Vehicle control method and device and vehicle-mounted equipment

Abstract

The invention discloses a vehicle control method and device and vehicle-mounted equipment, and relates to the field of automobiles, and the method comprises the steps: responding to a condition that a target vehicle meets a toll station passing condition, and determining a driving track of the target vehicle according to a lane position of a target lane in a target toll station output by a sensing model.

Description

[0001] This application claims priority to Chinese Patent Application No. 202411647421.3, filed on November 15, 2024, entitled "A Vehicle Control Method, Apparatus and On-board Equipment", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving technology, and in particular to a vehicle control method, device and vehicle-mounted equipment. Background Technology

[0003] In intelligent driving scenarios, after a vehicle arrives at a toll station, the intelligent driving system can control the vehicle to automatically enter the ETC lane according to the previously recorded location of the ETC (Electronic Toll Collection) lane at that toll station.

[0004] However, the location of ETC lanes at each toll station may change due to factors such as equipment status or business scenarios, which may cause the intelligent driving system to fail to accurately control the vehicle to enter the ETC lane. Summary of the Invention

[0005] In view of the above problems, this application provides a vehicle control method, device, and in-vehicle equipment to improve the accuracy of intelligent driving and enhance the user experience of intelligent driving. The specific solution is as follows:

[0006] The first aspect of this application provides a vehicle control method, the method comprising:

[0007] In response to the target vehicle meeting the toll station passage conditions, the driving trajectory of the target vehicle is determined based on the lane position of the target lane in the target toll station output by the perception model.

[0008] In one possible implementation, the method further includes:

[0009] Control the target vehicle to travel along the driving trajectory so that the target vehicle enters the target lane;

[0010] The raising and lowering state of the barrier arm on the target lane is detected, and the raising and lowering state of the barrier arm is represented by the relative position of the barrier arm and the target lane;

[0011] When the lifting / lowering state indicates that the barrier is not fully raised, the target vehicle is controlled to wait.

[0012] When the barrier is fully raised in the lifting / lowering state, the target vehicle is controlled to continue driving so that it passes through the target toll station.

[0013] In one possible implementation, detecting the raising or lowering state of the barrier gate on the target lane includes:

[0014] Obtain first sensing data; the first sensing data is sensing data collected by at least one sensor deployed on the target vehicle;

[0015] Based on the first sensor data, the raising and lowering state of the barrier is obtained using a detection model.

[0016] In one possible implementation, the method further includes:

[0017] Based on the lane position of the target lane output by the perception model, the target lane is displayed in the navigation interface of the target vehicle.

[0018] In one possible implementation, after the target vehicle enters the target lane, the method further includes:

[0019] Based on the relative position of the barrier on the target lane and the target lane, the barrier is displayed on the navigation interface of the target vehicle.

[0020] In one possible implementation, the toll station access condition includes: after sending a toll station request to the perception model, receiving the toll station location output by the perception model in response to the toll station request;

[0021] The toll station request is sent to the perception model when the target vehicle meets the travel progress condition; the perception model outputs the toll station location of the target toll station based on the first sensor data.

[0022] The driving progress condition includes: the distance between the current position of the target vehicle and the target position corresponding to the target toll station is less than or equal to a first threshold.

[0023] In one possible implementation, the toll station access conditions include: the target toll station exists in the direction of travel of the target vehicle; and the distance between the current position of the target vehicle and the target position corresponding to the target toll station is less than or equal to a second threshold.

[0024] Wherein, in response to the target vehicle meeting the toll station passage conditions, the lane position of the target lane in the target toll station output by the perception model is determined in the following way:

[0025] A lane request is sent to the perception model so that the perception model outputs the lane position of the target lane in the target toll station based on the second sensing data;

[0026] Receive the lane position of the target lane output by the perception model.

[0027] In one possible implementation, the target lane is an electronic non-stop toll collection lane at a toll station on a highway;

[0028] Alternatively, the target lane is the lane with the least congestion among the toll gates in the parking lot.

[0029] A second aspect of this application provides a vehicle control device, the device comprising:

[0030] Perceptual model;

[0031] An intelligent driving system is used to obtain the driving trajectory of a target vehicle based on the lane position of the target lane in the target toll station output by the perception model, in response to the target vehicle meeting the toll station passage conditions.

[0032] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an in-vehicle device, cause the in-vehicle device to implement the vehicle control method of the first aspect or any implementation thereof.

[0033] A fourth aspect of this application provides an in-vehicle device, comprising:

[0034] At least one sensor, said sensor being used to acquire sensing data;

[0035] At least one processor, on which an intelligent driving system and a perception model are deployed;

[0036] The intelligent driving system is used to obtain the driving trajectory of the target vehicle based on the lane position of the target lane in the target toll station output by the perception model, in response to the target vehicle meeting the toll station passage conditions.

[0037] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs that, when executed by an in-vehicle device, enable the in-vehicle device to implement the vehicle control method described in the first aspect or any implementation thereof.

[0038] By employing the above technical solutions, the vehicle control method, device, and on-board equipment provided in this application detect the lane position of the target lane through a perception model when the target vehicle passes through the target toll station, and determine the corresponding driving trajectory based on the lane position of the target lane, thereby controlling the target vehicle to enter the target lane in the target toll station. This does not depend on whether there is a previously recorded lane position. Even if there is, the vehicle may not drive according to the previously recorded lane position, but rather obtain the driving trajectory according to the lane position of the target lane detected in real time by the perception model. This avoids situations where the vehicle exits intelligent driving and is taken over by the user due to the absence of a previously recorded lane position, and also avoids situations where the vehicle enters the wrong lane due to an incorrect previously recorded lane position. This improves the accuracy of intelligent driving and enhances the user's experience with intelligent driving. Attached Figure Description

[0039] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0040] Figure 1 A flowchart of a vehicle control method provided in an embodiment of this application;

[0041] Figure 2 This is a schematic diagram of the architecture of the vehicle-mounted device in the embodiments of this application;

[0042] Figure 3 This is a schematic diagram of the lane position of the target lane in an embodiment of this application;

[0043] Figure 4 This is an example diagram of the driving trajectory of the target vehicle in an embodiment of this application;

[0044] Figure 5 Another flowchart of a vehicle control method provided in an embodiment of this application;

[0045] Figure 6 This is a schematic diagram showing the raising and lowering state of the barrier arm in an embodiment of this application;

[0046] Figure 7 This is an example diagram showing the barrier arm raised to an acute angle range in an embodiment of this application;

[0047] Figure 8 This is an example diagram showing the barrier arm raised to a right angle range in an embodiment of this application;

[0048] Figure 9 This is an example image of rendering the target toll station and target lane in an embodiment of this application;

[0049] Figure 10 This is an example diagram of rendering the target toll station, target lane, and barrier in an embodiment of this application;

[0050] Figure 11 This is an example diagram illustrating the opening of the autonomous communication ETC at the toll station through the settings interface of the intelligent driving system in this application embodiment;

[0051] Figure 12 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application;

[0052] Figure 13 This is a schematic diagram of the structure of a vehicle-mounted device provided in an embodiment of this application;

[0053] Figure 14 Example diagram showing how the intelligent driving system pre-sets the ETC access switch at the toll station to be turned on in the scenario where a vehicle passes through ETC;

[0054] Figure 15 In scenarios where vehicles pass through ETC (Electronic Toll Collection), the intelligent driving system displays a rendered example image of the current lane in the detailed navigation area;

[0055] Figure 16 In scenarios where vehicles pass through ETC, the intelligent driving system displays an example image of the ETC lane in the detailed navigation area;

[0056] Figure 17 In scenarios where vehicles pass through ETC, the intelligent driving system displays an example image of the barrier gate on the ETC lane in real time in the detailed navigation area;

[0057] Figure 18 In scenarios where vehicles pass through ETC (Electronic Toll Collection), the intelligent driving system displays an example image of the vehicle exiting the toll station in the detailed navigation area. Detailed Implementation

[0058] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0059] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0060] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0061] Reference Figure 1 This is a flowchart illustrating a vehicle control method provided in an embodiment of this application. This method is applicable to in-vehicle devices that are processor-based and equipped with intelligent driving systems and perception models. Figure 2 As shown, the target vehicle is equipped with at least one sensor and a processor, such as an on-board chip. Based on the processor on the target vehicle, an intelligent driving system and a perception model can be deployed. The perception model can be a visual-language model (VLM), GPT-4V (Generative Pre-trained Transformer 4 with Vision), or other models. The intelligent driving system can include end-to-end models and other models. The technical solution in this embodiment is mainly used to improve the accuracy of intelligent driving and enhance the user experience of intelligent driving.

[0062] Specifically, the method in this embodiment may include the following steps:

[0063] Step 101: Monitor whether the target vehicle meets the toll station passage conditions; if the target vehicle meets the toll station passage conditions, execute step 102; otherwise, return to continue executing step 101.

[0064] Step 102: Determine the trajectory of the target vehicle based on the lane position of the target lane in the target toll station output by the perception model.

[0065] The perception model outputs the lane position of the target lane based on the second sensor data. The lane position can be represented by coordinate data, or it can be identified by the relative position of the target lane among all lanes in the target toll station. For example... Figure 3 As shown, the target lanes are the first and fifth from the left among the six lanes at the target toll station.

[0066] The second sensing data can be sensing data collected by at least one sensor deployed on the target vehicle. The sensors deployed on the target vehicle collect corresponding sensing data according to a set acquisition frequency to obtain the second sensing data. For example, the first sensing data may include: multimedia data such as image or video data collected by each camera deployed on the target vehicle; scan data collected by various types of radar deployed on the target vehicle; acceleration and angular velocity data collected by the inertial measurement unit (IMU) deployed on the target vehicle; coordinate data collected by the positioning device deployed on the target vehicle; wheel rotation speed data collected by the wheel sensors deployed on the target vehicle, and so on.

[0067] In practice, the target toll station can be a location equipped with automatic toll collection devices, such as a highway toll station or a parking lot toll gate. The target lane can be an ETC lane at a highway toll station, or it can be the lane with the least congestion at a parking lot toll gate.

[0068] It should be noted that the perception model learns the lane features of the target lane in advance based on training samples.

[0069] For example, taking the target lane as an ETC lane as an example, in this embodiment, training samples such as sample images of toll stations marked with ETC lanes are provided to the perception model in advance, so that the perception model can identify the ETC lane in the target toll station and then output the lane position of the ETC lane.

[0070] For example, taking the target lane as the lane with the fewest congested vehicles as an example, in this embodiment, training samples such as sample images marked with toll gates with the fewest congested vehicles are provided to the perception model in advance, so that the perception model can identify the lane with the fewest congested vehicles in the toll gate.

[0071] Specifically, in step 102, in this embodiment, an intelligent driving system, such as an end-to-end model, can generate the target vehicle's driving trajectory based on the target vehicle's lane position. The target vehicle's driving trajectory includes the target lane. For example, such as... Figure 4 As shown, the target vehicle's trajectory includes the target lane.

[0072] As can be seen from the above technical solution, in the vehicle control method provided in this application embodiment, when the target vehicle passes through the target toll station, the lane position of the target lane is detected by the perception model and determined according to the lane position of the target lane. Therefore, it does not depend on whether there is a previously recorded lane position. Even if there is, it can not drive according to the previously recorded lane position, but obtain the driving trajectory according to the lane position of the target lane detected by the perception model. There will be no situation where the intelligent driving is discontinued and the user takes over because there is no previously recorded lane position, nor will there be a situation where the wrong lane is entered during the intelligent driving process due to the incorrect previously recorded lane position. This improves the accuracy of vehicle intelligent driving and improves the user's experience of intelligent driving.

[0073] based on Figure 1 In one implementation of the illustrated embodiment, this embodiment may further include the following processes, such as... Figure 5 As shown:

[0074] Step 103: Control the target vehicle to travel along the driving trajectory so that the target vehicle enters the target lane.

[0075] For example, refer to Figure 4 The target vehicle follows the trajectory shown and enters the first target lane on the left.

[0076] Step 104: Detect the raising and lowering status of the barrier gate on the target lane. If the raising and lowering status indicates that the barrier gate is not fully raised, proceed to step 105; if the raising and lowering status indicates that the barrier gate is fully raised, proceed to step 106.

[0077] The raising and lowering state of the barrier is indicated by its relative position to the target lane. For example, as... Figure 6 As shown, when the barrier is parallel to the target lane, the barrier's lifting state indicates that it is not fully raised; when the barrier is raised to an acute angle relative to the target lane (e.g., 0 to 85 degrees), the barrier is not fully raised; when the barrier is raised to a right angle relative to the target lane (e.g., 85 to 95 degrees), the barrier is fully raised.

[0078] In practice, step 104 can be implemented in the following way:

[0079] First, first sensing data is obtained. This first sensing data is real-time data collected by at least one sensor deployed on the target vehicle. The sensors deployed on the target vehicle collect corresponding sensing data according to a set collection frequency to obtain the first sensing data. Examples include image data collected by each camera deployed on the target vehicle, scan data collected by various types of radar deployed on the target vehicle, acceleration and angular velocity data collected by the IMU deployed on the target vehicle, coordinate data collected by the positioning device deployed on the target vehicle, wheel rotation speed data collected by the wheel sensors deployed on the target vehicle, etc. The first sensing data and the second sensing data can be sensing data collected by the same sensors deployed on the target vehicle.

[0080] Then, based on the first sensor data, the relative position of the barrier gate and the target lane is obtained using the detection model, i.e., the raising and lowering state of the barrier gate.

[0081] The detection model is a model included in the intelligent driving system deployed on the target vehicle. A pre-trained detection model can be deployed within the intelligent driving system. Through training with training samples, the detection model can detect the position of the barrier relative to the target lane in real time based on second sensor data, i.e., the raising and lowering state of the barrier.

[0082] It should be noted that the barrier is controlled by the control system in the target toll station. The control system in the target toll station raises the barrier when it detects that the target vehicle meets the conditions for communication.

[0083] The conditions for allowing passage include: the target vehicle being successfully charged or authorized to pass.

[0084] Step 105: Control the target vehicle to wait.

[0085] For example, such as Figure 7 As shown, when the barrier is raised to an acute angle relative to the target lane, the target vehicle is controlled to stop moving and wait for the barrier to be fully raised.

[0086] Step 106: Control the target vehicle to continue driving so that it passes through the target toll station.

[0087] For example, such as Figure 8 As shown, when the barrier is raised to the angle range corresponding to a right angle relative to the target lane, the target vehicle is controlled to continue driving, and then the target vehicle passes through the target toll station after driving in the target lane.

[0088] As can be seen, in this embodiment, after the target vehicle enters the target lane, it can autonomously pass through the target toll station by detecting the raising and lowering status of the barrier, thereby improving the user's intelligent driving experience when passing through the toll station.

[0089] Based on any of the above implementation schemes, in one implementation method, this embodiment may also have the following processing:

[0090] Based on the position of the target lane, the target lane is displayed in the navigation interface of the target vehicle.

[0091] For example, such as Figure 9 As shown, the navigation interface includes an overview navigation area and a detailed navigation area. The overview navigation area displays the target vehicle and its driving trajectory, while the detailed navigation area displays the target toll station, the target vehicle, and the target lane such as ETC. This informs the driver that the target vehicle is in the target lane, thereby improving the driver's intelligent driving experience.

[0092] Based on any of the above implementation schemes, in one implementation method, after the target vehicle enters the target lane, the following processing can also be performed in this embodiment:

[0093] Based on the relative position of the barrier gate on the target lane to the target lane, the barrier gate is displayed on the navigation interface of the target vehicle.

[0094] For example, such as Figure 10 As shown, in the detailed navigation area of ​​the navigation interface, the target toll station is displayed based on its location, the target vehicle is displayed based on its location, the target lane is displayed based on its location, and the barrier gate in front of the target vehicle is displayed based on its relative position to the target lane. The raising and lowering state of the barrier gate in the detailed navigation area corresponds to the relative position of the barrier gate and the target lane detected by the detection model, such as the barrier gate being raised halfway, to improve the driver's intelligent driving experience.

[0095] Based on any of the above implementation schemes, in one implementation method, the toll station access condition can be: after sending a toll station request to the perception model, the toll station location output by the perception model in response to the toll station request is received.

[0096] Specifically, the toll station request is sent to the perception model when the target vehicle meets the travel progress condition. This travel progress condition can be: the distance between the target vehicle's current location and the target location corresponding to the target toll station is less than or equal to a first threshold. For example, the travel progress condition could be: the target vehicle is on a ramp preparing to enter the highway or the target vehicle is on a ramp preparing to exit the highway. Based on this, the perception model outputs the toll station location of the target toll station according to the first sensor data.

[0097] It should be noted that the target location corresponding to the target toll station refers to the location of the target toll station as recorded earlier. The target location is a location related to the target toll station, such as the location of a highway ramp. Specifically, the target location can be a location set based on the driving environment of the target vehicle. For example, in a scenario where the target vehicle is preparing to enter the highway, the target location is the highway ramp; similarly, in a scenario where the target vehicle is preparing to exit the highway, the target location is the highway exit ramp. The first threshold can be set according to the driving status of the target vehicle and business needs. For example, the higher the speed of the target vehicle, the larger the first threshold.

[0098] For example, when the intelligent driving system detects that the distance between the target vehicle's current location and the previously recorded target location of the toll station is less than or equal to a first threshold, it sends a toll station request to the perception model. This request indicates the need to obtain the real-time location of the target toll station. Based on this, the perception model responds to the request by obtaining real-time first sensor data from sensors deployed on the target vehicle. Then, the perception model identifies the location of the target toll station based on this first sensor data. The toll station location can be represented by coordinate data, or by the relative position of the target toll station relative to the target vehicle. Furthermore, the perception model also identifies the lane position of the target lane based on the first sensor data. The intelligent driving system then obtains the toll station location output by the perception model. Thus, the intelligent driving system can determine that the toll station access conditions are met. At this point, the intelligent driving system continues to obtain the lane position of the target lane from the perception model. Based on the lane position of the target lane, the intelligent driving system obtains a driving trajectory. Under the control of the intelligent driving system, the target vehicle travels along the driving trajectory, thereby entering the target lane.

[0099] It should be noted that in this embodiment, there is no need to continuously send toll station requests to the perception model. Only when the distance between the target vehicle and the target toll station at the current location is less than or equal to the first threshold recorded by the target toll station is a toll station request sent to the perception model. This can reduce the number of times the perception model identifies the location of the toll station and the lane location of the target lane, reduce the data processing resources occupied by the on-board equipment, thereby reducing the power consumption of the on-board equipment and saving the data processing resources of the on-board equipment.

[0100] based on Figure 1 In one implementation of the embodiment shown, the toll station access condition can be: there is a target toll station in the direction of travel of the target vehicle, and the distance between the current position of the target vehicle and the target position corresponding to the target toll station is less than or equal to a second threshold.

[0101] It should be noted that the second threshold can be set based on the target vehicle's driving status and business needs. For example, the higher the target vehicle's speed, the larger the second threshold. The target location corresponding to the target toll station refers to its previously recorded historical location.

[0102] Based on this, in this embodiment, when it is determined that the target vehicle meets the conditions for passing through the toll station, a lane request can be sent to the perception model first, so that the perception model can output the lane position of the target lane in the target toll station according to the first sensing data, and then the lane position of the target lane output by the perception model can be received.

[0103] For example, when an intelligent driving system detects a target toll station and the distance between the target vehicle's current location and the toll station's previously recorded target location is less than or equal to a second threshold, the system can determine that the toll station access conditions are met. At this point, it sends a lane request to the perception model, indicating the desired lane position within the target toll station. Based on this, the perception model responds to the lane request by obtaining real-time first sensor data from sensors deployed on the target vehicle. Then, the perception model identifies the target lane's position within the target toll station based on the first sensor data. The target lane's position can be represented by coordinate data, or it can be represented by the target lane's relative position to all lanes within the target toll station. Subsequently, the intelligent driving system obtains the target lane's position from the perception model. Based on this position, the system can then determine its driving trajectory. Under the control of the intelligent driving system, the target vehicle follows this trajectory, thus entering the target lane.

[0104] It should be noted that the toll station access conditions in the above implementation methods also include: activating the automatic passage function of the target lane in the intelligent driving system. For example, such as... Figure 11 As shown in the diagram, in the settings interface of the intelligent driving system, a switch is set to enable the autonomous ETC communication at the toll station. Thus, based on the technical solution in this embodiment, the ETC lane in the toll station can be identified in real time, and the vehicle can autonomously pass through the ETC lane and then through the toll station.

[0105] It should also be noted that in this embodiment, there is no need to continuously send lane requests to the perception model. Lane requests are only sent to the perception model when the distance between the target vehicle and the target toll station at its current location is less than or equal to the second threshold. This reduces the number of times the perception model identifies the lane position of the target lane, reduces the data processing resources occupied by the onboard equipment, thereby reducing the power consumption of the onboard equipment and saving the data processing resources of the onboard equipment.

[0106] The above describes a vehicle control method provided by an embodiment of this application. The following describes an apparatus for performing the above vehicle control method.

[0107] Please see Figure 12 This is a schematic diagram of a vehicle control device provided in an embodiment of this application. The device can be configured in... Figure 2 The in-vehicle device shown is an example of a technology used in this embodiment to improve the accuracy of intelligent driving and enhance the user experience.

[0108] Specifically, the device in this embodiment may include the following units:

[0109] Perception Model 1201;

[0110] The intelligent driving system 1202 is used to obtain the driving trajectory of the target vehicle based on the lane position of the target lane in the target toll station output by the perception model in response to the target vehicle meeting the toll station passage conditions.

[0111] As can be seen from the above technical solution, in the vehicle control device provided in this application embodiment, when the target vehicle passes through the target toll station, the lane position of the target lane is detected by the perception model, and determined according to the lane position of the target lane. Therefore, it does not depend on whether there is a previously recorded lane position. Even if there is, it can not drive according to the previously recorded lane position, but obtain the driving trajectory according to the lane position of the target lane detected in real time by the perception model. There will be no situation where the intelligent driving is discontinued and the user takes over because there is no previously recorded lane position, nor will there be a situation where the previously recorded lane position is incorrect and the wrong lane is entered during the intelligent driving process. This improves the accuracy of vehicle intelligent driving and improves the user's experience of intelligent driving.

[0112] In one implementation, the intelligent driving system 1202 in this embodiment is further configured to: control the target vehicle to travel along the driving trajectory so that the target vehicle enters the target lane; detect the raising and lowering state of the barrier gate on the target lane, the raising and lowering state of the barrier gate being represented by the relative position of the barrier gate and the target lane; control the target vehicle to wait when the raising and lowering state indicates that the barrier gate is not fully raised; and control the target vehicle to continue driving when the raising and lowering state indicates that the barrier gate is fully raised so that the target vehicle passes through the target toll station.

[0113] In one implementation, when the intelligent driving system 1202 detects the raising and lowering state of the barrier on the target lane, it specifically performs the following steps: obtaining the first sensing data; the first sensing data is sensing data collected by at least one sensor deployed on the target vehicle; and obtaining the raising and lowering state of the barrier using a detection model based on the first sensing data.

[0114] In one implementation, the intelligent driving system 1202 in this embodiment is further configured to: display the target lane in the navigation interface of the target vehicle based on the lane position of the target lane output by the perception model.

[0115] In addition, the intelligent driving system 1202 is also used to: after the target vehicle enters the target lane, display the barrier on the navigation interface of the target vehicle according to the relative position of the barrier on the target lane and the target lane.

[0116] In one implementation, the toll station access condition includes: after sending a toll station request to the perception model, receiving the toll station location output by the perception model in response to the toll station request; wherein the toll station request is sent to the perception model when the target vehicle meets the travel progress condition; the perception model outputs the toll station location of the target toll station based on the first sensing data; the travel progress condition includes: the distance between the current location of the target vehicle and the target location corresponding to the target toll station is less than or equal to a first threshold.

[0117] In one implementation, the toll station access conditions include: the target toll station exists in the direction of travel of the target vehicle; and the distance between the current position of the target vehicle and the target position corresponding to the target toll station is less than or equal to a second threshold.

[0118] The intelligent driving system 1202 determines the lane position of the target lane in the target toll station output by the perception model in the following ways: sending a lane request to the perception model so that the perception model outputs the lane position of the target lane in the target toll station based on the second sensing data; and receiving the lane position of the target lane output by the perception model.

[0119] In one implementation, the target lane is an electronic toll collection lane at a toll station on a highway; or, the target lane is the lane with the least congestion at a toll gate in a parking lot.

[0120] It should be noted that the specific implementation methods of the intelligent driving system and perception model in this embodiment can be referred to the corresponding content above, and will not be detailed here.

[0121] refer to Figure 13 This is a schematic diagram of the structure of a vehicle-mounted device provided in an embodiment of this application. The vehicle-mounted device can be deployed on a target vehicle. Specifically, the vehicle-mounted device may include the following structure:

[0122] At least one sensor 1301, said sensor 1301 being used to collect sensing data;

[0123] At least one processor 1302, on which an intelligent driving system and a perception model are deployed;

[0124] The intelligent driving system is used to obtain the driving trajectory of the target vehicle based on the lane position of the target lane in the target toll station output by the perception model, in response to the target vehicle meeting the toll station passage conditions.

[0125] Additionally, the onboard equipment may include memory, input / output (I / O) interfaces, and a bus. The memory stores the data required for the operation of the intelligent driving system and the perception model, as well as the data generated by their respective operations. The processor 1502 and the memory are interconnected via the bus. The input / output (I / O) interfaces are also connected to the bus.

[0126] The in-vehicle equipment may also include the following devices, all of which can be connected to the input / output interface:

[0127] This includes input devices such as touchscreens, touchpads, cameras, microphones, accelerometers, and gyroscopes; output devices such as liquid crystal displays (LCDs), speakers, and vibrators; storage devices such as memory cards and hard drives; and communication devices. The communication devices allow the in-vehicle equipment to communicate wirelessly or wiredly with other devices to exchange data.

[0128] Although Figure 13 The vehicle-mounted equipment shown includes various devices; however, it should be understood that implementation or possession of all shown devices is not required. More or fewer devices may be implemented or possessed alternatively. Figure 13 The vehicle-mounted device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0129] As can be seen from the above technical solution, in the vehicle-mounted device provided in this application embodiment, when the target vehicle passes through the target toll station, the lane position of the target lane is detected by the perception model, and determined according to the lane position of the target lane. Therefore, it does not depend on whether there is a previously recorded lane position. Even if there is, it can not drive according to the previously recorded lane position, but obtain the driving trajectory according to the lane position of the target lane detected in real time by the perception model. There will be no situation where the intelligent driving is discontinued and the user takes over due to the absence of a previously recorded lane position, nor will there be a situation where the wrong lane is entered during the intelligent driving process due to an incorrect previously recorded lane position. This improves the accuracy of vehicle intelligent driving and enhances the user's experience of intelligent driving.

[0130] This application also provides a computer program product including computer-readable instructions, which, when executed on an in-vehicle device, cause the electronic device to implement any of the vehicle control methods provided in this application.

[0131] This application also provides a computer storage medium that carries one or more computer programs. When the one or more computer programs are executed by an in-vehicle device, the in-vehicle device can implement any of the vehicle control methods provided in this application.

[0132] The following example, using a vehicle passing through ETC (Electronic Toll Collection) as an example, illustrates the technical solution of this application:

[0133] Firstly, existing intelligent driving systems typically rely on prior information for toll station communication, such as previously recorded toll station locations and the locations of previously recorded ETC lanes within the toll station. Currently, the coverage of this prior information is limited, and its creation is costly, failing to fully meet user travel needs. At toll stations without prior information, the autonomous ETC passage function cannot be activated, or even if prior information is available, the ETC lane location may change, leading to lane entry errors even after activating the autonomous ETC passage function. This necessitates exiting intelligent driving mode before reaching the toll station, requiring the user to take over vehicle control in advance.

[0134] In view of this, this application proposes a technical solution for autonomous passage through toll stations using ETC in an intelligent driving system. Without relying on prior information, the intelligent driving system can automatically identify the location of toll stations and the lane positions of each ETC lane, thereby enabling autonomous passage through any toll station's ETC lane.

[0135] Specifically, the following describes the process and implementation results of the intelligent driving system for autonomous passage through toll stations using ETC (Electronic Toll Collection) users:

[0136] Step 1: Activate ETC at the toll station for self-service passage. (Example) Figure 14 As shown in the figure, in the intelligent driving system, the ETC passage switch at the toll station is pre-set to be turned on;

[0137] Step 2: Self-service ETC passage at the toll station, the steps are as follows:

[0138] A. Before the vehicle arrives at the toll station, a perception model, such as a visual language model (VLM), autonomously identifies the location of the toll station and the ETC lane. Figure 15 As shown, in the detailed navigation area of ​​the navigation interface, in addition to displaying the current vehicle speed and speed limit, it also displays the target vehicle's current lane and surrounding vehicles. In addition, an area can be divided in the detailed navigation area to output the real-time view in front of the vehicle.

[0139] B. The intelligent driving system automatically enters the ETC lane and waits for the barrier to lift. Figure 16 As shown in the diagram, in the detailed navigation area of ​​the navigation interface, in addition to displaying the current vehicle speed and speed limit, it also shows the target vehicle in the ETC lane based on the location of the ETC lane and the target vehicle, and displays the corresponding barrier gate of the ETC lane.

[0140] C. The intelligent driving system recognizes the raised state of the ETC lane gate, such as... Figure 17 As shown, in the detailed navigation area of ​​the navigation interface, the opening and closing of the barrier is displayed in real time according to its opening and closing status, such as its relative position to the ETC lane; the real-time display here can be understood as updating the opening and closing of the barrier every specific time interval, such as 1 second or 500 milliseconds.

[0141] D. After the barrier is raised, the intelligent driving system controls the vehicle to exit the toll station normally, such as... Figure 18 As shown in the image, after the barrier is fully raised, the vehicle passes through the ETC lane and then exits the toll station normally.

[0142] It should be noted that the navigation interface can display prompts for each of the above steps, such as... Figure 15 As shown in the image, this is a user notification: Please note that a toll station is approaching. Your vehicle will enter the ETC lane. The overview navigation area also displays the real-time distance to the toll station. Figure 17 The image shown is for illustrative purposes only: Please note that during ECT detection, the lane is narrow; please be aware of the curbs on both sides. Figure 18 The image shows a user notification: Please note that you are exiting a toll station. Please observe the roadside on both sides.

[0143] As can be seen, this application does not rely on prior information, but uses a visual language model (VLM) to identify the location of the toll station and the ETC lane, thereby enabling the intelligent driving system to control the vehicle to drive towards the ETC lane and pass through the gate without user intervention, thus improving the user's experience of intelligent driving. At the same time, it can also render the specific location of the ETC lane and the state of the gate opening to prompt the user with real-time information, further improving the user's experience of intelligent driving.

[0144] In summary, this application can bring users a seamless intelligent driving experience on urban highways and enable autonomous passage through ETC lanes at various toll stations.

[0145] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0146] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0147] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0148] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A vehicle control method, characterized in that, The method includes: In response to the target vehicle meeting the toll station passage conditions, the driving trajectory of the target vehicle is determined based on the lane position of the target lane in the target toll station output by the perception model.

2. The method according to claim 1, characterized in that, The method further includes: Control the target vehicle to travel along the driving trajectory so that the target vehicle enters the target lane; The raising and lowering state of the barrier arm on the target lane is detected, and the raising and lowering state of the barrier arm is represented by the relative position of the barrier arm and the target lane; When the lifting / lowering state indicates that the barrier is not fully raised, the target vehicle is controlled to wait. When the barrier is fully raised in the lifting / lowering state, the target vehicle is controlled to continue driving so that it passes through the target toll station.

3. The method according to claim 2, characterized in that, The detection of the raising and lowering state of the barrier gate on the target lane includes: Obtain first sensing data; the first sensing data is sensing data collected by at least one sensor deployed on the target vehicle; Based on the first sensor data, the raising and lowering state of the barrier is obtained using a detection model.

4. The method according to claim 1, 2 or 3, characterized in that, The method further includes: Based on the lane position of the target lane, the target lane is displayed in the navigation interface of the target vehicle.

5. The method according to claim 2, characterized in that, After the target vehicle enters the target lane, the method further includes: Based on the relative position of the barrier on the target lane and the target lane, the barrier is displayed on the navigation interface of the target vehicle.

6. The method according to claim 1, 2, 3, 4 or 5, characterized in that, The toll station access conditions include: after sending a toll station request to the perception model, receiving the toll station location output by the perception model in response to the toll station request; The toll station request is sent to the perception model when the target vehicle meets the travel progress condition; the perception model outputs the toll station location of the target toll station based on the first sensor data. The driving progress condition includes: the distance between the current position of the target vehicle and the target position corresponding to the target toll station is less than or equal to a first threshold.

7. The method according to claim 1, 2, 3, 4, 5 or 6, characterized in that, The toll station access conditions include: the target toll station exists in the direction of travel of the target vehicle; and the distance between the current position of the target vehicle and the target position corresponding to the target toll station is less than or equal to a second threshold. Wherein, in response to the target vehicle meeting the toll station passage conditions, the lane position of the target lane in the target toll station output by the perception model is determined in the following way: A lane request is sent to the perception model so that the perception model outputs the lane position of the target lane in the target toll station based on the second sensor data. Receive the lane position of the target lane output by the perception model.

8. The method according to claim 1, characterized in that, The target lane is the electronic non-stop toll collection lane in the toll station of the highway; Alternatively, the target lane is the lane with the least congestion among the toll gates in the parking lot.

9. A vehicle control device, characterized in that, The device includes: Perceptual model; An intelligent driving system is used to obtain the driving trajectory of a target vehicle based on the lane position of the target lane in the target toll station output by the perception model, in response to the target vehicle meeting the toll station passage conditions.

10. A vehicle-mounted device, characterized in that, include: At least one sensor, said sensor being used to acquire sensing data; At least one processor, on which an intelligent driving system and a perception model are deployed; The intelligent driving system is used to obtain the driving trajectory of the target vehicle based on the lane position of the target lane in the target toll station output by the perception model, in response to the target vehicle meeting the toll station passage conditions.

Images