Control method and apparatus, and vehicle

Abstract

A control method and apparatus, and a vehicle. The method comprises: acquiring environmental perception information, wherein the environmental perception information indicates a position change of at least one vehicle located within a first range of a first vehicle; on the basis of the environmental perception information, determining whether each of the at least one vehicle is in a reversing state or has a reversing intent; and when a second vehicle among the at least one vehicle is in the reversing state or has the reversing intent, controlling a prompting apparatus of the first vehicle to give a prompt regarding first information, and / or controlling the first vehicle to avoid the second vehicle, wherein the first information indicates at least one of the following: the position of the second vehicle, avoiding the second vehicle, or the reason for avoiding the second vehicle. The present solution can be applied to the field of intelligent driving of intelligent vehicles. Other vehicles in a reversing state or having a reversing intent can be selected, and a prompt can be given to the other vehicles and / or the other vehicles can be avoided in advance, such that the safety of an ego vehicle can be improved, and the losses of drivers and passengers in the ego vehicle and the other vehicles can be reduced.

Description

Control methods, devices and vehicles

[0001] This application claims priority to Chinese Patent Application No. 202510291391.5, filed on March 10, 2025, entitled "Control Method, Apparatus and Vehicle", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving, and more specifically, to a control method, device, and vehicle. Background Technology

[0003] As vehicles become increasingly intelligent and automated, more and more vehicles are equipped with intelligent driving systems to reduce driving stress and improve driving safety. Intelligent driving systems can plan the vehicle's path based on both static and dynamic obstacles on the road, controlling the vehicle to avoid these obstacles.

[0004] In certain scenarios, balancing vehicle safety and driving efficiency remains a pressing issue that needs to be addressed. Summary of the Invention

[0005] This application provides a control method, device, and vehicle that can screen out other vehicles that are in reversing or have the intention to reverse, and provide warnings and / or avoid them in advance, thereby improving the safety of the vehicle and reducing the risk of injury to the occupants of both the vehicle and other vehicles.

[0006] Firstly, a control method is provided that can be executed by a vehicle, for example, by the vehicle's computing platform, or by a chip or circuitry used in the vehicle. The following explanation uses the execution of this method by a first vehicle as an example.

[0007] The method includes: acquiring environmental perception information, the environmental perception information indicating position changes of at least one vehicle located within a first range of a first vehicle; determining, based on the environmental perception information, whether each of the at least one vehicle is in a reversing state or has an intention to reverse; when a second vehicle among the at least one vehicles is in a reversing state or has an intention to reverse, controlling a prompting device of the first vehicle to prompt first information, and / or controlling the first vehicle to avoid the second vehicle; wherein the first information indicates at least one of the following: the position of the second vehicle, avoiding the second vehicle, or the reason for avoiding the second vehicle.

[0008] In the above technical solution, the vehicle can detect the reversing state of other vehicles or predict the reversing intention of other vehicles based on the environmental information perceived by the vehicle. This allows the vehicle to provide warnings and / or avoid collisions with other vehicles that are reversing or have the intention to reverse, thereby reducing the probability of collisions between the vehicle and other vehicles that are reversing or have the intention to reverse. This improves the safety of the vehicle and reduces the risk of injury to the occupants of both the vehicle and other vehicles.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the prompting device includes a projection device, the first information includes projection information, the projection device is used to project the projection information onto the outside of the first vehicle, and the projection information indicates the position of the second vehicle, and / or the reversing status or reversing intention of the second vehicle.

[0010] In the above technical solution, by projecting relevant information about other vehicles that are reversing or have the intention to reverse (hereinafter, the vehicle being detected as reversing) outwards, it helps other road users around the vehicle to notice the reversing vehicle and thus avoid it, thereby reducing the probability of other road users colliding with the reversing vehicle and reducing the probability of road traffic congestion caused by such collisions.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the projection information includes a first part of information and / or a second part of information, wherein the first part of information is projected at a first location, which is associated with the locations of other traffic participants within a first range besides the second vehicle; and the second part of information is projected at the area where the second vehicle is located.

[0012] In the above technical solution, relevant projection information can be projected onto the location of the reversing vehicle and the locations of other traffic participants, which can improve the visibility of the projection information, thereby increasing the probability that other traffic participants will notice the projection information and ensuring the prompting effect of the projection information.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, when a third vehicle in at least one of the vehicles is also in a reversing state or has the intention to reverse, the first information further indicates at least one of the following: the position of the third vehicle, the reason for avoiding the third vehicle, or the reason for avoiding the third vehicle.

[0014] In some implementations, when a third vehicle is also in a reversing state or has the intention to reverse, the method also includes controlling the first vehicle to avoid the third vehicle.

[0015] In the above technical solution, when there are multiple reversing vehicles, prompts are given to all of them, enabling the driver of the vehicle and / or the driver of the vehicle to plan a more suitable driving route, thereby improving the traffic efficiency of the vehicle.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the first information includes a first set of elements and a second set of elements, the first set of elements being used to indicate information related to the second vehicle and the second set of elements being used to indicate information related to the third vehicle; when the risk of reversing caused by the second vehicle is higher than the risk of reversing caused by the third vehicle, the warning level corresponding to the first set of elements is higher than the warning level corresponding to the second set of elements.

[0017] In some implementations, the method may also include: first planning the driving path of the first vehicle based on the reversing vehicle with a higher risk of reversing.

[0018] In some implementations, the reversing risk of a vehicle can be determined based on information such as the speed of the reversing vehicle and the distance between the reversing vehicle and the vehicle being driven. For example, the higher the speed of the reversing vehicle, the higher its reversing risk; similarly, the closer the distance between the reversing vehicle and the vehicle being driven, the higher the reversing risk.

[0019] In the above technical solution, when there are multiple reversing vehicles and the risk levels caused by each reversing vehicle are different, providing information indicating different reversing risks to users in the vehicle's cabin and / or other traffic participants outside the vehicle's cabin helps to reduce the identification and cognitive costs of reversing risks for relevant personnel.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, determining whether each of the at least one vehicles is in a reversing state or has the intention to reverse, based on environmental perception information, includes: determining the speed direction and front-facing orientation of a fourth vehicle, wherein the fourth vehicle is any one of the at least one vehicles; and determining whether the fourth vehicle is in a reversing state or has the intention to reverse, based on the speed direction and front-facing orientation of the fourth vehicle.

[0021] In conjunction with the first aspect, in some implementations of the first aspect, determining whether the fourth vehicle is in a reversing state or has the intention to reverse is based on the speed direction and the direction of the vehicle's front end, including: determining that the fourth vehicle has the intention to reverse when the speed direction of the fourth vehicle is in the same direction as the direction of the vehicle's front end, and the rate of change of the heading angle of the fourth vehicle satisfies the first condition.

[0022] In some scenarios, the fourth vehicle and the aforementioned second or third vehicle can be the same vehicle.

[0023] In the aforementioned technical solution, based on the relationship between the speed and direction of other vehicles and their heading direction, as well as the rate of change of their heading angle, vehicles intending to reverse can be identified. This allows for alerting and / or avoiding such vehicles, improving the driver's own driving safety. Furthermore, this technical solution enhances the human-likeness of the vehicle's intelligent driving system in predicting the reversing intentions of other vehicles, thereby improving the driver's experience.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: deriving a virtual driving path of the fourth vehicle based on the heading angle and turning radius of the fourth vehicle; determining that the fourth vehicle has the intention to reverse, including: determining that the fourth vehicle has the intention to reverse when the virtual driving path indicates that there is a risk of collision between the fourth vehicle and the boundary of the road where the first vehicle is located.

[0025] Understandably, when the speed and direction of another vehicle are in the same direction as its heading, and the rate of change of its heading angle exceeds a certain threshold, it indicates that the other vehicle intends to turn or make a U-turn. In some cases, the other vehicle may not need to reverse to complete the turn or U-turn; for example, if there is no risk of collision between its path and the road boundary during the turn or U-turn, it may not need to reverse. Conversely, if there is a risk of collision between its path and the road boundary during the turn or U-turn, it is more likely that it will need to reverse. Therefore, based on the above technical solution, it helps to improve the reliability and accuracy of determining the other vehicle's reversing intention, thereby improving the reliability of the vehicle's intelligent driving system and the driver's and passengers' trust in the vehicle.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: a control prompting device prompting second information, the second information indicating at least one of the following: a first area, the first area indicating the area swept by the fourth vehicle during a turn; a virtual driving path; or, the distance between the virtual driving path and the boundary of the road where the first vehicle is located.

[0027] In the above technical solution, by indicating the predicted sweep area and / or driving path of the reversing vehicle, it helps the driver and passengers of the vehicle and / or other people outside the vehicle to understand the reason for indicating the reversing vehicle, thereby enabling the driver and passengers of the vehicle and / or other people outside the vehicle to understand the actions taken by the vehicle in response to the reversing vehicle, and increasing the trust of all parties in the vehicle.

[0028] In conjunction with the first aspect, in some implementations of the first aspect, determining whether the fourth vehicle is in a reversing state or has the intention to reverse is based on the speed direction and the direction in which the vehicle is facing, including: determining that the fourth vehicle is in a reversing state when the speed direction of the fourth vehicle is opposite to the direction in which the vehicle is facing.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the environmental perception information includes multiple frames of images carrying time information. Determining whether each vehicle in at least one vehicle is in a reversing state or has the intention to reverse, based on the environmental perception information, includes: inputting the multiple frames of images into a first neural network model to obtain a first processing result, the first processing result indicating at least one vehicle in a reversing state or having the intention to reverse.

[0030] In the above technical solution, the environmental perception information is processed by a neural network model to predict whether other vehicles are reversing vehicles, which helps to improve the real-time performance of reversing vehicle recognition, thereby improving the timeliness of the vehicle taking relevant measures (such as prompting other vehicles and / or avoiding them in advance) when encountering reversing vehicles.

[0031] In conjunction with the first aspect, in certain implementations of the first aspect, controlling the first vehicle's warning device to display first information, and / or controlling the first vehicle to avoid the second vehicle, includes: when the second vehicle intrudes into the lane where the first vehicle is located, and / or when there is a risk that the second vehicle will intrude into the lane where the first vehicle is located, controlling the warning device to display first information, and / or controlling the first vehicle to avoid the second vehicle.

[0032] In some implementations, when a second vehicle intrudes into the planned driving path of a first vehicle, and / or when there is a risk that the second vehicle will intrude into the planned driving path of the first vehicle, the control prompting device will provide a first message and / or control the first vehicle to avoid the second vehicle.

[0033] In the above technical solution, when the reversing vehicle poses a threat to the safety of the vehicle, the vehicle is then controlled to take relevant measures against the reversing vehicle (such as prompting other vehicles and / or avoiding it in advance); when the reversing vehicle does not pose a threat to the safety of the vehicle, the vehicle can ignore the reversing vehicle, which helps to reduce the processing complexity of the vehicle and save processing costs.

[0034] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: stopping the prompting of the first information and / or stopping the control of the first vehicle to avoid the second vehicle when at least one of the following is detected: the duration of not sensing the second vehicle is greater than or equal to a duration threshold; the change in the heading angle of the second vehicle is greater than or equal to an angle threshold; or the risk of the second vehicle intruding into the lane where the first vehicle is located is eliminated.

[0035] In conjunction with the first aspect, in some implementations of the first aspect, determining whether each of at least one vehicle is in a reversing state or has the intention to reverse, based on environmental perception information, includes: when the first vehicle is in a parking area, or when the width of the road where the first vehicle is located is less than or equal to a width threshold, determining whether each of at least one vehicle is in a reversing state or has the intention to reverse, based on environmental perception information.

[0036] In the aforementioned technical solutions, in parking areas and narrow roads, the likelihood of other vehicles reversing is high, and this poses a significant threat to the safety of the vehicle being driven. Therefore, in these scenarios, the control method provided in this application can improve the accuracy of identifying reversing vehicles, thereby enhancing the safety of the vehicle being driven. In particular, when the driver of the vehicle is inexperienced, this solution can assist the driver, greatly increasing the driver's confidence when navigating the aforementioned complex scenarios.

[0037] In conjunction with the first aspect, in some implementations of the first aspect, the prompting device includes a display device, and the prompting device controlling the first vehicle to prompt the first information includes: when the second vehicle is in a reversing state or has the intention to reverse, controlling the display device to switch from displaying a first interface to displaying a second interface, and prompting the first information through the second interface; wherein, the second interface is used to display real-time images during the vehicle's driving or parking process, and the first interface is used to display other information besides the real-time images.

[0038] In the above technical solution, when a reversing vehicle is detected, the display device of the vehicle is controlled to switch the interface, which helps to improve the timeliness of the driver and passengers obtaining relevant information about the reversing vehicle.

[0039] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: controlling the display device to display third information, the third information indicating the basis for determining that the second vehicle is in a reversing state or has the intention to reverse.

[0040] The above technical solutions help users understand why a vehicle is detected while reversing, thereby increasing user trust in the vehicle and improving the user's driving experience.

[0041] In a second aspect, a control device is provided, disposed in a first vehicle, the device comprising an acquisition unit and a processing unit, wherein the acquisition unit is configured to: acquire environmental perception information, the environmental perception information indicating position changes of at least one vehicle located within a first range of the first vehicle; the processing unit is configured to: determine, based on the environmental perception information, whether each of the at least one vehicle is in a reversing state or has an intention to reverse; the processing unit is further configured to: when a second vehicle among the at least one vehicles is in a reversing state or has an intention to reverse, control a prompting device of the first vehicle to prompt first information, and / or control the first vehicle to avoid the second vehicle; wherein the first information indicates at least one of the following: the position of the second vehicle, the reason for avoiding the second vehicle, or the reason for avoiding the second vehicle.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, the prompting device includes a projection device, the first information includes projection information, the projection device is used to project the projection information onto the outside of the first vehicle, and the projection information indicates the position of the second vehicle, and / or the reversing status or reversing intention of the second vehicle.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the projection information includes a first part of information and / or a second part of information, wherein the first part of information is projected at a first location, which is associated with the locations of other traffic participants within a first range besides the second vehicle; and the second part of information is projected at the area where the second vehicle is located.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, when a third vehicle in at least one of the vehicles is also in a reversing state or has the intention to reverse, the first information further indicates at least one of the following: the position of the third vehicle, the reason for avoiding the third vehicle, or the reason for avoiding the third vehicle.

[0045] In conjunction with the second aspect, in some implementations of the second aspect, the first information includes a first set of elements and a second set of elements. The first set of elements is used to indicate information related to the second vehicle, and the second set of elements is used to indicate information related to the third vehicle. When the risk of reversing caused by the second vehicle is higher than the risk of reversing caused by the third vehicle, the warning level corresponding to the first set of elements is higher than the warning level corresponding to the second set of elements.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to: determine the speed direction and front-facing orientation of the fourth vehicle based on environmental perception information, wherein the fourth vehicle is any one of at least one vehicle; and determine whether the fourth vehicle is in a reversing state or has the intention to reverse based on the speed direction and front-facing orientation of the fourth vehicle.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to: determine that the fourth vehicle has the intention to reverse when the speed direction of the fourth vehicle is in the same direction as the front direction of the fourth vehicle and the rate of change of the heading angle of the fourth vehicle satisfies the first condition.

[0048] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is also used to: deduce the virtual driving path of the fourth vehicle based on the heading angle and turning radius of the fourth vehicle; and determine that the fourth vehicle has the intention to reverse when the virtual driving path indicates that there is a risk of collision between the fourth vehicle and the boundary of the road where the first vehicle is located.

[0049] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: control the prompting device to prompt second information, the second information indicating at least one of the following: a first area, the first area indicating the area swept by the fourth vehicle body during the turning process; a virtual driving path; or, the distance between the virtual driving path and the boundary of the road where the first vehicle is located.

[0050] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to determine that the fourth vehicle is in a reversing state when the speed direction of the fourth vehicle is opposite to the direction in which the front of the fourth vehicle is facing.

[0051] In conjunction with the second aspect, in some implementations of the second aspect, the environmental perception information includes multiple frames of images carrying time information, and the processing unit is used to: input the multiple frames of images into a first neural network model to obtain a first processing result, the first processing result indicating at least one vehicle that is in a reversing state or has the intention to reverse.

[0052] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: stop prompting the first information and / or stop controlling the first vehicle to avoid the second vehicle when at least one of the following is detected: the duration of not sensing the second vehicle is greater than or equal to a duration threshold; the change in the heading angle of the second vehicle is greater than or equal to an angle threshold; or, the risk of the second vehicle intruding into the lane where the first vehicle is located is eliminated.

[0053] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is configured to: when the second vehicle intrudes into the lane where the first vehicle is located, and / or when there is a risk that the second vehicle may intrude into the lane where the first vehicle is located, control the prompting device to provide first information, and / or control the first vehicle to avoid the second vehicle.

[0054] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to: determine, based on environmental perception information, whether each of at least one vehicle is in a reversing state or has a reversing intention when the first vehicle is in a parking area or when the width of the road where the first vehicle is located is less than or equal to a width threshold.

[0055] In conjunction with the second aspect, in some implementations of the second aspect, the prompting device includes a display device, and the processing unit is configured to: when the second vehicle is in a reversing state or has the intention to reverse, control the display device to switch from displaying a first interface to displaying a second interface, and prompt the first information through the second interface; wherein, the second interface is used to display real-time images during the vehicle's driving or parking process, and the first interface is used to display other information besides the real-time images.

[0056] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: control the display device to display third information, the third information indicating the basis for determining that the second vehicle is in a reversing state or has the intention to reverse.

[0057] Thirdly, a control device is provided, comprising: a processor for executing a computer program stored in the memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0058] In conjunction with the third aspect, in some implementations of the third aspect, the device also includes a memory.

[0059] Fourthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer or processor, causes the computer or processor to perform the method in any possible implementation of the first aspect.

[0060] It should be noted that the above computer program code can be stored in whole or in part on a storage medium, which can be packaged together with the processor or packaged separately from the processor.

[0061] Fifthly, a computer-readable storage medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0062] In a sixth aspect, a chip is provided, the chip including circuitry for performing the method in any of the possible implementations of the first aspect described above.

[0063] In a seventh aspect, a vehicle is provided that includes means as in any possible implementation of the second or third aspect, or the vehicle includes a computer-readable storage medium as in any possible implementation of the fifth aspect, or the vehicle includes a chip as in any possible implementation of the sixth aspect, or the vehicle is loaded with a computer program product as in any possible implementation of the fourth aspect.

[0064] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the vehicle is a vehicle in a broad sense, such as a means of transportation (e.g., commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (e.g., forklifts, trailers, tractors, etc.), engineering vehicles (e.g., excavators, bulldozers, cranes, etc.), agricultural equipment (e.g., lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. In practical implementation, the vehicle can also be a road vehicle, a water vehicle, an air vehicle, industrial equipment, agricultural equipment, or other intelligent driving equipment such as entertainment equipment.

[0065] For the beneficial effects not described in detail in aspects two through seven, please refer to the description in aspect one, which will not be repeated here. Attached Figure Description

[0066] Figure 1 is a functional schematic block diagram of the vehicle provided in an embodiment of this application;

[0067] Figure 2 is a schematic block diagram of the control system architecture provided in an embodiment of this application;

[0068] Figure 3 is a schematic flowchart of the control method provided in an embodiment of this application;

[0069] Figure 4 is a schematic diagram of the neural network involved in the embodiments of this application;

[0070] Figure 5 is a schematic diagram of the application scenario of the embodiments of this application;

[0071] Figure 6 is a schematic flowchart for screening reversing vehicles provided in an embodiment of this application;

[0072] Figure 7 is another schematic diagram of the control method provided in the embodiments of this application;

[0073] Figure 8 is a schematic diagram of the application scenarios and GUI involved in the embodiments of this application;

[0074] Figure 9 is another schematic diagram of the GUI involved in the embodiments of this application;

[0075] Figure 10 is another schematic diagram of the GUI involved in the embodiments of this application;

[0076] Figure 11 is another schematic diagram of the GUI involved in the embodiments of this application;

[0077] Figure 12 is another schematic diagram of the GUI involved in the embodiments of this application;

[0078] Figure 13 is another schematic flowchart of the control method provided in the embodiments of this application;

[0079] Figure 14 is a schematic block diagram of the control device provided in an embodiment of this application;

[0080] Figure 15 is another schematic block diagram of the control device provided in the embodiments of this application. Detailed Implementation

[0081] As mentioned earlier, in certain scenarios, intelligent driving systems may fail to accurately judge the behavior of dynamic obstacles, leading to collisions between the vehicle and obstacles and threatening the personal safety and property of the vehicle's occupants; or, it may result in low traffic efficiency and affect the driving experience of the vehicle's occupants. For example, when the vehicle is moving forward, if there is a vehicle reversing or intending to reverse in front of it, the vehicle may not plan a path to avoid the vehicle because it has not yet encroached on the vehicle's current lane. If the driver of the vehicle also fails to notice the vehicle at this time, the reversing vehicle may collide with the vehicle.

[0082] In view of this, this application provides a control scheme that can improve the accuracy of identifying the reversing intention or reversing behavior of other vehicles, and control the driving path of the own vehicle based on the detection results of the reversing intention or reversing behavior, and / or alert the driver of the own vehicle to the reversing intention or reversing behavior of other vehicles, thereby reducing the threat to the driving safety of the own vehicle posed by other vehicles that have the intention or behavior of reversing.

[0083] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0084] Figure 1 is a functional block diagram of a vehicle provided in an embodiment of this application. As shown in Figure 1, the vehicle 100 may include a perception system 120, a prompting device 130, and a computing platform 150. The perception system 120 may include several sensors for sensing information about the surrounding environment of the vehicle 100. For example, the perception system 120 may include a positioning system, which may be a global navigation satellite system (GNSS), such as the global positioning system (GPS), the BeiDou system, etc. Alternatively, the perception system 120 may also include one or more of the following: an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device. Furthermore, the perception system 120 may also include one or more pressure sensors, acoustic sensors, etc., for monitoring whether there is a user inside the cabin and the user's location.

[0085] The prompting device 130 may include any of the following: a sound-emitting device, a display device, a lighting device, or a projection device. More specifically, the sound-emitting device may include a speaker, audio jack, or other device that plays audio. Display devices are mainly divided into two categories: the first is an in-vehicle display screen; the second is a projection display screen, such as a head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of an in-vehicle infotainment system. It should be noted that an in-vehicle display screen may include an HMI. A head-up display, also known as a head-up display system, is mainly used to display driving information such as speed and navigation on a display device in front of the user (e.g., the windshield), to reduce the user's gaze shift time, avoid pupil changes caused by gaze shift, and improve driving safety and comfort. The lighting device may include one or more pixel-type headlights, which may include, but are not limited to, lighting devices based on digital light processing (DLP) technology, lighting devices based on micro light emitting diode (Micro-LED) technology, or lighting devices based on liquid crystal display (LCD). More specifically, the aforementioned pixel-level vehicle lights may include front projection lights for projecting specific patterns onto the road surface or other buildings in front of the vehicle to alert other road users; or, the aforementioned pixel-level vehicle lights may also include side projection lights for projecting specific patterns onto the road surface or other buildings to the sides of the vehicle, and the side projection lights may be respectively located on the left and / or right sides of the vehicle. In some implementations, the lighting device may also include taillights of the vehicle 100, which may be matrix taillights composed of LED beads, through which a series of patterns and / or text may be displayed to alert other road users to the vehicle's intentions. In still other implementations, the lighting device may also include projection lights located at the rear of the vehicle 100, which may project specific patterns onto the road surface or other buildings to the rear of the vehicle.

[0086] The projection device may include a device capable of projecting light information, such as the aforementioned pixel-level vehicle lights or other projection lights; or, the projection device may also include other devices capable of projecting prompt information out of the vehicle.

[0087] Some or all of the functions of vehicle 100 can be controlled by computing platform 150. Computing platform 150 may include processors 151 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement related functions. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions. Some or all of the processors 151 to 15n can call the instructions in the memory to implement the corresponding functions.

[0088] The computing platform 150 can control the operation of the intelligent driving system, which may include advanced driving assistance systems (ADAS) and autonomous driving systems (ADS). The intelligent driving system utilizes various sensors on the vehicle (including but not limited to: LiDAR, millimeter-wave radar, cameras, ultrasonic sensors, GPS, and inertial measurement units) to acquire information from the vehicle's surroundings, and analyzes and processes this information to achieve functions such as obstacle perception, target recognition, vehicle localization, path planning, and driver monitoring / alerts, thereby improving the safety, automation, and comfort of driving.

[0089] At different levels of autonomous driving (or intelligent driving levels, ranging from L0 to L5, totaling six levels), intelligent driving systems can achieve different levels of automated driving assistance based on artificial intelligence algorithms and information acquired by multiple sensors. These levels of autonomous driving are based on the classification standards of the Society of Automotive Engineers (SAE). Specifically, L0 is no automation; L1 is driver assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At levels L1 to L3, the task of monitoring road conditions and reacting is jointly completed by the driver and the system, requiring the driver to take over dynamic driving tasks. Levels L4 and L5 allow the driver to completely transform into a passenger. Currently, the functions that intelligent driving systems can achieve mainly include, but are not limited to: adaptive cruise control, automatic emergency braking, automatic parking, blind spot monitoring, forward cross-traffic alert / braking, rear cross-traffic alert / braking, forward collision warning, lane departure warning, lane keeping assist, rear collision warning, traffic sign recognition, traffic jam assist, and highway assist. It should be understood that the various functions mentioned above can have specific modes at different levels of autonomous driving (L0-L5), with higher levels of autonomous driving corresponding to more intelligent modes. For example, automatic parking can include automatic parking assist (APA), remote parking assist (RPA), valet parking driver (VPD), and automatic valet parking (AVP). With APA, the driver does not need to operate the steering wheel but still needs to control the accelerator and brake from outside the vehicle; with RPA, the driver can remotely park the vehicle from outside using a terminal (e.g., a mobile phone); with AVP, the vehicle can park without a driver. In terms of corresponding autonomous driving levels, APA is approximately at level L1-L2, RPA is approximately at level L2-L3, and AVP and VPD are approximately at level L4.

[0090] The roles of the perception system 120, the prompting device 130, and the computing platform 150 in this application are described in detail below with reference to FIG2. As shown in FIG2, the system includes a perception module 210, a reversing intention determination module 220, a control module 230, and a prompting module 240. In some implementations, the system also includes an actuator. Exemplarily, the perception module 210 may include one or more sensors in the perception system 120 shown in FIG1; the reversing intention determination module 220 and the control module 230 may each include one or more processors in the computing platform shown in FIG1; the prompting module 240 may include one or more devices in the prompting device 130; and the actuator may include the steering and braking control system in the vehicle 100. The roles of each module are as described in items (I) to (V) below.

[0091] (a) The perception module 210 is used to collect perception information around the vehicle, which can indicate the position and position changes of other vehicles around the vehicle. The perception module 210 can send the perception information it collects to the reversing intention determination module 220.

[0092] For example, the perception information may include image information indicating the positional changes of one or more vehicles on a road over a period of time. This image information may be in the form of a video stream or multiple frames extracted from a video stream. In some implementations, the perception information may also include point cloud data, etc.

[0093] (ii) The reversing intention judgment module 220 is used to determine whether each vehicle within a certain range of the vehicle's driving direction has a reversing intention based on the perception information.

[0094] In some implementations, when it is determined that a vehicle is reversing or has the intention to reverse, the reversing intention determination module 220 can send the vehicle's information to the control module 230 and / or the prompting module 240, so that the control module 230 can perform path planning based on the vehicle's position, and the prompting module 240 can prompt the vehicle's reversing behavior or reversing intention.

[0095] In some other implementations, when it is determined that a vehicle is reversing or has the intention to reverse, and the vehicle intrudes into the lane where the vehicle is currently located or the predicted path of the vehicle intrudes into the lane where the vehicle is currently located, the reversing intention determination module 220 can send the vehicle information to the control module 230 and / or the prompting module 240, so that the control module 230 can perform path planning based on the vehicle's position, and the prompting module 240 can prompt the vehicle's reversing behavior or reversing intention.

[0096] (iii) The control module 230 is used to control the vehicle to avoid other vehicles based on information from the reversing intention judgment module 220 regarding other vehicles that have the intention or behavior of reversing.

[0097] (iv) The prompting module 240 is used to control the relevant devices to provide information prompts based on the information from the reversing intention judgment module 220.

[0098] (v) The actuator is used to receive and execute control quantities. When the aforementioned control quantities are executed, the vehicle can be controlled to travel along the planned path. The control quantities can be calculated by the control module 230 based on the planned path.

[0099] It should be understood that the above modules are only an example, and in actual applications, these modules may be added or removed according to actual needs. For example, in the system architecture shown in Figure 2, the reversing intention judgment module 220 and the control module 230 can be merged into one module.

[0100] Figure 3 shows a schematic flowchart of the control method provided in an embodiment of this application. The method 300 can be executed by the vehicle 100 shown in Figure 1, or by the reversing intention determination module 220 shown in Figure 2. Specifically, the method may include some or all of the steps in S310 to S340:

[0101] S310, acquire environmental perception information, which indicates the position and position changes of other vehicles within a certain range of the vehicle.

[0102] For example, environmental perception information may include the perception information in the foregoing embodiments.

[0103] In one example, a certain range can be the range within a circle centered on the center of the vehicle and with a radius of a preset length.

[0104] In another example, the certain range can be the area within a semicircle centered on the vehicle's center and with a radius of a preset length. The straight side of the semicircle coincides with the Y-axis of the vehicle's overall coordinate system, and the center of the semicircle coincides with the origin O of the overall coordinate system. When the vehicle is traveling forward (i.e., towards the front of the vehicle), the arc of the semicircle lies on one side of the positive X-axis; when the vehicle is traveling backward (i.e., towards the rear of the vehicle), the arc of the semicircle lies on one side of the negative X-axis. It should be noted that the origin O of the vehicle coordinate system can be located at the projection point of the rear axle center of the vehicle onto the ground. The positive directions of the X, Y, and Z axes are the vehicle's front direction, the left side direction, and the vertically upward direction perpendicular to the vehicle's plane, respectively. For example, the aforementioned preset length can be any value between 100 meters and 200 meters, or it can be any other value.

[0105] In another example, the certain range can be other ranges. For example, the certain range can also be the range that the vehicle's sensors can perceive, such as the perception range of a camera device or the perception range of a radar sensor.

[0106] S320 determines whether a reversing vehicle is present based on environmental perception information.

[0107] In some implementations, the reversing vehicle includes other vehicles that intend to reverse, or other vehicles that are reversing (or in a reversing state). Here, "other vehicles that intend to reverse" can be understood as: vehicles that did not reverse during the period when environmental perception information was collected, but whose probability of reversing in the future is greater than a preset probability value; "other vehicles that are reversing" can be understood as: vehicles that were reversing during the period when environmental perception information was collected.

[0108] In some implementations, if it is determined that there is no reversing vehicle, S310 is executed; if it is determined that there is a reversing vehicle, S330 is executed: determining whether the reversing vehicle poses a risk of encroaching on the lane where the vehicle is located.

[0109] Among them, "another vehicle intruding into the lane of one's own vehicle" means that part or all of the body of another vehicle is in the lane of one's own vehicle.

[0110] Furthermore, if it is determined that the reversing vehicle poses a risk of encroaching on the lane where the vehicle is located, or if the reversing vehicle has already encroached on the lane where the vehicle is located, execute S340; otherwise, execute S310.

[0111] For example, based on the orientation of the reversing vehicle, a predicted driving path of the reversing vehicle over a future period of time is predicted. If the predicted driving path indicates a point where part or all of the reversing vehicle's body is within the lane occupied by the vehicle being driven, then it is determined that the reversing vehicle poses a risk of intruding into the lane occupied by the vehicle being driven. For example, the future period of time can be between 1 and 2 seconds, or it can be any other period of time. For instance, the future period of time can be determined based on the vehicle's driving speed and the longitudinal distance between the reversing vehicle and the vehicle being driven. This future period of time decreases as the vehicle's driving speed increases and as the longitudinal distance between the reversing vehicle and the vehicle decreases. Here, longitudinal direction is the direction parallel to the vehicle's driving direction, or it can be the direction parallel to the X-axis of the vehicle's coordinate system.

[0112] In some implementations, if it is determined in S320 that a reversing vehicle exists, S340 can be executed directly; otherwise, S310 is executed.

[0113] S340, the control prompting device prompts the reversing vehicle, and / or controls the driving path of the vehicle based on the position of the reversing vehicle.

[0114] More specifically, controlling the vehicle's driving path based on the position of the reversing vehicle can be understood as controlling the vehicle to drive along a path that avoids the reversing vehicle.

[0115] In some implementations, the prompting of a reversing vehicle and the control of the vehicle's driving path based on the position of the reversing vehicle are stopped when one or more of the following are detected: the duration for which no reversing vehicle is detected is greater than or equal to a duration threshold; the change in the heading angle of the reversing vehicle is greater than or equal to an angle threshold; or the risk of the reversing vehicle encroaching on the lane occupied by the vehicle is eliminated. For example, the duration threshold can be one of 0.4s to 0.5s, or it can be any other duration; the angle threshold can be one of 120° to 150°, or it can be any other angle.

[0116] The control method provided in this application can determine whether another vehicle is reversing or filter reversing vehicles in ways including but not limited to: filtering reversing vehicles by processing environmental perception information through a neural network model; or, determining whether another vehicle is reversing by analyzing the position changes of other vehicles indicated by environmental perception information. The method for determining whether another vehicle is reversing will be described in detail below with reference to Figures 4 to 6.

[0117] Figure 4 shows a schematic diagram of the neural network model for screening reversing vehicles provided in this application embodiment. As shown in Figure 4, the neural network model includes a multi-task backbone network, a target detection network, and a risk identification network. The multi-task backbone network is used for feature extraction to obtain two-dimensional image features; the target detection network is used to select the observation object, determine the boundary information of each two-dimensional (2D) observation object (i.e., 2D target boundary information), and input the boundary information of each observation object into the risk identification network. The risk identification network performs cross-frame tracking of the observation target to determine whether the observation target is reversing and / or whether the observation target has intruded into the lane occupied by the vehicle. More specifically, before the multi-task backbone network processes the perception information, a preprocessing module can be used to preprocess the perception information, and after the risk identification network outputs the results, a post-processing module can be used to process the input results. The following describes in detail the actions performed by each module in Figure 4, taking the vehicle as if it is traveling in the direction its front is facing, and the perception information contains n frames of images, which are collected by the vehicle's forward-facing camera.

[0118] 1) The preprocessing module preprocesses the perceived information: it aligns the n frames of images to eliminate image shifts caused by vehicle movement or camera shake; and it uses techniques such as Gaussian filtering and histogram equalization to denoise and enhance each frame of the n frames.

[0119] 2) The object detection network selects the observation object. For example, the object detection network can be a YOLO neural network model, a fast region-based convolutional network (Fast R-CNN), or other convolutional neural networks. For example, the observation object can be a motor vehicle.

[0120] Furthermore, the object detection network can also use multi-object tracking algorithms to track the aforementioned observed objects across frames, extracting their features from different frame images. For example, multi-object tracking algorithms can include simple online and real-time tracking (SORT) algorithms, DeepSORT algorithms, etc.

[0121] 3) The risk identification network extracts temporal features and determines whether each tracked object is a reversing vehicle based on these features: Based on the processing results obtained in step 2), the risk identification network extracts temporal-related features such as motion features and position features of the observed objects. Motion features indicate motion-related characteristics such as the observed object's speed, acceleration, and direction of motion; position features indicate characteristics such as the relative distance, relative speed, and time to collision (TTC) between the observed object and the vehicle.

[0122] In some implementations, the analysis of temporal features can determine whether each tracked object is moving towards the rear of the vehicle (i.e., reversing). Once it is determined that each tracked object is in a reversing state, it can be further determined whether the tracked object in the reversing state has encroached on the lane occupied by the vehicle. In one example, when the image includes pixels indicating lane lines, the positional relationship between the tracked object and the lane lines of the vehicle's lane can be used to determine whether the tracked object has encroached on the vehicle's lane. In another example, when the image does not include pixels indicating lane lines, the boundary of the vehicle's lane can be predicted from the image, thereby determining whether the tracked object has encroached on the vehicle's lane.

[0123] In some implementations, temporal features can be input into the time series model to predict at least one of the following: the trajectory of the observed object over a future period of time; the relative distance between the vehicle and the observed object over a future period of time; or the change in TTC between the vehicle and the observed object over a future period of time. The future period of time can be one to two seconds, calculated from the acquisition time of the last frame in the n-frame images, or it can be any other length. Furthermore, the time series model can be a long short-term memory (LSTM) neural network model, a neural network model based on the Transformer architecture, etc.

[0124] For example, if the observed target is reversing and has not yet invaded the lane of the vehicle, but the time series model predicts that the observed target will invade the lane of the vehicle in the future, it is determined that the observed target has a risk of reversing and invading; or, if the time series model predicts that the observed target will reversing in the future and will invade the lane of the vehicle when reversing, it is determined that the observed target has a risk of reversing and invading.

[0125] 4) The post-processing module marks the observed targets that pose a risk of reversing intrusion and determines their location in the real world.

[0126] The information of the observed object obtained in steps 2) and 3) above is 2D information. The post-processing module can map the features of the image coordinate system to the bird's-eye-view (BEV) coordinate system based on the depth information carried by each pixel in the image and / or the depth information indicated by the laser point cloud data, thereby obtaining the three-dimensional (3D) features of the observed object and thus determining the location of the observed target with the risk of reversing intrusion in the real world.

[0127] It should be noted that the aforementioned n-frame images can be n frames extracted from a video stream, or n frames can be n consecutive frames from a video stream.

[0128] For example, Figure 5 illustrates an application scenario of the neural network model shown in Figure 4. Figure 5 can be considered a schematic diagram of a frame image captured by the vehicle's forward-facing camera, which includes vehicles 501, 502, 503, and 504. For example, using the target detection network in Figure 4, vehicles 501, 502, 503, and 504 can be identified as tracking targets. Then, by combining the positional changes of the tracking targets in multiple frames of images, it can be determined whether each vehicle is a reversing vehicle and / or whether there is a risk of reversing intrusion. If it is determined based on multiple frames of images that vehicle 501 is in a reversing state, then vehicle 501 can be identified as a reversing vehicle, and since vehicle 501 intrudes into the lane it is in, it can be determined that vehicle 501 has a risk of reversing intrusion.

[0129] In some implementations, the target detection network can be trained to identify other vehicles whose heading angles meet certain conditions as observation targets. For example, the aforementioned certain condition could be that the angle between the heading of the other vehicle and the heading of the vehicle itself is between 45° and 135°.

[0130] In some implementations, the target detection network can be trained to identify other vehicles whose longitudinal distance from the vehicle is less than or equal to a certain threshold as the observed target. For example, the aforementioned certain threshold can be a value between 60 meters and 100 meters, or it can be other values.

[0131] Figure 6 shows a schematic flowchart of a method for screening reversing vehicles provided in an embodiment of this application. This method can be regarded as an expanded description of S320 in method 300. This method can be executed by the reversing intention judgment module 220 shown in Figure 2. Specifically, the method includes some or all of the steps in S321 to S327:

[0132] S321 determines whether the current location is an intersection based on environmental perception information.

[0133] For example, if the environmental perception information does not include pixel or point cloud data indicating the intersection, it can be determined that the vehicle is not currently at the intersection; or, if the distance between the vehicle and the intersection is greater than or equal to a distance threshold, it can be determined that the vehicle is not currently at the intersection. The distance threshold can be a value between 150 meters and 200 meters, or it can be any other value.

[0134] More specifically, if it is determined that the vehicle is not currently at an intersection, execute S322; otherwise, end the process.

[0135] It should be noted that in actual implementation, S322 can be executed directly based on environmental perception information, that is, there is no need to determine whether the vehicle is currently at an intersection.

[0136] S322, determine whether the speed direction and the direction of the vehicle 1 are in the same direction.

[0137] For example, vehicle 1 can be any vehicle located within a certain range of its own driving direction.

[0138] For example, when the angle between the velocity direction of vehicle 1 and the heading of vehicle 1 is an acute angle, it is determined that the velocity direction of vehicle 1 and the heading of vehicle 1 are in the same direction. For instance, when the angle between the velocity direction of vehicle 1 and the heading of vehicle 1 is less than or equal to a value between 20° and 30°, it can be determined that the velocity direction of vehicle 1 and the heading of vehicle 1 are in the same direction.

[0139] More specifically, when the speed direction and the direction of the vehicle 1 are in the same direction, S323 is executed; otherwise, it is determined whether the speed direction and the direction of the vehicle 1 are opposite. When the speed direction and the direction of the vehicle 1 are opposite, it is determined that the vehicle 1 is a vehicle that is reversing (i.e., S323').

[0140] For example, when the angle between the velocity direction of vehicle 1 and the heading of vehicle 1 is obtuse, it is determined that the velocity direction and the heading of vehicle 1 are opposite. For instance, when the angle between the velocity direction of vehicle 1 and the heading of vehicle 1 is greater than or equal to a value between 150° and 160°, it can be determined that the velocity direction and the heading of vehicle 1 are opposite.

[0141] S323, determine whether the rate of change of heading angle of vehicle 1 meets the preset conditions.

[0142] For example, the rate of change of the heading angle of vehicle 1 can be determined based on the change value of the heading angle of vehicle 1 in two adjacent frames; or, the rate of change of the heading angle of vehicle 1 can be determined based on the average value of the difference in the heading angle of vehicle 1 in multiple frames.

[0143] For example, the preset condition can be: the rate of change of heading angle is greater than or equal to a preset threshold, wherein the preset threshold can be a value between 12° / s and 20° / s, or the preset threshold can be other values.

[0144] More specifically, if the rate of change of the heading angle of vehicle 1 meets the preset conditions, S324 is executed; otherwise, S321 is executed to continue monitoring the dynamics of vehicle 1.

[0145] S324, based on the heading angle and turning radius of vehicle 1, the virtual driving path of vehicle 1 over a period of time in the future is deduced.

[0146] The specific values ​​for the future period can be as described above, and will not be repeated here.

[0147] For example, a virtual driving path that satisfies kinematic constraints is deduced based on the heading angle and turning radius of vehicle 1.

[0148] S325, determine whether there is a risk of collision between the virtual driving path and the road boundary.

[0149] For example, the road boundary can be an immovable or invariable boundary of the road, such as a curb or green belt; or, the road boundary can be a boundary formed by obstacles temporarily parked beside the road (such as motor vehicles, non-motor vehicles, etc.).

[0150] It is understandable that when there is a collision risk between the virtual driving path and the road boundary, the vehicle may reverse to avoid a collision. Therefore, when it is determined that there is a collision risk between the virtual driving path and the road boundary, vehicle 1 is determined to be a vehicle with the intention to reverse (i.e., S326); otherwise, vehicle 1 is determined to be neither a vehicle that is reversing nor a vehicle with the intention to reverse (i.e., S327).

[0151] After determining that vehicle 1 is reversing or intends to reverse using the method shown in Figure 6, if vehicle 1 has not yet encroached on the lane occupied by the vehicle, further prediction can be made based on information such as the width of the road currently occupied by the vehicle and the orientation angle of vehicle 1. For example, if the width of the road currently occupied by the vehicle is less than or equal to a width threshold, it can be determined that vehicle 1 poses a risk of encroaching on the lane occupied by the vehicle. For example, the width threshold can be a value between 5 meters and 6 meters, or it can be other values, such as a value determined based on the length of vehicle 1.

[0152] In some implementations, the neural network model in Figure 4 can be trained based on the rules associated with the method shown in Figure 6, relevant image information, and the detection results of reversing vehicles. This can improve the neural network model's ability to detect reversing vehicles (such as detection accuracy) and enable the neural network model to filter out vehicles whose speed direction is the same as that of the vehicle but which have the intention to reverse.

[0153] It should be noted that in actual implementation, the environmental perception information can be processed based on the neural network model shown in Figure 4 to filter out reversing vehicles around the vehicle; alternatively, the method shown in Figure 6 can also be used to filter out reversing vehicles around the vehicle; or, the neural network model shown in Figure 4 and the method shown in Figure 6 can be used simultaneously to process the same or different environmental perception information to filter out reversing vehicles around the vehicle. For example, as shown in Figure 7, when a reversing vehicle is detected based on at least one of the neural network model and a pre-set rule (the rule indicated by the method shown in Figure 6), the control prompting device prompts relevant information about the reversing vehicle, and / or controls the vehicle to avoid the reversing vehicle. In addition, the reversing vehicle clearing module can determine whether the reversing state or reversing intention of the detected reversing vehicle has been eliminated based on the environmental perception information. Furthermore, as mentioned above, the neural network model can be trained based on the detection results corresponding to the pre-set rules to improve the accuracy of the neural network model's detection.

[0154] The above describes the method for detecting a reversing vehicle provided in the embodiments of this application. The following, with reference to Figures 8 to 12, describes some specific implementation methods for prompting the reversing vehicle after it is detected.

[0155] Figure 8 illustrates a schematic diagram of an application scenario and a graphical user interface (GUI) involved in an embodiment of this application. For example, if the method in the aforementioned embodiment determines that the vehicle 710 in front of the vehicle is a reversing vehicle, the vehicle's display device (such as the central control screen) can display the position of the vehicle 710 and the reversing behavior of the vehicle 710. Taking the vehicle being parked as an example, the display device can be controlled to display the parking interface shown in the lower left or lower right image of Figure 8, and relevant information about the reversing vehicle can be displayed in the parking interface.

[0156] For example, the parking interface includes element 701 indicating the location of the vehicle, element 702 indicating the location of vehicle 710, and elements 704-a and 704-b indicating that vehicle 710 is in a reversing state. More specifically, element 704-a indicates the projected driving path of vehicle 1, and element 704-b indicates the driving direction of vehicle 1. Furthermore, the style of element 702 may differ from that of elements indicating other non-reversing vehicles to increase the visibility of elements indicating reversing vehicles. This difference in style may include, but is not limited to, different colors or different line types.

[0157] In some implementations, the parking interface may also include text information to inform the driver and passengers of the location and status of the reversing vehicle. In one example, when the vehicle is in human-driven mode (i.e., controlled by a human driver) or in intelligent driving mode (i.e., controlled by an intelligent driving system), the parking interface can display dialog box 703 as shown in Figure 8. Dialog box 703 includes the text information "! The vehicle in front is reversing, please be careful to avoid it," to alert the driver of vehicle 710. In another example, when the vehicle is in intelligent driving mode and the vehicle stops moving based on the location of vehicle 710, the parking interface can display dialog box 705 as shown in Figure 8. Dialog box 705 includes the text information indicating the current status of the vehicle: '! Yielding to other vehicles', and the text information indicating the reason for the current status: 'Other vehicle detected reversing'.

[0158] It should be noted that Figure 8 uses the information displayed when a vehicle in reversing mode is detected as an example. It should be understood that when a vehicle intending to reverse is detected, a prompt can also be made through the interface shown in Figure 8. For example, elements with a different style than those used to indicate other non-reversing vehicles can be used to indicate a vehicle intending to reverse. Alternatively, text information can be used to indicate a vehicle intending to reverse. For example, if a vehicle intending to reverse is located behind the vehicle, the dialog box may include the text message: 'A vehicle intending to reverse has been detected. Please be careful and avoid it.'

[0159] In some implementations, when a reversing vehicle is detected, a real-time video interface can also provide a notification. For example, when the vehicle detects a reversing vehicle and stops driving based on the vehicle's position, the display device can show the interface shown in Figure 9. Here, element 801 indicates the vehicle itself, element 802 indicates the detected reversing vehicle, element 803 indicates the reversing status and path of the vehicle, and the text information in dialog box 804 indicates the vehicle's current status and the reason for that status.

[0160] It should be noted that the elements, controls, components, etc. in each interface in Figure 8 or Figure 9 are only illustrative examples. In actual implementation, each element, control, or component may be presented in a different form than in the aforementioned embodiments. Or, compared to the interface shown in Figure 8 or Figure 9, the actual interface may include more or fewer elements, components, controls, etc.

[0161] Figures 8 and 9 illustrate this by showing the information about a reversing vehicle displayed on the cockpit screen. In practice, this information can also be displayed via audio from a sound system. For example, the sound system could play the audio message "A vehicle is reversing (or intends to reverse)" to indicate the reversing action or intention, and the vehicle's position relative to the driver's vehicle. Alternatively, in practice, the presence of a reversing vehicle can be indicated by combining this with cockpit lighting (such as ambient lighting).

[0162] In some implementations, different warning levels can be used to alert the driver of the reversing vehicle based on its perceived threat level. For example, a higher warning level or stronger alert can be used for a reversing vehicle posing a greater threat. In one example, when the threat level is low, elements indicating the reversing vehicle on the display device can use elements with a lower warning level, such as orange; when the threat level is high, elements with a higher warning level, such as red, can be used. In another example, when alerting the driver of a reversing vehicle via an audio device, the volume of the audio can be increased as the threat level increases.

[0163] For example, the degree of threat posed by a reversing vehicle to the safety of the vehicle can be determined based on at least one of the following: the speed of the reversing vehicle, or the distance between the reversing vehicle and the vehicle. Wherein, the faster the speed of the reversing vehicle, the higher the degree of threat posed by the reversing vehicle to the safety of the vehicle; or, the closer the distance between the reversing vehicle and the vehicle, the higher the degree of threat posed by the reversing vehicle to the safety of the vehicle.

[0164] Furthermore, the aforementioned embodiment uses the example of one reversing vehicle around the vehicle for illustration. In actual implementation, when multiple reversing vehicles are around the vehicle, the prompting device can provide prompts for each reversing vehicle. For example, when vehicle 710 shown in Figure 8 and the nearest neighboring vehicle to the right front of the vehicle are both in a reversing state, the display device can be controlled to display the interface shown in Figure 10. This interface includes a parking interface section and a real-time image section. The parking interface section includes elements 911 and 913 indicating the reversing vehicle, and elements 912 and 914 indicating the reversing state of the reversing vehicle. In addition, the parking interface section also includes a dialog box 915, including the text message: 'Multiple vehicles detected reversing, please be careful to avoid them'. The real-time image section is used to display images captured in real time by the vehicle's camera device. Furthermore, the pixels of the reversing vehicles in the image can be enhanced, for example, by highlighting the pixels of the reversing vehicles, or by using specific colors (such as red, orange, etc.) to enhance the pixels of the reversing vehicles to indicate the reversing vehicles.

[0165] In some implementations, when multiple reversing vehicles exist around the vehicle, and the degree of threat posed by these vehicles varies, the warning device can use different styles of elements to warn different reversing vehicles. For example, if the threat posed by vehicle 710 shown in Figure 8 is lower than that of the nearest vehicle to the right front of the vehicle, then elements 911 and 913 in Figure 10 would be different colors, and the warning level of element 913 would be higher than that of element 911; and / or pixel areas 916 and 917 in Figure 10 would be different colors, and the warning level of pixel area 917 would be higher than that of pixel area 916. For example, elements 913 and pixel area 917 could be red, and elements 911 and pixel area 916 could be yellow or orange.

[0166] In some implementations, in addition to displaying information about reversing vehicles through in-cabin notification devices, the vehicle can also display such information to other road users (such as pedestrians, other vehicles, etc.) outside the vehicle's cabin. For example, taking the case shown in Figure 8 where vehicle 710 and the nearest neighboring vehicle to the right front of the vehicle are both reversing vehicles, projection elements can be projected onto the areas where vehicle 710 and the nearest neighboring vehicle to the right front of the vehicle are located, respectively, so that other road users will notice these two reversing vehicles. For instance, Figure 11 shows a projection device projecting light element 901 onto the area where vehicle 710 is located in Figure 8, and a projection device projecting light element 902 onto the area where the nearest neighboring vehicle to the right front of the vehicle is located, as shown in the upper part of Figure 11, to draw the attention of other road users to these two reversing vehicles.

[0167] In certain scenarios, when a reversing vehicle poses a threat to the safety of a road user, a warning message can be projected onto the area where that road user is located, or onto an area easily visible to them. For example, if the reversing behavior of the nearest vehicle to the right front of the vehicle poses a threat to the safety of vehicle 710, the projection device can be controlled to project text message 903 onto the wall in front of vehicle 710. This text message 903 includes "Another reversing vehicle is present on the right," thus alerting vehicle 710 to the reversing behavior of the nearest vehicle to the right front of the vehicle. In some scenarios, the vehicle can also display light information through its headlights to alert other road users to the threat posed by a reversing vehicle. For example, when other road users are in front of the vehicle, and the vehicle detects that a reversing vehicle poses a threat to their safety, it can also control its headlights to display alternating high and low beams or hazard lights to alert road users in front of the vehicle to the threat posed by the reversing vehicle.

[0168] In some implementations, when the vehicle's prompting device prompts each of one or more reversing vehicles about its reversing status or intention, the dynamics of each reversing vehicle can be continuously observed. Furthermore, when it is detected that a reversing vehicle has exited its reversing status or intention, the prompting of relevant information for that vehicle stops. Specifically, it is determined that a reversing vehicle has exited its reversing status or intention when any of the following 1) to 4) is detected:

[0169] 1) The duration of the reverse vehicle remaining stationary is greater than or equal to the duration threshold 1.

[0170] 2) Even if the duration of the reversing vehicle's stationary position is less than the duration threshold 1, the reversing vehicle is determined to have the intention to reverse, and the reversing vehicle intends to return to its original lane. For example, when the reversing vehicle's orientation changes in the direction opposite to direction 1, it is determined that the reversing vehicle intends to return to its original lane, where direction 1 is the direction opposite to the direction of the orientation angle change that identified the reversing intention. For instance, if the reversing vehicle is detected as having the intention to reverse because the rate of change of the orientation angle when it deflects to the left is greater than the rate of change threshold, then when the reversing vehicle's orientation angle deflects to the right at an angle greater than a certain angle (such as one of 10° to 15°, or other angles), it is determined that the reversing vehicle intends to return to its original lane.

[0171] 3) The duration of the reversing vehicle being stationary is less than the duration threshold 1, but the direction of the reversing vehicle's front is not detected (or no reversing vehicle is detected) for m consecutive frames.

[0172] 4) If the duration of the reversing vehicle being stationary is less than the duration threshold 1, the reversing vehicle is a vehicle in a reversing state, but the direction of the front of the reversing vehicle and the speed direction of the reversing vehicle are detected in consecutive p frames.

[0173] For example, the duration threshold 1 can be a value from 3 seconds to 7 seconds, or the duration threshold 1 can be other values; m can be a value from 3 to 5, or m can be other values; p can be a value from 3 to 5 frames, or p can be other values.

[0174] For example, if it is determined that the vehicle 710 shown in FIG8 and the nearest vehicle to the right front of the vehicle are reversing vehicles, and the vehicle's display device is controlled to display the interface shown in FIG10, and the projection device is controlled to project the projection element shown in FIG11, if it is determined through the aforementioned method that the nearest vehicle to the right front of the vehicle has exited the reversing state, the vehicle's prompting device can be controlled to stop prompting the vehicle. For example, the display device can be controlled to switch from displaying the interface shown in FIG10 to displaying the interface shown in the right figure of FIG12; another example is controlling the projection device to stop projecting the light element 902.

[0175] In addition, the colors and / or brightness of light elements 901 and 902 may also be different. For example, when the reversing behavior of vehicle 710 poses a greater threat to the safety of the vehicle and / or other road users than the reversing behavior of the nearest neighboring vehicle to the right front of the vehicle, light element 901 may be brighter and / or more conspicuous than light element 902.

[0176] It should be noted that the warning levels of lighting elements 901 and 902 may differ from the warning levels of elements 911 and 913 displayed on the in-cabin display device. For example, the warning levels of lighting elements 901 and 902 may be determined based on the degree of threat posed by the reversing vehicle to the safety of other traffic participants outside the passenger compartment; similarly, the warning levels of elements 911 and 913 may be determined based on the degree of threat posed by the reversing vehicle to the safety of the passenger vehicle.

[0177] It should also be noted that the style and position of the projection element shown in Figure 11 are merely illustrative. In actual implementation, the projection element used to indicate the reversing vehicle can also be of other styles. For example, the projection element can also include text information indicating the reversing status or intention of the reversing vehicle. Furthermore, when using the projection element to indicate the position and behavior of the reversing vehicle to other road users, the vehicle can control the projection position of the relevant prompts based on the position of the other road users relative to the vehicle. For example, when other road users are in front of the vehicle, the aforementioned prompts (such as text information 903) can be projected in front of the vehicle; as another example, when relevant personnel are behind the vehicle, the aforementioned prompts (such as text information 903) can be projected behind the vehicle; and as yet another example, when relevant personnel are to the side of the vehicle, the aforementioned prompts (such as text information 903) can be projected to the side of the vehicle.

[0178] In some implementations, when the vehicle is in motion and the central control screen displays the navigation interface shown in the left image of Figure 12, if a reversing vehicle is detected, the central control screen can be switched to the interface shown in the right image of Figure 12 to provide relevant information about the reversing vehicle.

[0179] It should be noted that the processing actions (such as control, detection, etc.) or steps involved in Figures 8 to 12 can be executed by the computing platform 150 shown in Figure 1, or by the reversing intention judgment module 220 in the system shown in Figure 2.

[0180] Figure 13 shows another schematic flowchart of the control method provided in the embodiments of this application. The method can be executed by the vehicle 100 shown in Figure 1, or the method can also be executed by the reversing intention determination module 220 shown in Figure 2. The method 1000 includes:

[0181] S1010, acquire environmental perception information, the environmental perception information indicating the position change of at least one vehicle located within a first range of the first vehicle.

[0182] For example, the environmental perception information can be the environmental perception information in the aforementioned method 300. This environmental perception information may include image information indicating the positional changes of one or more vehicles on the road over a period of time. The specific form of the image information may be a video stream, or it may be multiple frames of images extracted from a video stream. In some implementations, the environmental perception information may also include point cloud data, etc.

[0183] For example, the first vehicle may be the self-driving vehicle in the foregoing embodiments, and the first range may be the "certain range" defined in method 300.

[0184] S1020, based on environmental perception information, determine whether each of at least one vehicle is in a reversing state or has the intention to reverse.

[0185] In some implementations, S1020 can be further refined as follows: based on environmental perception information, determine the speed direction and heading of the fourth vehicle, wherein the fourth vehicle is any one of at least one vehicle; based on the speed direction and heading of the fourth vehicle, determine whether the fourth vehicle is in a reversing state or has the intention to reverse.

[0186] In one example, determining whether the fourth vehicle is in a reversing state or has the intention to reverse is based on the speed direction and the direction in which the vehicle is facing. This includes determining that the fourth vehicle has the intention to reverse when the speed direction of the fourth vehicle is in the same direction as the direction in which the vehicle is facing and the rate of change of the heading angle of the fourth vehicle meets the first condition.

[0187] For example, the first condition for the rate of change of heading angle to satisfy the condition can be that the rate of change of heading angle is greater than or equal to a preset threshold. The preset threshold can be a value between 12° / s and 20° / s, or it can be other values.

[0188] For example, the method for determining the rate of change of the heading angle, and the method for determining whether the rate of change of the heading angle satisfies the first condition, can be referred to the description in S323, and will not be repeated here.

[0189] More specifically, the method further includes: deriving a virtual driving path of the fourth vehicle based on the heading angle and turning radius of the fourth vehicle; determining that the fourth vehicle has the intention to reverse, including: determining that the fourth vehicle has the intention to reverse when the virtual driving path indicates that there is a risk of collision between the fourth vehicle and the boundary of the road where the first vehicle is located.

[0190] For example, the collision risk between the fourth vehicle and the first vehicle can be determined based on the minimum distance between the virtual driving path and the boundary of the road where the first vehicle is located. For instance, if the aforementioned minimum distance is less than a certain threshold, a collision risk is determined to exist between the fourth vehicle and the first vehicle, and the smaller the minimum distance, the greater the collision risk between the fourth vehicle and the first vehicle.

[0191] In this example, the method further includes: a control prompting device prompting second information, the second information indicating at least one of the following: a first area, the first area indicating the area swept by the fourth vehicle during a turn; a virtual driving path; or, the distance between the virtual driving path and the boundary of the road where the first vehicle is located.

[0192] For example, the first region can be the area swept by the predicted body of the fourth vehicle.

[0193] In some scenarios, taking a display device or projection device as an example, the display device can be controlled to show or the projection device to project a first area, a virtual driving path, and the distance between the virtual driving path and the boundary of the road where the first vehicle is located. Alternatively, the display device can be controlled to display different information depending on the stage of the other vehicle. For example, when the other vehicle is in the same direction as its speed and heading, and its heading angle is constantly changing, the display device can be controlled to display the first area; when the other vehicle is about to reverse or is reversing, the display device can be controlled to display the virtual driving path and / or the distance between the virtual driving path and the boundary of the road where the first vehicle is located.

[0194] In another example, the determination of whether the fourth vehicle is in reverse or has the intention to reverse is based on the speed direction and the direction in which the vehicle is facing. This includes determining that the fourth vehicle is in reverse when the speed direction of the fourth vehicle is opposite to the direction in which the vehicle is facing.

[0195] In some implementations, the environmental perception information includes multiple frames of images carrying time information. S1020 can be refined to: inputting the multiple frames of images into a first neural network model to obtain a first processing result. The first processing result indicates at least one vehicle that is in a reversing state or has the intention to reverse.

[0196] For example, the first neural network model can be the neural network model shown in Figure 4. The multiple frames of images can include the n frames of images in the aforementioned embodiments. For a more specific implementation of the first neural network model processing the image information to obtain the processing result, please refer to the description of the corresponding part of Figure 4 above, which will not be repeated here.

[0197] In some implementations, S1020 is executed when the first vehicle is in the parking area, or when the width of the road where the first vehicle is located is less than or equal to the width threshold.

[0198] For example, the width threshold can be a value between 4 meters and 6 meters, or it can be any other value.

[0199] S1030, when the second vehicle in at least one of the vehicles is in a reversing state or has the intention to reverse, the warning device controlling the first vehicle displays the first information, and / or controls the first vehicle to avoid the second vehicle.

[0200] The first information indicates at least one of the following: the location of the second vehicle, the reason for avoiding the second vehicle, or the reason for avoiding the second vehicle.

[0201] For example, the first information may include relevant information indicating the reversing vehicle in the interface shown in FIG8, or the first information may also include other information. For example, element 702 can be regarded as an example of the part of the first information indicating the position of the second vehicle, and the text information in dialog box 703 can be regarded as an example of the part of the first information indicating the reason for avoiding the second vehicle.

[0202] In some implementations, the prompting device includes a projection device, the first information includes projection information, the projection device is used to project the projection information onto the outside of the first vehicle, and the projection information indicates the position of the second vehicle, and / or the reversing status or reversing intention of the second vehicle.

[0203] For example, the light element 901, light element 902 and text information 903 shown in FIG11 can be regarded as some examples of the aforementioned projection information.

[0204] In some implementations, the projection information includes a first part of information and / or a second part of information, wherein the first part of information is projected at a first location, which is associated with the locations of other traffic participants within a first range besides the second vehicle; and the second part of information is projected in the area where the second vehicle is located.

[0205] For example, the first location can be the location of other traffic participants, or it can be a location easily viewed by other traffic participants. In some implementations, the first location can be the location of the traffic participant within a first range who is most affected by the second vehicle, or a location easily viewed by them. The extent to which other traffic participants are affected by the second vehicle can be determined based on the distance between the second vehicle and other traffic participants. For example, the closer the second vehicle is to other traffic participants, and the closer the distance becomes as the second vehicle reverses, the greater the impact on other traffic participants.

[0206] For example, the text information 903 shown in Figure 11 can be an example of the aforementioned first part of information; the light elements 901 and 902 shown in Figure 11 can be regarded as an example of the aforementioned second part of information.

[0207] In some implementations, when a third vehicle in at least one of the vehicles is also in a reversing state or has the intention to reverse, the first information also indicates at least one of the following: the position of the third vehicle, the reason for avoiding the third vehicle, or the reason for avoiding the third vehicle.

[0208] For example, taking the second vehicle as vehicle 710 shown in Figure 8 and the third vehicle as the nearest neighbor vehicle to the right front of the vehicle as an example, the first information may include the relevant information indicating the reversing vehicle in the interface shown in Figure 10.

[0209] In some implementations, the first information includes a first set of elements and a second set of elements. The first set of elements is used to indicate information related to the second vehicle, and the second set of elements is used to indicate information related to the third vehicle. When the risk of reversing caused by the second vehicle is higher than the risk of reversing caused by the third vehicle, the warning level corresponding to the first set of elements is higher than the warning level corresponding to the second set of elements.

[0210] For example, the reversing risk caused by a reversing vehicle can be understood as: the degree of threat posed by the reversing vehicle to the driving safety of the vehicle itself, and / or the degree of threat posed by the reversing vehicle to the safety of other road users. The higher the degree of threat, the higher the reversing risk caused by the reversing vehicle.

[0211] For example, taking the second vehicle as vehicle 710 shown in Figure 8 and the third vehicle as the nearest vehicle to the right front of the vehicle, the first set of elements may include at least one of element 911, pixel area 916, and light element 901; the second set of elements may include at least one of element 912, pixel area 917, and light element 902. More specific methods for determining reversing risk and for providing different warning levels based on reversing risk can be found in the descriptions in the foregoing embodiments, and will not be repeated here.

[0212] In some implementations, S1030 can be further refined as follows: when the second vehicle intrudes into the lane where the first vehicle is located, and / or when there is a risk that the second vehicle will intrude into the lane where the first vehicle is located, the control prompting device will provide a first message, and / or control the first vehicle to avoid the second vehicle.

[0213] For example, the specific implementation of determining whether the second vehicle has intruded into the lane where the first vehicle is located, and / or whether the second vehicle poses a risk of intruding into the lane where the first vehicle is located, can be referred to the description in the foregoing embodiments, and will not be repeated here.

[0214] In some implementations, the method further includes: stopping the prompting of the first information and / or stopping the control of the first vehicle to avoid the second vehicle when at least one of the following is detected: the duration of not sensing the second vehicle is greater than or equal to a duration threshold; the change in the heading angle of the second vehicle is greater than or equal to an angle threshold; or the risk of the second vehicle intruding into the lane where the first vehicle is located is eliminated.

[0215] In some implementations, the prompting device includes a display device, and the prompting device controlling the first vehicle prompts the first information, including: when the second vehicle is in a reversing state or has the intention to reverse, controlling the display device to switch from displaying a first interface to displaying a second interface, and prompting the first information through the second interface; wherein, the second interface is used to display real-time images during the vehicle's driving or parking process, and the first interface is used to display other information besides the real-time images.

[0216] For example, the first interface can be the interface shown in the left figure of Figure 12, and the second interface can be the interface shown in the right figure of Figure 12; or, the first interface and the second interface can also be other interfaces.

[0217] In some implementations, the method further includes: controlling the display device to display third information, the third information indicating the basis for determining that the second vehicle is in a reversing state or has the intention to reverse.

[0218] For example, if it is determined that the second vehicle intends to reverse, the third information can be text information indicating that the second vehicle intends to reverse based on the rate of change of the heading angle of the second vehicle and the deduced virtual driving path; or, the third information can also include the aforementioned second information.

[0219] The control method provided in this application can detect the reversing state of other vehicles or predict their reversing intentions based on environmental information perceived by the vehicle itself. This allows the method to alert and / or proactively avoid reversing vehicles, reducing the likelihood of collisions between the vehicle and other vehicles in a reversing state or with the intention to do so. This improves vehicle safety and reduces the risk of injury to both the vehicle and its occupants. Furthermore, by projecting relevant information about the reversing vehicle onto the vehicle's exterior, other road users around the vehicle are alerted to the reversing vehicle and are prompted to avoid it, further reducing the likelihood of collisions between other road users and the reversing vehicle, and consequently reducing the likelihood of traffic congestion caused by such collisions.

[0220] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0221] The methods provided by the embodiments of this application have been described in detail above with reference to Figures 1 to 13. The apparatus provided by the embodiments of this application will now be described in detail below with reference to Figures 14 and 15. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any content not described in detail can be found in the above method embodiments, and for the sake of brevity, will not be repeated here.

[0222] Figure 14 shows a schematic block diagram of a control device 2000 provided in an embodiment of this application. The device 2000 may include units for executing the methods described in the foregoing embodiments. Furthermore, each unit in the device 2000 implements a corresponding process of the above method embodiments. The device 2000 includes an acquisition unit 2010, which can be used to implement corresponding data acquisition or transmission / reception functions. The device 2000 also includes a processing unit 2020, which can be used to implement corresponding processing functions.

[0223] Optionally, the device 2000 further includes a storage unit, which can be used to store instructions and / or data. The processing unit 2020 can read the instructions and / or data in the storage unit so that the device can perform the relevant actions in the aforementioned method embodiments.

[0224] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0225] It should also be understood that the device 2000 described herein is embodied in the form of a functional unit. The terms “module” or “unit” may refer to application-specific ASICs, electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components that support the described functions.

[0226] The apparatuses described above have the function of implementing the corresponding steps in the methods described above. These functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above; for example, the acquisition unit 2010 can be replaced by a transceiver, and other units, such as the processing unit, can be replaced by a processor, used to execute the relevant processing operations in each method embodiment.

[0227] Exemplarily, the acquisition unit 2010 and processing unit 2020 can be disposed in the vehicle 100 shown in FIG. 1, or they can also be disposed in the system shown in FIG. 2. More specifically, the acquisition unit 2010 and processing unit 2020 can be disposed in the reversing intention determination module 220. Exemplarily, the operations performed by the acquisition unit 2010 and processing unit 2020 can be performed by a single processor, or they can be performed by different processors. In specific implementation, the one or more processors can be processors disposed in the vehicle 100 shown in FIG. 1; or, the device 2000 can be a chip disposed in the vehicle 100.

[0228] In the specific implementation process, the units in the above device can be fully or partially integrated together, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0229] Figure 15 is another schematic block diagram of the control device provided in an embodiment of this application. The device 2100 shown in Figure 15 may include a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, transceiver 2120, and memory 2130 are connected via internal interconnection paths. The memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 may be coupled to the processor 2110 via an interface or integrated with the processor 2110.

[0230] It should be noted that the transceiver 2120 mentioned above may include, but is not limited to, transceiver devices such as input / output interfaces, to realize communication between device 2100 and other devices or communication networks.

[0231] Memory 2130 can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes various forms such as: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0232] Transceiver 2120 uses transceiver devices, such as but not limited to transceivers, to enable communication between device 2100 and other devices or communication networks to receive / send data / information for implementing the methods in the above embodiments.

[0233] This application also provides an intelligent driving device, which includes the device 2000 or device 2100 in the above embodiments.

[0234] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to implement the methods described in the above embodiments of this application.

[0235] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to implement the methods described in the above embodiments of this application.

[0236] This application also provides a chip, including circuitry, for performing the methods described in the above embodiments of this application.

[0237] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0238] In the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. In this application, "at least one" means one or more, and "more" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0239] The use of prefixes such as "first" and "second" in this application embodiment is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions.

[0240] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0241] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0242] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0243] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0244] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A control method characterized by, Applied to the first vehicle, including: Acquire environmental perception information, the environmental perception information indicating the positional changes of at least one vehicle located within a first range of the first vehicle; Based on the environmental perception information, determine whether each of the at least one vehicles is in a reversing state or has the intention to reverse. When the second vehicle in the at least one vehicle is in a reversing state or has the intention to reverse, the warning device of the first vehicle is controlled to provide a first message, and / or the first vehicle is controlled to avoid the second vehicle; The first information indicates at least one of the following: the location of the second vehicle, the reason for avoiding the second vehicle, or the reason for avoiding the second vehicle.

2. The method of claim 1, wherein, The prompting device includes a projection device, the first information includes projection information, the projection device is used to project the projection information onto the outside of the first vehicle, the projection information indicates the position of the second vehicle, and / or the reversing status or reversing intention of the second vehicle.

3. The method of claim 2, wherein, The projection information includes a first part of information and / or a second part of information, wherein, The first portion of information is projected at a first location, which is associated with the location of other traffic participants within the first range, excluding the second vehicle. The second part of the information is projected onto the area where the second vehicle is located.

4. The method according to any one of claims 1 to 3, characterized in that, When a third vehicle among the at least one vehicles is also in a reversing state or has the intention to reverse, the first information further indicates at least one of the following: the position of the third vehicle, the reason for avoiding the third vehicle, or the reason for avoiding the third vehicle.

5. The method of claim 4, wherein, The first information includes a first set of elements and a second set of elements, wherein the first set of elements is used to indicate information related to the second vehicle and the second set of elements is used to indicate information related to the third vehicle. When the risk of reversing caused by the second vehicle is higher than the risk of reversing caused by the third vehicle, the warning level corresponding to the first group of elements is higher than the warning level corresponding to the second group of elements.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining whether each of the at least one vehicles is in a reversing state or has the intention to reverse, based on the environmental perception information, includes: Based on the environmental perception information, the speed direction and frontal orientation of the fourth vehicle are determined, wherein the fourth vehicle is any one of the at least one vehicles; Based on the speed direction and the orientation of the fourth vehicle, determine whether the fourth vehicle is in the reversing state or has the intention to reverse.

7. The method of claim 6, wherein, The step of determining whether the fourth vehicle is in a reversing state or has the intention to reverse based on the speed direction and frontal orientation of the fourth vehicle includes: When the speed direction of the fourth vehicle is in the same direction as the front of the fourth vehicle, and the rate of change of the heading angle of the fourth vehicle satisfies the first condition, it is determined that the fourth vehicle has the intention to reverse.

8. The method of claim 7, wherein, The method further includes: Based on the heading angle and turning radius of the fourth vehicle, the virtual driving path of the fourth vehicle is deduced; Determining that the fourth vehicle has the intention to reverse includes: When the virtual driving path indicates a risk of collision between the fourth vehicle and the boundary of the road where the first vehicle is located, it is determined that the fourth vehicle has the intention to reverse.

9. The method of claim 8, wherein, The method further includes: The prompting device is controlled to display a second message, the second message indicating at least one of the following: The first region indicates the area swept by the fourth vehicle during its turn; The virtual driving route; or... The distance between the virtual driving path and the boundary of the road where the first vehicle is located.

10. The method according to claim 6, characterized in that, The step of determining whether the fourth vehicle is in a reversing state or has the intention to reverse based on the speed direction and frontal orientation of the fourth vehicle includes: When the speed direction of the fourth vehicle is opposite to the direction in which the front of the fourth vehicle is facing, it is determined that the fourth vehicle is in the reversing state.

11. The method according to any one of claims 1 to 10, characterized in that, The environmental perception information includes multiple frames of images carrying time information. Determining whether each of the at least one vehicle is in a reversing state or has the intention to reverse, based on the environmental perception information, includes: The multi-frame images are input into a first neural network model to obtain a first processing result, which indicates at least one of the vehicles that is in a reversing state or has the intention to reverse.

12. The method according to any one of claims 1 to 11, characterized in that, The device for controlling the first vehicle to provide a first message, and / or controlling the first vehicle to avoid the second vehicle, includes: When the second vehicle intrudes into the lane occupied by the first vehicle, and / or when the second vehicle poses a risk of intruding into the lane occupied by the first vehicle, the system controls the warning device to display the first information, and / or controls the first vehicle to avoid the second vehicle.

13. The method according to any one of claims 1 to 12, characterized in that, The method further includes: If at least one of the following is detected, the first information will be stopped being displayed, and / or the control of the first vehicle to avoid the second vehicle will be stopped: The duration of the second vehicle was not detected to be greater than or equal to the duration threshold; The change in the heading angle of the second vehicle is greater than or equal to the angle threshold; or, The risk of the second vehicle encroaching on the lane where the first vehicle is located has been eliminated.

14. The method according to any one of claims 1 to 13, characterized in that, The step of determining whether each of the at least one vehicles is in a reversing state or has the intention to reverse, based on the environmental perception information, includes: When the first vehicle is in a parking area, or when the width of the road where the first vehicle is located is less than or equal to a width threshold, the environmental perception information is used to determine whether each of the at least one vehicle is in a reversing state or has the intention to reverse.

15. The method according to any one of claims 1 to 14, characterized in that, The prompting device includes a display device, and the prompting device controlling the first vehicle prompts first information, including: When the second vehicle is in reverse or has the intention to reverse, the display device is controlled to switch from displaying the first interface to displaying the second interface, and the first information is displayed through the second interface; The second interface is used to display real-time images of the vehicle during driving or parking, while the first interface is used to display other information besides the real-time images.

16. The method according to claim 15, characterized in that, The method further includes: The display device is controlled to display third information, which indicates the basis for determining that the second vehicle is in a reversing state or has the intention to reverse.

17. A control device, characterized in that, Installed in the first vehicle, including: An acquisition unit is configured to acquire environmental perception information, the environmental perception information indicating the positional changes of at least one vehicle located within a first range of the first vehicle; The processing unit is configured to determine, based on the environmental perception information, whether each of the at least one vehicle is in a reversing state or has the intention to reverse. The processing unit is further configured to: when the second vehicle in the at least one vehicle is in a reversing state or has the intention to reverse, control the prompting device of the first vehicle to prompt the first information, and / or control the first vehicle to avoid the second vehicle; The first information indicates at least one of the following: the location of the second vehicle, the reason for avoiding the second vehicle, or the reason for avoiding the second vehicle.

18. The apparatus according to claim 17, characterized in that, The prompting device includes a projection device, the first information includes projection information, the projection device is used to project the projection information onto the outside of the first vehicle, the projection information indicates the position of the second vehicle, and / or the reversing status or reversing intention of the second vehicle.

19. The apparatus according to claim 18, characterized in that, The projection information includes a first part of information and / or a second part of information, wherein, The first portion of information is projected at a first location, which is associated with the location of other traffic participants within the first range, excluding the second vehicle. The second part of the information is projected onto the area where the second vehicle is located.

20. The apparatus according to any one of claims 17 to 19, characterized in that, When a third vehicle among the at least one vehicles is also in a reversing state or has the intention to reverse, the first information further indicates at least one of the following: the position of the third vehicle, the reason for avoiding the third vehicle, or the reason for avoiding the third vehicle.

21. The apparatus according to claim 20, characterized in that, The first information includes a first set of elements and a second set of elements, wherein the first set of elements is used to indicate information related to the second vehicle and the second set of elements is used to indicate information related to the third vehicle. When the risk of reversing caused by the second vehicle is higher than the risk of reversing caused by the third vehicle, the warning level corresponding to the first group of elements is higher than the warning level corresponding to the second group of elements.

22. The apparatus according to any one of claims 17 to 21, characterized in that, The processing unit is used for: Based on the environmental perception information, the speed direction and frontal orientation of the fourth vehicle are determined, wherein the fourth vehicle is any one of the at least one vehicles; Based on the speed direction and the orientation of the fourth vehicle, determine whether the fourth vehicle is in the reversing state or has the intention to reverse.

23. The apparatus according to claim 22, characterized in that, The processing unit is used for: When the speed direction of the fourth vehicle is in the same direction as the front of the fourth vehicle, and the rate of change of the heading angle of the fourth vehicle satisfies the first condition, it is determined that the fourth vehicle has the intention to reverse.

24. The apparatus according to claim 23, characterized in that, The processing unit is also used for: Based on the heading angle and turning radius of the fourth vehicle, the virtual driving path of the fourth vehicle is deduced; When the virtual driving path indicates a risk of collision between the fourth vehicle and the boundary of the road where the first vehicle is located, it is determined that the fourth vehicle has the intention to reverse.

25. The apparatus according to claim 24, characterized in that, The processing unit is also used for: The prompting device is controlled to display a second message, the second message indicating at least one of the following: The first region indicates the area swept by the fourth vehicle during its turn; The virtual driving route; or... The distance between the virtual driving path and the boundary of the road where the first vehicle is located.

26. The apparatus according to claim 22, characterized in that, The processing unit is used for: When the speed direction of the fourth vehicle is opposite to the direction in which the front of the fourth vehicle is facing, it is determined that the fourth vehicle is in the reversing state.

27. The apparatus according to any one of claims 17 to 26, characterized in that, The environmental perception information includes multiple frames of images carrying time information, and the processing unit is used for: The multi-frame images are input into a first neural network model to obtain a first processing result, which indicates at least one of the vehicles that is in a reversing state or has the intention to reverse.

28. The apparatus according to any one of claims 17 to 27, characterized in that, The processing unit is used for: When the second vehicle intrudes into the lane occupied by the first vehicle, and / or when the second vehicle poses a risk of intruding into the lane occupied by the first vehicle, the system controls the warning device to display the first information, and / or controls the first vehicle to avoid the second vehicle.

29. The apparatus according to any one of claims 17 to 28, characterized in that, The processing unit is also used for: If at least one of the following is detected, the first information will be stopped being displayed, and / or the control of the first vehicle to avoid the second vehicle will be stopped: The duration of the second vehicle was not detected to be greater than or equal to the duration threshold; The change in the heading angle of the second vehicle is greater than or equal to the angle threshold. or, The risk of the second vehicle encroaching on the lane where the first vehicle is located has been eliminated.

30. The apparatus according to any one of claims 17 to 29, characterized in that, The processing unit is used for: When the first vehicle is in a parking area, or when the width of the road where the first vehicle is located is less than or equal to a width threshold, the environmental perception information is used to determine whether each of the at least one vehicle is in a reversing state or has the intention to reverse.

31. The apparatus according to any one of claims 17 to 30, characterized in that, The prompting device includes a display device, and the processing unit is used for: When the second vehicle is in reverse or has the intention to reverse, the display device is controlled to switch from displaying the first interface to displaying the second interface, and the first information is displayed through the second interface; The second interface is used to display real-time images of the vehicle during driving or parking, while the first interface is used to display other information besides the real-time images.

32. The apparatus according to claim 31, characterized in that, The processing unit is also used for: The display device is controlled to display third information, which indicates the basis for determining that the second vehicle is in a reversing state or has the intention to reverse.

33. A control device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 16.

34. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 16.

35. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 16.

36. A computer program product, characterized in that, The computer program product includes: computer program code, which, when executed by a processor, implements the method as described in any one of claims 1 to 16.

37. A vehicle, characterized in that, Includes the apparatus as described in any one of claims 17 to 33, or the computer-readable storage medium as described in claim 34, or the chip as described in claim 35, or the vehicle is equipped with the computer program product as described in claim 36.

Images