condition that "there is a first object and a second object to be detoured in the direction of travel of the target mobile device" is not met, the autonomous driving system will not trigger the process of determining the target detour path.

[0050] Optionally, in some embodiments, the channel attribute information is used to describe the structural characteristics of the traffic channel, and the channel attribute information includes at least one of the following: channel size information, channel marking line type, and number of channel marking lines; preset conditions are used to determine that the traffic channel belongs to a preset type based on the channel attribute information.

[0051] In the above optional embodiments, during the movement of the target mobile device, traffic channels with different structural features may have different requirements for detour path planning. For example, some traffic channels with certain structural features may have limited passage space or significant interference with oncoming traffic flow. Therefore, assessing whether the target traffic channel belongs to a preset type by measuring its structural features helps to initiate a suitable target detour path generation process for that traffic channel. The channel attribute information acquired by the target mobile device is used to describe the structural features of the traffic channel.

[0052] Specifically, the aforementioned channel attribute information may include channel size information. This channel size information may be a parameter describing the spatial dimensions of the traffic channel. For example, the aforementioned channel size information may include, but is not limited to, channel width. The aforementioned channel size information can be measured by the sensing components of the target mobile device, or read from high-precision map data pre-stored in the target mobile device.

[0053] The aforementioned lane attribute information may include lane marking line categories. These categories can be the types of marking lines used to delineate traffic areas within a lane. For example, these lane marking line categories may include, but are not limited to, lane lines and lane center lines. These lane marking line categories can be obtained by classifying perceived data using image recognition technology.

[0054] The aforementioned channel attribute information may include the number of channel marking lines. This number of channel marking lines may be the number of specific types of marking lines present in the traffic channel. Specific types of marking lines may include channel lines and channel center lines. Lane lines refer to marking lines on the surface of the traffic channel used to demarcate channel boundaries and separate traffic flows in the same or opposite directions. Channel center lines refer to the central reference axis inside the traffic channel used to indicate the direction of channel extension. Specifically, when the target moving device is a vehicle, the aforementioned channel lines are lane lines, and the aforementioned channel center lines are lane center lines. For example, the aforementioned number of channel marking lines may include, but is not limited to, the number of lane lines and the number of lane center lines. The aforementioned number of channel marking lines can be obtained by counting the identified marking lines.

[0055] In addition, the aforementioned channel attribute information may also include any two of the following: channel size information, channel label line type, and number of channel label lines. The aforementioned channel attribute information may also include channel size information, channel label line type, and number of channel label lines simultaneously.

[0056] The aforementioned preset type can be a traffic channel category that has special requirements for the detour path planning of the target mobile device. For example, according to some embodiments of this application, the preset type may include a narrow road category or an unstructured road category.

[0057] Based on the aforementioned channel attribute information, in the application scenario, the autonomous driving system of the target mobile device can determine whether the current traffic channel belongs to a preset type based on whether the channel attribute information meets the preset conditions. When the channel attribute information meets the preset conditions, the current traffic channel is determined to belong to the preset type, that is, the current traffic channel is determined to be the target traffic channel in step S201; when the channel attribute information does not meet the preset conditions, the current traffic channel is determined not to belong to the preset type, that is, the current traffic channel is determined not to be the target traffic channel in step S201.

[0058] It should be noted that determining that the traffic passage belongs to a preset type is one of the necessary conditions for triggering the target detour path generation process in step S201. By determining that the traffic passage belongs to a preset type, it is ensured that the target detour path determination method included in the driving method of this application embodiment is activated in target traffic passages whose structural features meet the preset conditions, thereby improving the applicability of the driving method of this application embodiment to specific types of target traffic passages.

[0059] Optionally, in some embodiments, the channel attribute information includes: channel size information, channel marking line type, and number of channel marking lines. The channel size information includes the channel width of the traffic channel. Preset conditions are determined based on the number of channel marking lines and the channel width. The preset conditions include: the number of channels is equal to 1 or 2, and the channel width is less than or equal to a first width threshold, wherein the number of channels is determined based on the channel marking line type and the number of channel marking lines; or, the channel attribute information includes channel size information, the channel size information includes the channel width, and the preset conditions are determined based on the channel width. The preset conditions include: the channel width is less than or equal to a second width threshold.

[0060] In the above optional embodiments, when the target mobile device detects a lane marking corresponding to the target traffic lane, the lane attribute information acquired by the target mobile device according to the aforementioned method can simultaneously include lane size information, lane marking type, and number of lane markings. Specifically, the lane size information includes the lane width of the traffic lane. For example, when the target mobile device is a vehicle, the lane width is the width of a single lane of the target lane currently occupied by the vehicle.

[0061] Based on the aforementioned channel attribute information, the preset conditions can be determined according to the number of channel identifier lines and the channel width. One possible preset condition includes: the number of channels is equal to 1 or 2, and the channel width is less than or equal to a first width threshold, wherein the number of channels is determined based on the channel identifier line category and the number of channel identifier lines.

[0062] At this point, according to step S201, in the process of determining whether the channel attribute information of the target traffic channel traveled by the target mobile device meets the preset conditions, firstly, the automatic driving system of the target mobile device determines the number of channels based on the channel marking line category and the number of channel marking lines in the channel attribute information; then, it determines whether the number of channels is equal to 1 or 2, and whether the channel width is less than or equal to a first width threshold. When the automatic driving system determines that the channel attribute information meets the condition of "the number of channels is equal to 1 or 2, and the channel width is less than or equal to the first width threshold", it determines that the channel attribute information of the target traffic channel meets the preset conditions, that is, it determines that the target traffic channel belongs to a preset type.

[0063] For example, in an exemplary application scenario, the target mobile device is a vehicle, and the traffic channel is the current lane the vehicle is traveling in. On one hand, the vehicle's autonomous driving system determines, through interaction with the cloud, that the current lane has a clear lane centerline, and thus determines the number of lanes to be 1. On the other hand, the autonomous driving system determines, through data collected by the vehicle's sensors, that the width of the current lane is 3.2 meters. A first width threshold is set to 3.8 meters. Based on this, the autonomous driving system, according to the judgment that "the number of lanes is equal to 1, and the lane width (3.2 meters) is less than the first width threshold (3.8 meters)," determines that the lane attribute information of the current lane meets the preset conditions, and the current lane is classified as a target lane of a preset type (e.g., a narrow single-lane road).

[0064] In the above optional embodiments, when the target mobile device does not detect the marking line corresponding to the target traffic lane, the lane attribute information acquired by the target mobile device according to the aforementioned method may include lane size information. Specifically, the lane size information includes lane width. For example, when the target mobile device is a vehicle, the lane width is the total width of the road currently being traveled by the vehicle.

[0065] Based on the channel attribute information described above, the preset conditions can be determined according to the channel width. One possible preset condition includes: the channel width is less than or equal to a second width threshold.

[0066] At this point, according to step S201, in the process of determining whether the channel attribute information of the target traffic channel traveled by the target mobile device meets the preset conditions, firstly, the automatic driving system of the target mobile device acquires or measures the current channel width. Then, the automatic driving system determines whether the channel width is less than or equal to a second width threshold. When the automatic driving system determines that "the channel width is less than or equal to the second width threshold", it determines that the channel attribute information of the target traffic channel meets the preset conditions, that is, it determines that the target traffic channel belongs to a preset type.

[0067] For example, in another exemplary application scenario, the target mobile device is a vehicle, and the traffic channel is a rural road currently being traveled by the vehicle. The vehicle's autonomous driving system, through sensor perception, confirms that the rural road does not have corresponding lane markings or lane center lines. In this case, the autonomous driving system determines, through sensor measurement or based on map data, that the total passable road width of the rural road is 4.5 meters. A second width threshold is set to 5.0 meters. Based on this, the autonomous driving system, according to the judgment that "the channel width (4.5 meters) is less than or equal to the second width threshold (5.0 meters)," determines that the channel attribute information of the rural road meets the preset conditions, and the rural road is identified as a target traffic channel of a preset type (e.g., an unstructured narrow road).

[0068] It should be noted that the two implementation methods described above provide different judgment logics. When the target mobile device detects a lane marking corresponding to the target traffic lane, the lane attribute information includes lane size information, lane marking type, and number of lane markings. In this case, the determination method of the preset conditions combines lane line information and width information, resulting in a more refined judgment, suitable for traffic scenarios where lane markings are relatively clear. When the target mobile device does not detect a lane marking corresponding to the target traffic lane, the lane attribute information includes lane size information. In this case, the determination method of the preset conditions depends on the road width, and the driving method based on these preset conditions is more robust, suitable for traffic scenarios where lane markings are lacking.

[0069] Optionally, in some embodiments, the channel attribute information is obtained by performing preprocessing operations and feature analysis on the channel sensing data when the channel sensing data corresponding to the target mobile device meets the accuracy conditions. The accuracy conditions are constructed based on the historical traffic channel classification data corresponding to the target mobile device, and the preprocessing operations include at least one of the following: removing abnormal line data and completing missing line data.

[0070] In the above optional embodiments, the channel perception data corresponding to the target mobile device can be a data set describing the original state and original characteristics of the target traffic channel. For example, the channel perception data may include, but is not limited to: road surface images captured by image sensors, point cloud data acquired by lidar, road network segments extracted from high-precision maps, and road information including location and simple descriptions actively reported by users. The above-mentioned channel perception data can be collected by the perception components equipped on the target mobile device, or it can be obtained through interaction between the target mobile device and its associated cloud service platform.

[0071] Because the aforementioned channel perception data may contain noise, errors, or missing information, the reliability of traffic channel attribute information obtained directly based on channel perception data analysis is low. Therefore, this embodiment verifies the accuracy of the channel perception data.

[0072] The aforementioned accuracy criteria refer to a set of rules used to determine whether the channel sensing data is sufficiently reliable for subsequent analysis. Specifically, these accuracy criteria are constructed based on historical traffic channel classification data corresponding to the target mobile device. This historical traffic channel classification data refers to a collection of correctly classified different traffic channels and their corresponding sensing data, which have been confirmed through preset methods (such as manual review, multi-source data cross-validation, etc.). This historical traffic channel classification data can be accumulated and stored through a cloud service platform.

[0073] For example, the historical traffic channel classification data may include, but is not limited to, confirmed samples of "single-lane roads," "two-lane roads," and "unstructured roads," and their corresponding channel sensing data (e.g., image features, geometric parameters, etc.). Correspondingly, the accuracy condition may include: the feature matching degree between the channel sensing data and a certain type of channel in the historical traffic channel classification data reaches a predetermined threshold (e.g., feature similarity is greater than or equal to a preset threshold).

[0074] In application scenarios, after a target mobile device acquires lane perception data, its autonomous driving system verifies the data based on accuracy criteria. For example, one exemplary accuracy criterion includes: when the key features described by the user-reported road information (such as the number and width of lane lines) match the results of manual verification or other reliable data sources to a degree equal to or exceeding a preset threshold, the user-reported road data is determined to meet the accuracy criteria. During the verification process based on these accuracy criteria, the autonomous driving system first extracts the perception features from the lane perception data. Then, it determines whether the match between these perception features and the verified data features in the historical traffic lane classification database reaches a preset threshold. When the autonomous driving system determines that the "match reaches the preset threshold," it concludes that "the lane perception data corresponding to the target mobile device meets the accuracy criteria."

[0075] Furthermore, once it is verified that the channel perception data corresponding to the target mobile device meets the accuracy requirements, the autonomous driving system of the target mobile device will perform preprocessing operations and feature analysis on the channel perception data to obtain channel attribute information.

[0076] The aforementioned preprocessing operations may include removing anomalous line data. Specifically, the autonomous driving system performs image filtering and / or rule-based spatial relationship analysis on the lane perception data to identify and remove false line segments (also known as "noisy lines") that are not part of the road structure itself and are caused by perceived noise or environmental interference. After removing anomalous line data, the lane perception data represents lane lines, lane boundaries, and other structural information more clearly and accurately.

[0077] The aforementioned preprocessing operations may also include completing missing line data. Specifically, the autonomous driving system uses prior knowledge of road structure or a line continuity model to predict and connect broken lines caused by occlusion, wear, or perception limitations in the lane perception data to restore complete and continuous lane lines or lane center lines (also known as "residual line completion"). After completing the missing line data, the continuity of lines in the lane perception data is enhanced, facilitating structured analysis.

[0078] Specifically, the above preprocessing operations may also include removing abnormal line data and filling in missing line data simultaneously. This application does not limit the specific execution order of removing abnormal line data and filling in missing line data.

[0079] The autonomous driving system of the aforementioned target mobile device performs feature analysis on the preprocessed lane perception data to obtain lane attribute information. Specifically, the feature analysis can be implemented by calling computer vision algorithms, geometric models, or pre-built classifiers. For example, in the feature analysis process, firstly, the autonomous driving system counts the number of lines in the lane perception data (e.g., perception images) that conform to the features of lane lines or lane center lines, thereby obtaining the number of lane identification lines in the lane attribute information; secondly, it measures the average or effective width between these lines, thereby obtaining the lane width in the lane attribute information.

[0080] It should be noted that the above optional implementation improves the reliability and consistency of the channel attribute information extracted from the channel perception data by introducing accuracy condition verification based on historical traffic channel classification data and preprocessing the channel perception data.

[0081] Based on step S201 and the various optional implementation methods described above, the driving method provided in this application, by first determining whether the channel attribute information of the target traffic channel meets preset conditions, can distinguish between specific types of traffic channels (such as narrow roads and unstructured roads) requiring the generation of target detour paths and conventional traffic channels. On this basis, combined with the identification of a first object and a second object in the driving direction, when both "the channel attribute information of the target traffic channel traveled by the target mobile device meets preset conditions" and "there are first and second objects to be detoured in the driving direction of the target mobile device" are simultaneously satisfied, the process of determining the target detour path is triggered. This method enables the autonomous driving system of the target mobile device to generate an adapted detour trajectory for a specific traffic scenario defined by preset conditions, improving the safety and smoothness of the target mobile device during detours. Simultaneously, by verifying and preprocessing the accuracy of channel perception data, the reliability of channel attribute information extraction is improved, thereby enhancing the accuracy of traffic channel type determination.

[0082] According to step S201, if the channel attribute information of the target traffic channel traveled by the target mobile device meets the preset conditions, and there is a first object and a second object to be detoured in the direction of travel of the target mobile device, a target detour path is determined. The target detour path is determined based on the first position of the first object, the second position of the second object, and the motion information of the second object. The implementation method of "determining the target detour path" is explained below.

[0083] The first position of the aforementioned first object can be its spatial coordinates within the coordinate system of the target traffic channel. This first position can be detected and located in real time by the sensing components of the target mobile device, or it can be provided to the target mobile device by the cloud service platform through communication between the target mobile device and the cloud service platform. The first position can be represented as the coordinates of the geometric center point of the first object, or as the coordinates of the center point of the bounding box of the area occupied by the first object. For example, when the first object is a temporarily parked vehicle, the first position is the center coordinates of the projection of the vehicle chassis onto the ground; as another example, when the first object is a stationary pedestrian, the first position is the center coordinates of the point of contact between the pedestrian and the ground.

[0084] The second position of the second object can be its real-time spatial coordinates within the coordinate system of the target traffic channel. This second position can be obtained through real-time tracking and positioning by the sensing components of the target mobile device, or it can be acquired from the data stream emitted by the second object via vehicle-to-everything (V2X) communication. The second position can be represented as the coordinates of the geometric center point of the second object. For example, when the second object is a vehicle traveling in the opposite direction, the second position is the location coordinates of that vehicle at the current moment; similarly, when the second object is a pedestrian crossing laterally, the second position is the location coordinates of that pedestrian at the current moment.

[0085] The motion information of the second object can be a set of parameters describing the motion state and trend of the second object. This motion information can be obtained by continuously observing and calculating the second object through the sensing components of the target moving device, or by receiving the state information broadcast by the second object. The motion information of the second object may include, but is not limited to: the real-time velocity of the second object, the direction of motion of the second object, the acceleration of the second object, and the predicted trajectory of the second object.

[0086] In the application scenario, when both the "channel attribute information of the target traffic channel in which the target mobile device travels meets the preset conditions" and the "there is a first object and a second object to be detoured in the direction of travel of the target mobile device" are met, the automatic driving system of the target mobile device will obtain the first position of the first object, the second position of the second object and the motion information of the second object, and further determine the target detour path based on the first position of the first object, the second position of the second object and the motion information of the second object.

[0087] Step S202: Based on the target detour path, control the target mobile device to drive so that the target mobile device detours around the first object and the second object during its travel within the target traffic channel, thereby avoiding collision with the first object and the second object.

[0088] The aforementioned target detour path refers to the driving path planned by the autonomous driving system for the target mobile device to avoid the first object and the second object. This target detour path guides the target mobile device to deviate from its original driving path while maintaining a safe distance, in order to avoid the first and second objects, and also guides the target mobile device back to its original driving path after avoiding the first and second objects. Specifically, the autonomous driving system of the target mobile device determines the target detour path based on the first position of the first object, the second position of the second object, and the motion information of the second object, with the principle of "ensuring that the target mobile device detours around the first and second objects during its travel within the target traffic channel, avoiding collisions with the first and second objects." After determining the target detour path, step S202 is executed.

[0089] Optionally, in some embodiments, the target detour path includes a detour offset path and a detour return path. The detour offset path is a path that controls the target mobile device to deviate from the original driving path based on the first position, the second position, the width of the target mobile device, and a first distance threshold. The detour return path is a path that controls the target mobile device to return to the original driving path when a return condition is met. The return condition is that there are no obstacles in the first orientation area corresponding to the first object, and the target mobile device has traveled to the second orientation area corresponding to the first object. The first orientation area is the area within a first preset distance in a first direction centered on the first position of the first object, where the first direction is the direction of the original driving path of the target mobile device. The second orientation area is the area within a second preset distance in a second direction centered on the first position of the first object, where the second direction is the direction of the current driving path of the target mobile device.

[0090] In the above optional embodiments, the target detour path may further include different path segments to accommodate different stages of the target mobile device's detour around the first object. Specifically, the target detour path includes a detour offset path and a detour return path.

[0091] The detour offset path in the aforementioned target detour path can be the path segment corresponding to the lateral offset performed by the target mobile device to avoid the first object. The automatic driving system of the target mobile device determines the detour offset path based on the first position of the first object, the width of the target mobile device, and a first distance threshold. This detour offset path is used to control the target mobile device to deviate from its original driving path.

[0092] For example, when the target moving device is a vehicle, the aforementioned first position is the positioning coordinate of the first object (such as a temporarily parked vehicle), the vehicle's body width is the vehicle's own width, and the first distance threshold is a preset safety threshold (e.g., 0.5 meters). The vehicle's autonomous driving system determines the detour direction based on the first position and the vehicle's real-time position, and calculates the required lateral offset based on the vehicle's own width and the first distance threshold, planning a path that causes the vehicle to deviate from the original lane centerline in the detour direction, thereby obtaining the detour offset path.

[0093] The detour-back path in the aforementioned target detour path can be the path segment corresponding to the lateral offset performed by the target mobile device after completing the detour in order to return to the original driving path. When the target mobile device's automatic driving system detects that the return-to-center conditions are met, it generates the detour-back path to control the target mobile device to return to the original driving path.

[0094] Specifically, during the movement of the target mobile device, its autonomous driving system continuously monitors whether the return-to-center condition is met. Specifically, first, the autonomous driving system acquires obstacle information within the first orientation area corresponding to the first object, and also acquires the real-time position of the target mobile device. Then, based on the obstacle information, the autonomous driving system determines whether there are obstacles within the first orientation area corresponding to the first object, and based on the real-time position of the target mobile device, determines whether the target mobile device has moved to the second orientation area corresponding to the first object. When the autonomous driving system determines that "there are no obstacles within the first orientation area corresponding to the first object, and the target mobile device has moved to the second orientation area corresponding to the first object," the return-to-center condition is considered met.

[0095] It should be noted that the first directional area is the area within a first preset distance in a first direction centered on the first position of the first object, and the first direction is the direction of the original travel path of the target mobile device. The second directional area is the area within a second preset distance in a second direction centered on the first position of the first object, and the second direction is the direction of the current travel path of the target mobile device.

[0096] Figure 3 This is a schematic diagram illustrating an optional method for determining the correction condition according to an embodiment of this application. Please refer to it. Figure 3The target moving device is the current vehicle. After traveling along the detour offset path, the current vehicle deviates from its original travel direction to its current travel direction. The first object is a stationary obstacle. Assume the road direction is Y-direction and the perpendicular direction of the road is X-direction. The position of the first orientation region in the X-direction is determined by the original travel direction; the position of the first orientation region in the Y-direction is determined by the first position of the first object; the size of the first orientation region in the Y-direction is determined by a first preset distance. The position of the second orientation region in the X-direction is determined by the current travel direction; the position of the second orientation region in the Y-direction is determined by the first position of the first object; the size of the second orientation region in the Y-direction is determined by a second preset distance.

[0097] like Figure 3 As shown, when the current vehicle determines that there are no obstacles in the first direction area and has already traveled to the second direction area, the return-to-center condition is met. Specifically, the current vehicle has traveled to the second direction area, meaning that the current vehicle has "passed" the first object in its direction of travel, and returning to the original direction of travel will not result in a collision with the first object, that is, it has "avoided" the first object. The absence of obstacles in the first direction area means that the current vehicle will not collide with any obstacles when returning to the original direction of travel, that is, while "avoiding" the first object, it also "avoids" obstacles "behind" the first object.

[0098] It should be noted that the first preset distance corresponding to the first azimuth area is used to ensure that the autonomous driving system has sufficient detection range for the area behind the first object that may affect the rerouting path when determining whether the target mobile device can safely return to center, thereby avoiding collisions caused by ignoring nearby obstacles. The second preset distance corresponding to the second azimuth area is used to ensure that the target mobile device has traveled to a safe position relative to the first object in both the lateral (i.e., X direction) and longitudinal (i.e., Y direction) directions, indicating that the target mobile device has sufficient safe space to perform the rerouting operation.

[0099] Optionally, in some embodiments, the method for determining the detour offset path in the target detour path includes: determining the lateral offset direction based on the first position and the second position; determining the lateral offset amount based on the body width of the target mobile device and the first distance threshold; and determining the detour offset path according to the lateral offset direction and the lateral offset amount.

[0100] The aforementioned lateral offset direction can be the direction in which the target mobile device performs a lateral offset to avoid the first object and the second direction. In the target traffic channel, "lateral" refers to a direction perpendicular to the target traffic channel. As the target mobile device travels along the direction of the target traffic channel, the aforementioned "lateral" refers to the direction perpendicular to the direction of travel, and this "lateral" is usually also perpendicular to the direction of the target traffic channel. For the target mobile device, the aforementioned lateral offset direction can be to the left or to the right.

[0101] In some application scenarios, during the process of determining the lateral offset direction based on a first position and a second position, the autonomous driving system of the target mobile device determines the relative lateral orientation of the first and second positions, and determines the lateral offset direction based on this relative orientation. Alternatively, the lateral offset direction can also be determined based on the first position, the second position, and the real-time position of the target mobile device. First, based on the first position and the real-time position, a first relative direction of the target mobile device relative to a first object is determined; and based on the second position and the real-time position, a second relative direction of the target mobile device relative to a second object is determined; then, based on the first and second relative directions, the lateral offset direction of the target mobile device is determined.

[0102] The aforementioned lateral offset can be the lateral distance that the target mobile device needs to deviate from its original travel path in the lateral offset direction when performing a detour. The first distance threshold is a preset safety threshold used to ensure a safe distance between the target mobile device and the detour object (i.e., the first object or the second object) after the target mobile device has deviated in the lateral offset direction according to the lateral offset amount.

[0103] The specific method for determining the lateral offset based on the target mobile device's body width and a first distance threshold is as follows: The autonomous driving system adds half the target mobile device's body width to the first distance threshold to determine the lateral offset. The lateral offset determined in this way ensures that after the target mobile device performs a lateral offset action in the lateral offset direction, the safe distance between the target mobile device's outer contour and the object it is bypassing is greater than or equal to the sum of half the body width and the first distance threshold.

[0104] For example, when the target moving device is a vehicle, assuming the vehicle's width is 1.8 meters and the first distance threshold is set to 0.5 meters, the lateral offset is calculated as (1.8 / 2) + 0.5 = 1.4 meters. This indicates that, in order to achieve a safe detour, the planned detour path for this vehicle needs to offset the vehicle's centerline by 1.4 meters in the lateral direction (e.g., to the left or right) relative to the original driving path.

[0105] The detour path is determined based on the lateral offset direction and lateral offset amount. Specifically, the autonomous driving system uses the current position and current direction of travel of the target mobile device as the detour starting point, constrains the path point position based on the lateral offset amount, and further combines the vehicle's kinematics and dynamics model to determine a detour path that smoothly transitions from the current position to the position after the lateral offset. The position after the lateral offset is determined by the current position, the lateral offset direction, and the lateral offset amount.

[0106] In the application scenario, the autonomous driving system of the target mobile device takes the lateral offset direction (e.g., to the right) and the lateral offset amount (e.g., 1.4 meters) as input to generate a detour offset path. When the target mobile device travels according to the detour offset path, in the longitudinal dimension, the target mobile device travels along the target traffic channel, and in the lateral dimension, the target mobile device will offset 1.4 meters to the right. Thus, the target mobile device completes the offset phase of detour driving.

[0107] Optionally, in some embodiments, the target detour path further includes a detour-maintaining path, which is between the detour offset path and the detour-righting path. The method further includes: if the second object is identified as being in motion and its speed is less than a first speed threshold based on the motion information of the second object, then the target mobile device is controlled to travel along the detour-maintaining path, wherein the detour-maintaining path is the section of road in which the target mobile device needs to maintain a lateral offset after completing the detour offset path.

[0108] In this application scenario, the second object corresponding to the target mobile device may be moving at a low speed. If the target mobile device immediately corrects its course after deviating from the deviating path, a collision risk may arise due to the second object remaining close. Therefore, during the control of the target mobile device, a deviating and correcting path can be introduced between the deviating and correcting paths. While traveling along the deviating and correcting path, the target mobile device maintains a lateral offset to observe and utilize changes in the motion state of the second object, ensuring safety during the deviating process.

[0109] The aforementioned detour-keeping path can be a segment of the path along which the target mobile device continues to travel in the current direction of travel to maintain the lateral offset from the obstacle after completing the detour offset path. Based on this detour-keeping path, the target mobile device maintains the executed lateral offset, and travels in the current direction of travel parallel to the original travel path.

[0110] In the application scenario, the autonomous driving system of the target mobile device determines the detour-keeping section based on the motion information of the second object. Specifically, the autonomous driving system of the target mobile device identifies whether the second object is in motion and obtains its speed. When the autonomous driving system detects that the second object is in motion and its speed is less than a first speed threshold, it determines that the target mobile device needs to perform detour-keeping, that is, the current travel path of the target mobile device belongs to the detour-keeping section.

[0111] Specifically, in determining the aforementioned detour and maintaining path, the target moving device is required to maintain the currently achieved lateral offset for a certain distance or for a certain duration. For example, when the condition "the second object is in motion and the speed of the second object is less than a first speed threshold" is met, the maintaining time of the detour and maintaining path segment is determined to be a pre-set fixed value (e.g., 2 seconds). The end of the detour and maintaining path is triggered by conditions such as meeting the return-to-center condition or the end of the maintaining time.

[0112] Optionally, in some embodiments, the method for determining the detour-back path in the target detour path includes: if it is identified that the target mobile device meets the back-alignment condition, the target mobile device is controlled to return to the original driving path to drive, so as to determine the end of the detour-back path; if it is identified that the target mobile device does not meet the back-alignment condition, the detour-maintaining path is updated, and the target mobile device is controlled to maintain the lateral offset and continue to drive according to the updated detour-maintaining path.

[0113] In the above optional implementation, if the target mobile device is found to meet the return-to-center condition, it indicates that there is no obstacle in the first directional area corresponding to the first object, and the target mobile device has traveled to the second directional area corresponding to the first object. At this time, the target mobile device is controlled to return to the original driving path. The process of returning to the original driving path is carried out according to the detour return-to-center path. After returning to the original driving path, it can be determined that the detour return-to-center path has ended.

[0114] If the target mobile device is found to have failed to meet the return-to-center condition, this indicates that there is an obstacle in the first orientation area corresponding to the first object, or that the target mobile device has not traveled to the second orientation area corresponding to the first object. In this case, the detour path is updated, for example, by extending the holding distance or the holding time. The target mobile device is then controlled to maintain its lateral offset according to the updated detour path.

[0115] In one application scenario, the target mobile device is a vehicle, and the first vehicle is a temporarily parked vehicle. The vehicle's compliance with the aforementioned return-to-center condition criteria is determined. For example, if no other vehicles or pedestrians are detected within the first directional area corresponding to the temporarily parked vehicle, and the vehicle has moved to or past the second directional area corresponding to the temporarily parked vehicle, the return-to-center condition for that vehicle is met. At this point, the vehicle begins to return to the original lane centerline along the detour return-to-center path. As another example, if another stationary vehicle is immediately behind the temporarily parked vehicle (i.e., an obstacle exists within the first directional area), the return-to-center condition for that vehicle is not met. In this case, the vehicle will update its detour path, extending the duration of the lateral offset, and continue traveling on the offset path.

[0116] The above optional implementation methods ensure that the target mobile device returns to the original driving path when the return-to-center conditions are met, otherwise it continues to drive while maintaining the lateral offset, thereby improving the safety and reliability of the detour process.

[0117] Optionally, in some embodiments, when controlling the target mobile device to travel along the target detour path, if a collision risk between the target mobile device and the second object is identified based on the motion information of the second object, the travel speed of the target mobile device is reduced based on a second speed threshold, and / or, the target detour path of the target mobile device is updated based on the real-time distance and the real-time angle to obtain an updated target detour path; wherein, the updated target detour path is used to instruct the target mobile device to detour around the second object, the real-time distance is the real-time lateral distance between the target mobile device and the second object during travel, the real-time angle is the angle between the first tangent direction and the second tangent direction, the first tangent direction is the tangent direction corresponding to the real-time travel position of the target mobile device on the trajectory of the target mobile device, and the second tangent direction is the tangent direction corresponding to the predicted position of the second object on the predicted trajectory of the second object, and during the process of the target mobile device traveling according to the updated target detour path, the real-time distance is greater than the second distance threshold, and the real-time angle is greater than a preset angle threshold.

[0118] In the process of identifying the collision risk between the target mobile device and the second object based on the motion information of the second object, the autonomous driving system of the target mobile device uses a prediction module to deduce the target mobile device's detour path as its future trajectory, and predicts the future trajectory of the second object as its predicted trajectory. The autonomous driving system compares the spatial relationship between the trajectory and the predicted trajectory at multiple future time steps. If at any moment the lateral distance between the two trajectories is less than a preset threshold, or the angle between the tangent directions of the two trajectories is too small, indicating a tendency to intersect, then a collision risk is identified.

[0119] When a collision risk is identified, the specific method for adjusting the speed of the target mobile device can be: reducing the speed of the target mobile device based on a second speed threshold. This second speed threshold can be a preset fixed value, lower than the current speed of the target mobile device. In application scenarios, when reducing the speed of the target mobile device based on the second speed threshold, the target mobile device can be controlled to reduce its speed to the second speed threshold within a specified time range.

[0120] When a collision risk is detected, the specific method for updating the target detour path of the target mobile device based on real-time distance and real-time angle can be as follows: First, calculate the real-time lateral distance between the target mobile device and the second object as the real-time distance, and calculate the angle between the tangent direction of the target mobile device's trajectory and the tangent direction of the predicted trajectory of the second object as the real-time angle. Next, determine whether the real-time distance is less than or equal to a second distance threshold, or whether the real-time angle is less than or equal to a preset angle threshold. If either the "real-time distance is less than or equal to the second distance threshold" or the "real-time angle is less than or equal to the preset angle threshold" is satisfied, then the lateral position or direction of the current target detour path is optimized and adjusted to generate a new trajectory as the updated target detour path. The optimization objective is to ensure that when the target mobile device travels along the new trajectory, the real-time distance between it and the second object remains greater than the second distance threshold, and the real-time angle remains greater than the preset angle threshold. Finally, control the target mobile device to switch to the updated target detour path.

[0121] Figure 4 This is a schematic diagram of a detour path update method based on a second object according to an embodiment of this application, as shown below. Figure 4 As shown, the current vehicle is controlled to travel according to a trajectory obtained through target detour path planning. Oncoming vehicles will travel according to a predicted trajectory, which is predicted based on the motion information of the oncoming vehicles. When the current vehicle's autonomous driving system identifies a collision risk with an oncoming vehicle, it will control the current vehicle to reduce its speed to a preset speed threshold. Then, it will predict the real-time distance and real-time angle, and update the current vehicle's target detour path based on the real-time distance and real-time angle.

[0122] Specifically, based on the motion trajectory, the first predicted position of the current vehicle at multiple future time steps is determined; based on the predicted trajectory, the second predicted position of the oncoming vehicle at multiple future time steps is determined; based on these multiple future time steps, the real-time lateral distance between the current vehicle and the oncoming vehicle at the current predicted time step is determined during the prediction process, thus obtaining the real-time distance. Similarly, during the prediction process, the angle between the tangent direction of the current vehicle's motion trajectory at the first predicted position and the tangent direction of the oncoming vehicle's predicted trajectory at the second predicted position is determined, thus obtaining the real-time angle.

[0123] During the process of updating the target detour path of the current vehicle based on the real-time distance and the real-time angle, the target detour path is adjusted according to the constraint that "the real-time distance is greater than the second distance threshold and the real-time angle is greater than the preset angle threshold" so that the current vehicle maintains the above-mentioned real-time distance greater than the second distance threshold and the real-time angle greater than the preset angle threshold while driving along the updated target detour path.

[0124] Based on steps S201 to S202 above, this embodiment generates a target detour path based on the channel attribute information of the target traffic channel, the first position of the first object, and the second position and motion information of the second object. This allows the detours for the first and second objects to be planned and executed collaboratively within a unified path. This method enhances the integrity and coordination of the target detour path determination process, helping the target mobile device to perform more coherent and smooth driving actions in complex traffic channel environments containing both the first and second objects, thereby improving the smoothness and safety of the target mobile device's driving process. Based on this, this embodiment achieves the goal of enhancing the driving smoothness and safety of the target mobile device by fusing channel attribute information and information about the objects to be detoured to determine the detour path. This achieves the technical effect of improving the driving smoothness and safety of the target mobile device in complex traffic channel environments containing both the first and second objects, thus solving the technical problem of poor driving smoothness and safety of the target mobile device in complex traffic channel environments containing both the first and second objects.

[0125] The following explanation, in conjunction with specific application scenarios, further clarifies the specific implementation of the driving method described in the embodiments of this application.

[0126] In one specific implementation of this application, the driving method relies on a system architecture that integrates cloud-based map data processing, in-vehicle environmental perception, trajectory prediction, and vehicle control. This system architecture aims to enhance the vehicle's intelligent assisted driving capabilities in complex road conditions. The overall operation of this driving method can be summarized as follows: vehicle-side perception data is reported to the cloud for intelligent processing and scene classification; the cloud sends the classification results and appropriate algorithm strategies back to the vehicle; and the vehicle ultimately executes prediction and fine-grained control based on the fused scene information.

[0127] First, the process of automatically identifying, classifying, and distributing strategies for small road scenarios using cloud-based maps is initiated. This process can be combined with... Figure 5 To understand this, we can refer to the vehicle's assisted driving control process shown. For example... Figure 5As shown, firstly, step S501 is executed, automatically extracting side road sign information based on the vehicle-side map data reported by the user. Specifically, the vehicle's driver assistance system uploads map data (such as lane line information and road width) perceived or extracted in real time by the vehicle's sensors to the cloud map system as user-reported data. After receiving the user-reported vehicle-side map data, the cloud service system initiates the automated side road sign information extraction process, that is, automatically extracting potential side road sign information based on the vehicle-side map data. Further, to avoid misjudgment, step S502 is executed to determine whether the current vehicle is on an urban expressway or at an intersection. Specifically, the system will determine whether the vehicle location corresponding to the currently reported vehicle-side map data is in an area that is clearly not a side road, such as an urban expressway or intersection. If the judgment result of S502 is "yes", then step S503 is executed to remove the side road sign information. Specifically, the automatically extracted side road sign information is removed from the vehicle-side map data. If the judgment result of S502 is "no", then step S504 is executed, enumerating the small road identification information into: single-lane small roads, two-lane small roads, and unstructured small roads based on the number of lane lines. Then, step S505 is executed, where the prediction module adapts different prediction algorithms based on different small road enumeration types and passes the prediction results to downstream consumers. Specifically, the prediction module in the cloud map system will match and activate different prediction algorithm models based on different small road enumeration types to form a scenario-specific prediction strategy as the prediction result. Further, the above-mentioned small road enumeration types and prediction results will be passed to downstream consumers, such as returning to the vehicle's assisted driving system. Then, step S506 is executed, where the control rule module, based on different small road enumeration types and combined with the prediction results, realizes algorithm adaptation in small road scenarios to improve the intelligent driving experience. After receiving the small road enumeration type and prediction results, the vehicle-side control rule module, based on the small road enumeration type and combined with the vehicle's real-time perception and data prediction results, executes the corresponding scenario-based control algorithm, thereby improving the experience of the intelligent assisted driving system in small road environments.

[0128] Secondly, at the vehicle-side execution level, the system generates predicted trajectories and controls the vehicle based on the aforementioned information. The prediction module generates safe and reasonable detour trajectories according to the path type adaptation algorithm. For example, in classic scenarios requiring detours around stationary obstacles and handling oncoming traffic, such as... Figure 6The diagram illustrates an optional detour prediction trajectory. The prediction module (or second prediction algorithm) generates a trajectory containing a clear "detour segment" and a "return segment." When the current vehicle detects a stationary vehicle (corresponding to the first object mentioned above) in the same target traffic lane ahead and an oncoming vehicle (corresponding to the second object mentioned above) in the opposite target traffic lane, in the "detour segment," the system controls the vehicle to deviate to one side (e.g., to the left) from the centerline of the original target traffic lane and bypass the stationary vehicle with a safe lateral distance (e.g., half the vehicle's width plus 0.5 meters). After successfully overtaking the stationary vehicle, the trajectory enters the "return segment," where the system guides the vehicle smoothly back to the centerline of the original target traffic lane. This "detour-return" trajectory design effectively avoids vehicles occupying the opposite target traffic lane for extended periods. The prediction algorithm ensures a safe path can be planned even in narrow road conditions by accurately calculating the angle and lateral distance between the detour trajectory and the predicted trajectory of the oncoming vehicle.

[0129] Finally, after receiving map attributes, scene type, and the trajectory output by the prediction module, the control algorithm module performs final path tracking and dynamic control. The control algorithm module translates the predicted trajectory into specific steering, acceleration, and braking commands. When planning the detour path, the control algorithm strictly applies safety rules; for example, for stationary obstacles or oncoming vehicles, the vehicle's lateral offset is calculated as half the vehicle width plus a fixed safety threshold (e.g., 0.5 meters). During the detour process, such as... Figure 6 The trajectory reflects the control algorithm's need to precisely manage the transition from the "detour segment" to the "return segment." Specifically, in the latter half of the detour, the control algorithm determines when to initiate the "return segment" based on continuous perception of the surrounding environment (such as whether there are other obstacles behind the detoured vehicle). If it is safe behind, the vehicle is controlled to return to the centerline of the target traffic channel in a timely and smooth manner; otherwise, it will remain in an off-center state, i.e., extend the "detour segment." When encountering oncoming vehicles during the detour, the control algorithm will adopt a strategy of moderate deceleration and path fine-tuning to ensure that the vehicle's trajectory meets the minimum lateral distance requirement (corresponding to the second distance threshold mentioned above) and trajectory angle requirement (corresponding to the preset angle threshold mentioned above) with the oncoming vehicle's trajectory, thereby achieving safe interaction.

[0130] In summary, the embodiments of this application achieve automatic identification and classification of side roads through collaborative processing from the cloud to the vehicle, and drive downstream prediction and control algorithms to perform deep scenario-based adaptation. Figure 5 It demonstrates the cloud-based decision-making process from data reporting to policy dissemination, and Figure 6 This demonstrates the refined trajectory generated by the vehicle in a specific interaction scenario. Combined, these two examples showcase a complete cooperative driving solution for narrow and complex road environments.

[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0132] It should be noted that, for the sake of simplicity, the technical solutions in the above method embodiments are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the order of actions in the described action combination, because according to this application, some of the above steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this application specification are preferred embodiments, and the actions and modules involved are not necessarily essential for implementing the technical solutions of this application.

[0133] According to embodiments of the present invention, a device embodiment for a driving device is also provided. This driving device is used to implement the above-described method embodiment and various optional implementations of the method embodiment. The technical content already described above will not be repeated in the device embodiment. It should be noted that, in the following related descriptions of the device embodiment, a "module" can be software, hardware, or a combination of software and hardware used to implement a specified function.

[0134] Figure 7 This is a structural block diagram of a driving device according to an embodiment of this application, such as... Figure 7 As shown, the driving device includes: a determining module 701, used to determine a target detour path if the channel attribute information of the target traffic channel in which the target mobile device is traveling meets preset conditions, and there is a first object and a second object to be detoured in the driving direction of the target mobile device; and a control module 702, used to control the target mobile device to drive based on the target detour path, so that the target mobile device detours around the first object and the second object during its travel in the target traffic channel, avoiding collisions with the first object and the second object; wherein the first object is in a stationary state, the movement direction of the second object is different from the movement direction of the target mobile device, and the target detour path is determined based on the first position of the first object, the second position of the second object, and the movement information of the second object.

[0135] In the aforementioned driving device, the channel attribute information is used to describe the structural characteristics of the traffic channel. The channel attribute information includes at least one of the following: channel size information, channel marking line type, and number of channel marking lines; preset conditions are used to determine whether the traffic channel belongs to a preset type based on the channel attribute information.

[0136] In the aforementioned driving device, the channel attribute information includes: channel size information, channel marking line type, and number of channel marking lines. The channel size information includes the channel width of the traffic channel. Preset conditions are determined based on the number of channel marking lines and the channel width. The preset conditions include: the number of channels is equal to 1 or 2, and the channel width is less than or equal to a first width threshold. The number of channels is determined based on the channel marking line type and the number of channel marking lines. Alternatively, the channel attribute information includes channel size information, which includes the channel width. The preset conditions are determined based on the channel width. The preset conditions include: the channel width is less than or equal to a second width threshold.

[0137] In the aforementioned driving device, the channel attribute information is obtained by performing preprocessing operations and feature analysis on the channel perception data corresponding to the target mobile device, provided that the accuracy conditions are met. The accuracy conditions are constructed based on the historical traffic channel classification data corresponding to the target mobile device. The preprocessing operations include at least one of the following: removing abnormal line data and completing missing line data.

[0138] In the aforementioned driving device, the target detour path includes a detour offset path and a detour return path. The detour offset path is a path that controls the target moving device to deviate from the original driving path based on the first position, the second position, the width of the target moving device, and a first distance threshold. The detour return path is a path that controls the target moving device to return to the original driving path when the return condition is met. The return condition is that there are no obstacles in the first orientation area corresponding to the first object, and the target moving device has traveled to the second orientation area corresponding to the first object. The first orientation area is the area within a first preset distance in a first direction centered on the first position of the first object, where the first direction is the direction of the original driving path of the target moving device. The second orientation area is the area within a second preset distance in a second direction centered on the first position of the first object, where the second direction is the direction of the current driving path of the target moving device.

[0139] Optionally, the determining module 701 is further configured to: determine the lateral offset direction based on the first position and the second position; determine the lateral offset amount based on the body width of the target mobile device and the first distance threshold; and determine the detour offset path according to the lateral offset direction and the lateral offset amount.

[0140] Optionally, the target detour path also includes a detour-maintaining path, which is located between the detour offset path and the detour-righting path. The control module 702 is further configured to: if the second object is identified as being in motion and its speed is less than a first speed threshold based on the motion information of the second object, then control the target mobile device to travel along the detour-maintaining path, wherein the detour-maintaining path is the section of road in which the target mobile device needs to maintain a lateral offset after completing the detour offset path.

[0141] Optionally, the determination module 701 is further configured to: if the target mobile device is found to meet the return-to-center conditions, control the target mobile device to return to the original driving path to determine the end of the detour return-to-center path; if the target mobile device is found not to meet the return-to-center conditions, update the detour maintenance path and control the target mobile device to maintain the lateral offset according to the updated detour maintenance path.

[0142] Optionally, the aforementioned driving device further includes an update module (not shown in the figure) which is also used to: when controlling the target mobile device to travel along the target detour path, if a collision risk between the target mobile device and the second object is identified based on the motion information of the second object, then the driving speed of the target mobile device is reduced based on a second speed threshold, and / or the target detour path of the target mobile device is updated based on the real-time distance and the real-time angle to obtain an updated target detour path; wherein, the updated target detour path is used to instruct the target mobile device to detour around the second object, the real-time distance is the real-time lateral distance between the target mobile device and the second object during driving, the real-time angle is the angle between the first tangent direction and the second tangent direction, the first tangent direction is the tangent direction corresponding to the real-time driving position of the target mobile device on the motion trajectory of the target mobile device, the second tangent direction is the tangent direction corresponding to the predicted position of the second object on the predicted trajectory of the second object, and during the process of the target mobile device traveling according to the updated target detour path, the real-time distance is greater than the second distance threshold, and the real-time angle is greater than a preset angle threshold.

[0143] It should be noted that the above-mentioned determining module 701 and control module 702 correspond to steps S201 to S202 in the method embodiment. The two modules are the same as the corresponding steps in terms of implementation instances and application scenarios, but are not limited to the content disclosed in the above method embodiment.

[0144] It should be noted that the modules mentioned in the above device embodiments can be implemented by software, hardware, or a combination of both. For example, when the modules are implemented by hardware, they can be placed in the same processor, or they can be placed in different processors in any combination. As another example, the modules can be hardware or software components stored in memory and processed by one or more processors; they can also run as part of a computing terminal.

[0145] According to an embodiment of the present invention, an embodiment of a vehicle assisted driving system is also provided. The vehicle assisted driving system includes: a current vehicle and a cloud service module, wherein the current vehicle is used to upload road structure data of a restricted road scenario to the cloud service module; the cloud service module is used to determine the road type based on road structure characteristics and return the road type to the current vehicle; the current vehicle is also used to perform motion prediction on a predicted object in the restricted road scenario based on the road type and road structure data to obtain prediction data, and to perform assisted driving calculations based on the road type and prediction data to generate control commands, the control commands being used to drive the current vehicle in the restricted road scenario.

[0146] According to an embodiment of the present invention, an embodiment of a vehicle is also provided. The vehicle includes: a memory storing an executable program; and a processor for running the program, wherein the program executes any of the above-described driving methods during runtime.

[0147] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to implement the above-described driving method.

[0148] Optionally, the aforementioned computer storage media may include, but are not limited to: hard disk drives (HDDs), solid state drives (SSDs), USB flash drives, optical discs, memory cards, cloud storage media, and network-attached storage (NAS) devices.

[0149] Optionally, the aforementioned computer-readable storage medium may be configured to store a computer program for performing the following steps: if the channel attribute information of the target traffic channel in which the target mobile device travels meets preset conditions, and there are a first object and a second object to be detoured in the direction of travel of the target mobile device, a target detour path is determined; based on the target detour path, the target mobile device is controlled to travel so that the target mobile device detours around the first object and the second object during its travel in the target traffic channel, avoiding collisions with the first object and the second object; wherein the first object is in a stationary state, the direction of movement of the second object is different from the direction of movement of the target mobile device, and the target detour path is determined based on the first position of the first object, the second position of the second object, and the movement information of the second object.

[0150] According to an embodiment of the present invention, a computer program product is also provided. This computer program product includes a computer program that, when executed by a processor, can implement the aforementioned driving method.

[0151] Optionally, the aforementioned computer program product can provide driving services based on the aforementioned driving method.

[0152] Optionally, in this embodiment, the computer program product described above may be a set of instructions and code pre-written according to the driving method described above. This computer program product can run on various computer platforms, including personal computers, servers, mobile devices, etc.

[0153] Optionally, in this embodiment, the instructions and code corresponding to the computer program product are used to implement the following method steps: uploading the road structure data of the restricted road scene where the current vehicle is located to the cloud service module; receiving the road type returned by the cloud service module, wherein the road type is determined by the cloud service module based on the road structure characteristics; performing motion prediction on the predicted object in the restricted road scene based on the road type and road structure data to obtain prediction data; performing assisted driving calculations based on the road type and prediction data to generate control instructions, wherein the control instructions are used to drive the current vehicle to drive in the restricted road scene.

[0154] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of multiple modules can be a logical functional division, and in actual implementation in application scenarios, there can be any other possible division methods. Furthermore, multiple modules (or units or components within modules) can be combined with each other and integrated into another system. For example, some features in the method embodiments described above can be ignored or skipped during execution.

[0156] It should be noted that in the above embodiments, the modules, components, or units described as separate parts can be physically separated or physically integrated. The components shown as modules or units can be physical modules or units, or virtual modules or units. That is, multiple modules or units can be located in the same position or distributed across multiple positions or spaces. In application scenarios, depending on the actual needs of the scenario, some or all of the multiple modules or units can be selected to implement the technical solutions of the embodiments of this application, thereby achieving the corresponding technical objectives.

[0157] Specifically, for integrated functional modules or units, if they are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0158] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of driving, characterized in that, include: If the channel attribute information of the target traffic channel in which the target mobile device travels meets the preset conditions, and there are a first object and a second object to be detoured in the direction of travel of the target mobile device, the target detour path is determined. Based on the target detour path, the target mobile device is controlled to travel so that the target mobile device detours around the first object and the second object during its travel within the target traffic channel, thereby avoiding collisions with the first object and the second object; The first object is stationary, the second object moves in a direction different from the target moving device, and the target detour path is determined based on the first position of the first object, the second position of the second object, and the motion information of the second object.

2. The driving method according to claim 1, characterized in that, The channel attribute information is used to describe the structural features of the traffic channel, and the channel attribute information includes at least one of the following: channel size information, channel marking line type, and number of channel marking lines; the preset conditions are used to determine that the traffic channel belongs to a preset type based on the channel attribute information.

3. The driving method according to claim 2, characterized in that, The channel attribute information includes: channel size information, channel marking line type, and number of channel marking lines. The channel size information includes the channel width of the traffic channel. The preset conditions are determined based on the number of channel marking lines and the channel width. The preset conditions include: the number of channels is equal to 1 or 2, and the channel width is less than or equal to a first width threshold. The number of channels is determined based on the channel marking line type and the number of channel marking lines. or, The channel attribute information includes channel size information, the channel size information includes channel width, and the preset condition is determined based on the channel width. The preset condition includes: the channel width is less than or equal to a second width threshold.

4. The driving method according to claim 2 or 3, characterized in that, The channel attribute information is obtained by performing preprocessing operations and feature analysis on the channel perception data corresponding to the target mobile device, under the condition that the accuracy condition is met. The accuracy condition is constructed based on the historical traffic channel classification data corresponding to the target mobile device. The preprocessing operation includes at least one of the following: removing abnormal line data and completing missing line data.

5. The driving method according to claim 1, characterized in that, The target detour path includes a detour offset path and a detour return path, wherein, The detour offset path is a path that controls the target mobile device to deviate from the original driving path based on the first position, the second position, the body width of the target mobile device, and the first distance threshold. The detour-back-to-center path is the path by which the target mobile device returns to the original driving path when the back-to-center condition is met. The back-to-center condition is that there are no obstacles in the first orientation area corresponding to the first object, and the target mobile device has traveled to the second orientation area corresponding to the first object. The first orientation area is the area within a first preset distance in a first direction centered on the first position of the first object, and the first direction is the direction of the original driving path of the target mobile device. The second orientation area is the area within a second preset distance in a second direction centered on the first position of the first object, and the second direction is the direction of the current driving path of the target mobile device.

6. The driving method according to claim 5, characterized in that, The method for determining the detour offset path in the target detour path includes: Based on the first position and the second position, determine the lateral offset direction; The lateral offset is determined based on the body width of the target mobile device and a first distance threshold. The detour offset path is determined based on the lateral offset direction and the lateral offset amount.

7. The driving method according to claim 6, characterized in that, The target detour path further includes a detour-maintaining path, which lies between the detour offset path and the detour-righting path. The method further includes: If the motion information of the second object indicates that the second object is in motion and its speed is less than a first speed threshold, then the target mobile device is controlled to travel along the detour-maintaining path, wherein the detour-maintaining path is the section of road in which the target mobile device needs to maintain the lateral offset after completing the detour-off path.

8. The driving method according to claim 7, characterized in that, The method for determining the detour path in the target detour path includes: If the target mobile device is identified as meeting the return-to-center condition, the target mobile device is controlled to return to the original driving path to determine the end of the detour return-to-center path; If it is detected that the target mobile device does not meet the return-to-center condition, the detour-keeping path is updated, and the target mobile device is controlled to continue traveling according to the updated detour-keeping path to maintain the lateral offset.

9. The driving method according to claim 1, characterized in that, The method further includes: When controlling the target mobile device to travel along the target detour path, if a collision risk between the target mobile device and the second object is identified based on the motion information of the second object, the travel speed of the target mobile device is reduced based on a second speed threshold, and / or the target detour path of the target mobile device is updated based on the real-time distance and the real-time angle to obtain the updated target detour path; The updated target detour path is used to instruct the target mobile device to detour around the second object. The real-time distance is the real-time lateral distance between the target mobile device and the second object during travel. The real-time angle is the angle between the first tangent direction and the second tangent direction. The first tangent direction is the tangent direction corresponding to the real-time travel position of the target mobile device on the trajectory of the target mobile device. The second tangent direction is the tangent direction corresponding to the predicted position of the second object on the predicted trajectory of the second object. During the process of the target mobile device traveling according to the updated target detour path, the real-time distance is greater than the second distance threshold, and the real-time angle is greater than the preset angle threshold.

10. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 9.

Images