Projection headlight control method and device for vehicle and intelligent vehicle

Abstract

This application relates to a method, apparatus, and intelligent vehicle for controlling projection headlights, comprising: acquiring multimodal road condition perception data of the vehicle's external surrounding environment; drawing a temporary road semantic map of the external surrounding environment based on the multimodal road condition perception data; the temporary road semantic map being used to mark passable roads in the external surrounding environment and road condition information of the passable roads; determining a driving scenario matching the temporary road semantic map as the current driving scenario; matching the scenario label associated with the current driving scenario with the road condition information associated with the temporary road semantic map; and driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to projection headlight control parameters matching the current driving scenario. This method can improve the driving environment adaptability of the projection headlights projecting driving instructions.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a method, device, intelligent vehicle, computer-readable storage medium, and computer program product for controlling the projection headlights of a vehicle. Background Technology

[0002] With the rapid development of intelligent and connected vehicles, vehicle projection headlights have gradually evolved from a single lighting function into an important carrier integrating intelligent human-machine interaction and driver assistance functions.

[0003] Traditional vehicle projection navigation technologies often rely on high-precision maps and Global Navigation Satellite Systems (GNSS). Based on these maps and GNSS, vehicles can determine their current geographical location. Then, they retrieve projection patterns that match their current location from a pre-set pattern library, such as left-turn arrows, exit guide lines, and lane keeping boundaries. The vehicle's projection headlights (e.g., DLP (Digital Light Processing) headlights) then project these predefined patterns onto the road surface.

[0004] However, when a vehicle travels to an area outside the map data coverage area or is obstructed or interfered with by tunnels, dense building complexes, or inclement weather, the vehicle often cannot obtain an accurate current geographical location. This also makes it impossible for the vehicle to retrieve a matching projection pattern from the preset pattern library, causing the vehicle to lose the function of providing driving guidance through projection headlights and making it unable to effectively adapt to complex and ever-changing driving environments.

[0005] Therefore, the method of projecting driving instruction information based on projection headlights in related technologies has the problem of weak adaptability to driving environment. Summary of the Invention

[0006] Therefore, it is necessary to provide a vehicle projection headlight control method, device, intelligent vehicle, computer-readable storage medium, and computer program product that can improve the driving environment adaptability of the projection headlights' driving instructions, thereby addressing the aforementioned technical problems.

[0007] In a first aspect, this application provides a method for controlling the projection headlights of a vehicle, the method comprising:

[0008] Acquire multimodal road condition perception data of the vehicle's external surrounding environment;

[0009] Based on the multimodal road condition perception data, a temporary road semantic map of the surrounding environment outside the vehicle is drawn; the temporary road semantic map is used to mark the passable roads in the surrounding environment outside the vehicle, as well as the road condition information of the passable roads;

[0010] The driving scenario that matches the temporary road semantic map is identified as the current driving scenario; the scenario label associated with the current driving scenario matches the road condition information associated with the temporary road semantic map;

[0011] According to the projection headlight control parameters matched with the current driving scenario, the vehicle's projection headlight assembly is driven to project driving instruction information that matches the current driving scenario onto the road surface.

[0012] In one embodiment, after the step of determining that the driving scenario matching the temporary road semantic map is the current driving scenario, the method further includes:

[0013] In response to the vehicle navigation system's operating status meeting preset availability conditions, the vehicle high-precision positioning data output by the vehicle navigation system is acquired;

[0014] The scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data is retrieved from the preset high-precision map resources to obtain the target scene label; the high-precision map resources record the mapping relationship between preset geographical locations and preset scene labels;

[0015] If the driving scenario associated with the target scenario label is inconsistent with the driving scenario matched by the temporary road semantic map, the driving scenario associated with the target scenario label is determined to be the new current driving scenario.

[0016] In one embodiment, the step of querying a scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data from a preset high-precision map resource to obtain the target scene label includes:

[0017] The scene labels corresponding to the geographical locations represented by the vehicle's high-precision positioning data are retrieved from the preset high-precision map resources to obtain candidate scene labels;

[0018] Acquire real-time road condition data and real-time environmental data collected by the vehicle;

[0019] Based on the real-time traffic data and real-time environmental data, the candidate scene labels are adjusted to obtain the target scene labels.

[0020] In one embodiment, the projection headlight control parameters include at least the road surface light carpet width parameter, and driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched to the current driving scenario includes:

[0021] When the current driving scenario is a driving scenario with lane markings, the lane marking spacing of the lane where the vehicle is currently located is obtained, and the road light carpet width parameter that matches the lane marking spacing is used to drive the projection headlight assembly to project a first road light carpet onto the road surface in front of the vehicle.

[0022] or,

[0023] When the current driving scenario is a driving scenario without lane markings, the maximum vehicle width is obtained, and the projection headlight assembly is driven to project a second road surface light blanket onto the road surface in front of the vehicle according to the road surface light blanket width parameter that matches the maximum vehicle width.

[0024] In one embodiment, the projection headlight control parameters include the projection coordinates of navigation markers on the road surface ahead of the vehicle. Driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched to the current driving scenario includes:

[0025] Obtain the current navigation command of the vehicle, and generate a target navigation identifier to be projected that matches the current driving scenario based on the current navigation command;

[0026] The road surface parameters in the temporary road semantic map are analyzed, and the projection coordinates of the target navigation mark on the road surface are determined based on the installation parameters of the projection headlight assembly and the road surface parameters.

[0027] According to the projection coordinates of the target navigation mark on the road surface, the projection headlight assembly is controlled to project the target navigation mark onto the road surface.

[0028] In one embodiment, after the step of driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to projection headlight control parameters matched to the current driving scenario, the method further includes:

[0029] The projected image is captured by an external camera; the projected image is a superimposed image of the driving instruction information and the actual road surface.

[0030] Based on the difference between the feature points of the driving instruction information in the projected image and the feature points of the actual lane road surface in the projected image, the projection error description information of the projection headlight assembly is determined;

[0031] If the projection error description information meets the preset calibration conditions, the projection vehicle headlight assembly is calibrated according to the projection error description information; the calibration operation includes, in sequence, projection angle calibration, projection position calibration, projection distortion calibration, and projection brightness calibration.

[0032] Return to the step of acquiring the projection effect image through the vehicle's external camera until the projection error description information no longer meets the preset calibration conditions.

[0033] Secondly, this application also provides a projection headlight control device for a vehicle, the device comprising:

[0034] The data acquisition module is used to acquire multimodal road condition perception data of the vehicle's external surrounding environment;

[0035] The map drawing module is used to draw a temporary road semantic map of the surrounding environment outside the vehicle based on the multimodal road condition perception data; the temporary road semantic map is used to mark the passable roads in the surrounding environment outside the vehicle, as well as the road condition information of the passable roads;

[0036] The scene matching module is used to determine the driving scene that matches the temporary road semantic map as the current driving scene; the scene tag associated with the current driving scene matches the road condition information associated with the temporary road semantic map;

[0037] The information projection module is used to drive the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters that match the current driving scenario.

[0038] Thirdly, this application also provides an intelligent vehicle, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0039] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0040] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0041] The aforementioned vehicle projection headlight control method, device, intelligent vehicle, computer-readable storage medium, and computer program product acquire multimodal road condition perception data of the vehicle's external environment and, based on this data, create a temporary road semantic map of the external environment. This temporary road semantic map is used to label passable roads and their road condition information. The driving scenario matching the temporary road semantic map is then determined as the current driving scenario. The scenario label associated with the current driving scenario is matched with the road condition information associated with the temporary road semantic map, and then... The projection headlight control parameters matched to the current driving scenario drive the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface. In this way, even if the vehicle travels to an area outside the map data coverage or is obstructed or interfered with by tunnels, dense building clusters, or inclement weather, the vehicle can still use the multimodal road condition perception data collected by the perception unit to draw a temporary road semantic map of the surrounding environment outside the vehicle, and control the projection headlights based on this temporary road semantic map to provide the driver with clear and timely driving guidance, thereby improving the driving environment adaptability of the projection headlights to project driving instructions. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is an application environment diagram of a vehicle projection headlight control method in one embodiment;

[0044] Figure 2 This is a flowchart illustrating a method for controlling the projection headlights of a vehicle in one embodiment.

[0045] Figure 3 This is a flowchart illustrating a method for controlling the projection headlights of a vehicle in another embodiment;

[0046] Figure 4 This is a structural block diagram of a projection headlight control device for a vehicle in one embodiment;

[0047] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] This application provides a method for controlling the projection headlights of a vehicle, which can be applied to, for example... Figure 1 In the application environment shown, the control unit of vehicle 100 can acquire multimodal road condition perception data of the vehicle's external surrounding environment; then, the control unit of vehicle 100 draws a temporary road semantic map of the external surrounding environment based on the multimodal road condition perception data; the temporary road semantic map is used to mark the passable roads in the external surrounding environment and the road condition information of the passable roads; then, the control unit of vehicle 100 determines the driving scenario that matches the temporary road semantic map as the current driving scenario; the scenario label associated with the current driving scenario matches the road condition information associated with the temporary road semantic map; finally, the control unit of vehicle 100 drives the vehicle's projection headlight assembly to project driving instruction information that matches the current driving scenario onto the road surface according to the projection headlight control parameters that match the current driving scenario.

[0050] In one exemplary embodiment, such as Figure 2 As shown, a method for controlling the projection headlights of a vehicle is provided, which is applied to... Figure 1 Taking the control unit of vehicle 100 as an example, the explanation includes the following steps S202 to S208. Wherein:

[0051] Step S202: Obtain multimodal road condition perception data of the vehicle's external surrounding environment.

[0052] In practice, the vehicle's control unit can detect the operating status of the vehicle's navigation system. If it is determined that the operating status of the vehicle's navigation system does not meet the preset availability conditions, the vehicle's control unit can acquire multimodal road condition perception data of the vehicle's surrounding environment.

[0053] Among them, the preset availability conditions can refer to the vehicle navigation system being able to receive high-precision positioning signals (such as GNSS+RTK signals) normally, and being able to load high-precision map data covering the current driving area from local or cloud sources.

[0054] Among them, situations that do not meet the preset availability conditions may include, but are not limited to: vehicles traveling on rural roads or old urban roads without high-precision map coverage, or the loss of positioning signals or a sharp drop in accuracy due to tunnels or dense buildings blocking the view.

[0055] The multimodal road condition perception data can include laser point cloud data collected by the front-facing LiDAR, road image data collected by the front-view camera (such as lane markings, curbs, obstacles, traffic signs, etc.), millimeter-wave radar detection data, and UWB (Ultra-Wideband) detection data collected by the UWB anchor point component. In practical applications, the UWB anchor points are arranged around the vehicle body, such as two UWB anchor points on the front bumper, two on the rear bumper, and one on each side door. The UWB anchor points on the front bumper can be positioned at a preset first angle towards the ground to facilitate close-range parking detection; the UWB anchor points on the rear bumper can be positioned horizontally towards the rear of the vehicle to facilitate rear blind spot detection; and the UWB anchor points on the side doors can be positioned at a preset second angle to facilitate side blind spot detection. In practical applications, UWB anchor points use high-gain broadband directional planar antennas to improve signal penetration and detection stability.

[0056] Step S204: Based on the multimodal road condition perception data, draw a temporary road semantic map of the surrounding environment outside the vehicle.

[0057] The temporary road semantic map is used to mark the passable roads in the surrounding environment outside the vehicle, as well as the road condition information of the passable roads.

[0058] In practical implementation, the vehicle's control unit can use a convolutional neural network (CNN) model to perform semantic segmentation on road images from multimodal road condition perception data. For example, elements such as road surface, lane lines, shoulders, pedestrians, and vehicles in the road image can be labeled with pixels of different colors. Simultaneously, the vehicle's control unit can align the coordinates of LiDAR point cloud data with the segmented image, so that each semantic element in the road image is associated with corresponding three-dimensional spatial information. Then, based on the corresponding three-dimensional spatial information associated with each semantic element in the road image, the vehicle's control unit can draw a temporary road semantic map centered on the vehicle with a preset radius. This temporary road semantic map is used to label one or more passable roads, as well as road condition information for those roads, such as "construction area 50 meters ahead" or "left lane line blurred."

[0059] Step S206: Determine the driving scenario that matches the temporary road semantic map as the current driving scenario.

[0060] Among them, the scene label associated with the current driving scenario is matched with the road condition information associated with the temporary road semantic map.

[0061] The current driving scenario can refer to the driving scenario determined by scenario matching based on road condition information in a temporary road semantic map.

[0062] In practice, the vehicle's control unit can parse the label information in the temporary road semantic map. For example, when the temporary road semantic map is labeled with "construction area" and the "detour route" is identified, the vehicle's control unit can confirm that the current driving scenario is a temporary road closure scenario; when the temporary road semantic map displays "marking status" as "no markings" and "road type" as "rural road", the vehicle's control unit can confirm that the current driving scenario is a rural road scenario.

[0063] Step S208: According to the projection headlight control parameters that match the current driving scenario, drive the vehicle's projection headlight assembly to project driving instruction information that matches the current driving scenario onto the road surface.

[0064] The projection headlight control parameters refer to a set of parameters that are pre-set or dynamically generated for a specific driving scenario to control the projection headlights. These parameters may include projection content encoding, projection coordinate parameters, projection angle, projection brightness, projection duration, projection effect, and projection light carpet width parameters.

[0065] In practice, when the current driving scenario is determined to be a rural road scenario, the vehicle's control unit can query or generate a set of projection headlight control parameters that match the current driving scenario. For example, these projection headlight control parameters include: setting the light carpet width to the vehicle body width, setting the light carpet color to white, projecting a blue arc light strip on the inside of curves to warn of blind spots, and projecting dynamic turn arrows at intersections based on the branch road directions in the temporary road semantic map.

[0066] Then, the vehicle's control unit can drive the vehicle's projection headlight assembly to project driving instruction information that matches the current driving scenario onto the road surface, according to the projection headlight control parameters.

[0067] In practical applications, when the driving instruction information is a warning information, different driving scenarios have different danger warning levels; the vehicle's control unit can obtain the danger warning level of the current driving scenario; based on the projection headlight control parameters that match the danger warning level of the current driving scenario, driving instruction information that matches the current driving scenario is projected onto the road.

[0068] The hazard warning levels can include high-risk, medium-risk, and low-risk warning levels. The projection headlight control parameters for different hazard warning levels can be used to achieve the following projection rules:

[0069] Under high-risk warning levels, the vehicle's control unit can drive the vehicle's projection headlight assembly to project a flashing red box onto the target object (pedestrian, obstacle) on the road. The flashing red box is used to select the outline of the target object. At the same time, the projection headlight assembly projects a dynamic distance scale and a deceleration pattern. The dynamic distance scale is used to indicate the distance between the vehicle and the target object, and the deceleration pattern is used to remind the driver to slow down in time and to inform pedestrians outside the vehicle to pay attention and avoid the obstacle.

[0070] At the medium-risk warning level, the vehicle's control unit can drive the vehicle's projection headlight assembly to project a yellow dynamic arrow (the yellow dynamic arrow can flash in segments to point to the direction of movement of the target object) and a yellow warning circle (the size of the yellow warning circle changes with the distance between the vehicle and the target object to remind the driver to pay attention).

[0071] Under low-risk warning levels, the vehicle's control unit can drive the vehicle's projection headlight assembly to project a green safety zone sign, indicating to the driver that there is no collision risk in the current area.

[0072] In practical applications, the above-mentioned projected content has different projection priorities. Specifically, the projection priority of hazard warning projection content is greater than that of driving guidance projection content, and the projection priority of driving guidance projection content is greater than that of conventional lighting projection content.

[0073] In addition, the vehicle's control unit can connect to the audio-visual warning module and seat vibration module in the passenger compartment. When the vehicle's projection headlights project warning information onto the road, the audio-visual warning module simultaneously emits a buzzer warning that matches the hazard warning level of the current driving scenario (e.g., a high-frequency buzzer signal for a high-hazard warning level; a medium-frequency buzzer signal for a medium-hazard warning level; and a low-frequency buzzer signal for a low-hazard warning level). Simultaneously, the seat vibration module can output a vibration warning signal corresponding to the direction of danger (e.g., vibration of the right side of the seat when a vehicle approaches from the right).

[0074] Optionally, the vehicle's control unit can determine the projection lead N of the driving instruction information based on the hazard warning level and the vehicle's current speed (the projection lead N represents the projection of the warning information of the target object when the vehicle is N meters away from the target object). Taking the scenario of the vehicle projecting the warning information of the target object A (e.g., a pedestrian or obstacle) as an example, during the vehicle's operation, the vehicle can obtain the current distance D between the vehicle and the target object A. If the current distance D is less than or equal to the projection lead N corresponding to the warning information, the vehicle's control unit drives the vehicle's projection headlight assembly to project the warning information of the target object A onto the road surface.

[0075] In practical applications, the projection lead time of driving instruction information is positively correlated with the hazard warning level, and also positively correlated with the vehicle's current speed. In other words, the higher the hazard warning level, the higher the projection lead time of the driving instruction information. For example, under a high-hazard warning level, the projection lead time N can be set to 50 meters; under a medium-hazard warning level, it can be set to 40 meters; and under a low-hazard warning level, it can be set to 30 meters.

[0076] In the aforementioned vehicle projection headlight control method, multimodal road condition perception data of the vehicle's external environment is acquired, and a temporary road semantic map of the external environment is drawn based on the multimodal road condition perception data. The temporary road semantic map is used to mark the passable roads in the external environment and the road condition information of the passable roads. Then, the driving scenario matching the temporary road semantic map is determined as the current driving scenario. The scenario label associated with the current driving scenario is matched with the road condition information associated with the temporary road semantic map, and the projection headlight component of the vehicle is driven to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched with the current driving scenario. In this way, even if the vehicle travels to an area outside the map data coverage area or is blocked or interfered with by tunnels, dense building clusters, or bad weather, the vehicle can still draw a temporary road semantic map of the external environment through the multimodal road condition perception data collected by the perception unit, and control the projection headlights based on the temporary road semantic map to provide the driver with clear and timely driving guidance, thereby improving the driving environment adaptability of the projection headlights to project driving instructions.

[0077] In an exemplary embodiment, after determining that the driving scenario matching the temporary road semantic map is the current driving scenario, the method further includes: in response to the vehicle navigation system's operating state meeting preset availability conditions, obtaining high-precision positioning data of the vehicle output by the vehicle navigation system; querying the scene label corresponding to the geographical location represented by the vehicle high-precision positioning data in preset high-precision map resources to obtain a target scene label; and determining that the driving scenario associated with the target scene label is the new current driving scenario if the driving scenario associated with the target scene label is inconsistent with the driving scenario matching the temporary road semantic map.

[0078] High-definition map resources record the mapping relationship between preset geographical locations and preset scene labels. In practical applications, high-definition map resources include the geometry and topology of roads, and record the mapping relationship between preset geographical locations (such as specific intersections, ramps, construction areas, scenic spot entrances, etc.) and preset scene labels. In practical applications, high-definition map resources can be a high-definition map scene label library.

[0079] In practice, the vehicle's control unit obtains the vehicle's high-precision positioning data output by the vehicle's navigation system. The vehicle's control unit can then query the scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data from the preset high-precision map resources to obtain the target scene label.

[0080] Then, the vehicle's control unit can compare whether the driving scenario associated with the target scenario label is consistent with the driving scenario matched by the temporary road semantic map. If the driving scenario associated with the target scenario label is consistent with the driving scenario matched by the temporary road semantic map, the vehicle's control unit determines that the driving scenario associated with the target scenario label is the new current driving scenario, and returns to the step of executing the step of driving the vehicle's projection headlight assembly to project driving instruction information that matches the current driving scenario onto the road surface according to the projection headlight control parameters that match the current driving scenario.

[0081] For example, when a vehicle enters a highway from a rural road, its navigation system can receive high-precision positioning signals (such as GNSS+RTK signals) and load high-precision map data covering the current driving area from the cloud. The vehicle's control unit can then use the high-precision positioning data output by the navigation system to query the high-precision map data covering the current driving area for scene tags corresponding to the geographical location represented by the vehicle's high-precision positioning data, obtaining the target scene tag, such as "lane line" or "highway." The driving scenario associated with this target scene tag is determined to be a highway scenario.

[0082] Then, the vehicle's control unit can compare the driving scenario associated with the target scenario label with the driving scenario matched by the temporary road semantic map. For example, if the driving scenario "highway scenario" associated with the target scenario label is inconsistent with the driving scenario "rural road scenario" matched by the temporary road semantic map, the vehicle's control unit can take the driving scenario "highway scenario" associated with the target scenario label as the current driving scenario of the vehicle due to the reliability of the high-precision map and positioning data. The vehicle's control unit no longer needs to rely on the real-time perception data collected by the perception unit to identify the current driving scenario of the vehicle.

[0083] Then, the vehicle's control unit can query or generate a set of projection headlight control parameters that match the current driving scenario. The vehicle's control unit can then drive the projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to these parameters. It should be noted that the specific process by which the vehicle's control unit drives the projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters can be found above and will not be repeated here.

[0084] The technical solution of this embodiment, in response to the vehicle navigation system's operating state meeting preset availability conditions, queries the preset high-precision map resources to find the scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data, obtains the target scene label, and when the driving scene associated with the target scene label is inconsistent with the driving scene matched by the temporary road semantic map, prioritizes the use of high-precision map resources to determine the vehicle's current driving scene. This can effectively divert the load of the vehicle performing real-time mapping based on real-time perception data, and effectively achieve optimized allocation of system resources.

[0085] In an exemplary embodiment, querying the scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data in a preset high-precision map resource to obtain the target scene label includes: querying the scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data in a preset high-precision map resource to obtain candidate scene labels; acquiring real-time traffic data and real-time environmental data collected by the vehicle; and adjusting the candidate scene labels according to the real-time traffic data and real-time environmental data to obtain the target scene label.

[0086] Real-time traffic data can refer to dynamic information such as whether other vehicles are occupying the current lane, whether there is temporary traffic control or construction barriers, and whether pedestrians are crossing the road.

[0087] Real-time environmental data can refer to dynamic information such as whether it is day or night, weather conditions (rain, snow, fog), and ambient light intensity.

[0088] In practice, the vehicle's control unit queries a pre-defined high-precision map resource to find scene labels corresponding to the geographical location represented by the vehicle's high-precision positioning data. During the process of obtaining the target scene label, the control unit can integrate real-time collected dynamic data to obtain a more accurate target scene label. Specifically, the control unit can query the high-precision map resource (i.e., the high-precision map library) based on the vehicle's high-precision positioning data output by the navigation system to find candidate scene labels matching the vehicle's current geographical location. For example, if the vehicle is approaching an intersection and the navigation route indicates a left turn, the control unit can determine the candidate scene labels as "left turn guidance," "lane boundary," and "low projection brightness." Then, the control unit can acquire real-time traffic and environmental data collected by the vehicle; based on the real-time traffic and environmental data, it adjusts the candidate scene labels to obtain the target scene label. For example, if the control unit determines, based on the real-time traffic and environmental data, that there is a pedestrian on the left, an oncoming vehicle, or a street light malfunction, the control unit can adjust the candidate scene labels to obtain the target scene label. For example, the control unit can determine that the target scene label is "left turn guidance", "pedestrian reminder", "lane boundary" and "high level of projection brightness", so that the driving projection headlight assembly will prioritize projecting the driving guidance patterns of "left turn arrow", "lane keeping line" and "pedestrian reminder".

[0089] For example, when a vehicle approaches a complex five-way intersection, and the navigation route indicates that it should exit from the third exit, the vehicle's control unit can determine the candidate scenario label as "multi-way intersection scenario." If the control unit detects a temporary electronic sign at the intersection indicating "third exit closed" through a camera, it can adjust the candidate scenario label "multi-way intersection scenario" to the target scenario label "multi-way intersection scenario" and "third exit closed." Subsequently, based on the driving scenario matched by this target scenario label, the control unit can drive the projection headlights to project a red no-entry sign in front of the third exit on the road where the vehicle is located.

[0090] The technical solution of this embodiment dynamically optimizes the scene labels initially determined based on high-precision map data according to the real-time road condition data and real-time environmental data collected by the vehicle. This avoids redundant or delayed prompts and effectively prevents incorrect or incomplete driving guidance due to outdated or insufficient high-precision map data, thereby effectively improving vehicle driving safety.

[0091] In an exemplary embodiment, the projection headlight control parameters include at least the road surface light carpet width parameter. According to the projection headlight control parameters matched with the current driving scenario, the projection headlight assembly of the vehicle is driven to project driving instruction information matched with the current driving scenario onto the road surface, including: when the current driving scenario is a driving scenario with lane markings, obtaining the lane marking spacing of the lane where the vehicle is currently located, and driving the projection headlight assembly to project a first road surface light carpet onto the road surface in front of the vehicle according to the road surface light carpet width parameter matched with the lane marking spacing.

[0092] In the current driving scenario without lane markings, the maximum vehicle width is obtained, and the projection headlight assembly is driven to project a second road surface light blanket onto the road surface in front of the vehicle according to the road surface light blanket width parameter that matches the maximum vehicle width.

[0093] Among them, the road surface light blanket width parameter can refer to the control parameter used to control the width of the road surface light blanket projected by the vehicle's projection headlights.

[0094] Among them, driving scenarios with lane markings refer to driving scenarios where the vehicle is currently located on both sides of the road with clearly visible and standard lane dividing lines or lane edge lines.

[0095] Lane marking spacing refers to the distance between two parallel lane markings. In practical applications, the vehicle's control unit can identify lane marking spacing in real time using external cameras.

[0096] Among them, the driving scenario without lane markings refers to the vehicle being on a rural road without lane markings, a road within a residential area, or a temporary road where the lane markings have been worn or covered.

[0097] In practice, during the process of driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched with the current driving scenario:

[0098] When the current driving scenario is determined to be a driving scenario with lane markings (for example, the vehicle is driving on a highway with clear lane markings), the vehicle's control unit can continuously capture the road image in front of the vehicle through the forward-facing camera, and identify the two right lane lines in the road image in front of the vehicle through a pre-trained image recognition network, calculate the distance between the two parallel lane markings, and obtain the lane marking spacing of the lane where the vehicle is currently located.

[0099] Then, the vehicle's control unit can determine the width parameters of the road surface light carpet that match the lane marking spacing, such as a target width of 3.5 meters; and according to the road surface light carpet width parameters, drive the projection headlight assembly to project the first road surface light carpet onto the road surface in front of the vehicle, so that the first road surface light carpet can cover the road surface of the lane where the vehicle is currently located, thereby marking the vehicle's driving boundary, and will not be projected onto adjacent lanes to interfere with other vehicles.

[0100] When the current driving scenario is determined to be a lane-marked driving scenario (e.g., a vehicle entering a village road from a highway), the vehicle's control unit can switch the road surface light carpet from lane marking adaptation mode to vehicle body adaptation mode. Specifically, the vehicle's control unit can access stored vehicle body width data (e.g., a maximum vehicle body width of 1.95 meters). Then, the vehicle's control unit can determine the road surface light carpet width parameters that match the lane marking spacing. In practical applications, the road surface light carpet width can be the sum of the maximum vehicle body width and a preset safety distance (e.g., 0.1 meters). The vehicle's control unit can then drive the projection headlight assembly to project a second road surface light carpet onto the road surface in front of the vehicle according to this road surface light carpet width parameter. This ensures that the width of the second road surface light carpet matches the vehicle body width, thus marking the vehicle's physical boundaries and providing the driver with a visual reference on lane-marked roads, avoiding the risk of scraping or deviating from the road surface due to a lack of perception of road width.

[0101] The technical solution of this embodiment effectively improves the adaptability of the road light carpet projected by the projection headlight assembly to different driving scenarios by using different road light carpet width modes in driving scenarios with lane markings and driving scenarios without lane markings. This effectively provides the driver with driving guidance information that meets the current driving scenario and improves driving safety.

[0102] In an exemplary embodiment, the projection headlight assembly of the vehicle is driven to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched with the current driving scenario. This includes: obtaining the vehicle's current navigation command; generating a target navigation identifier to be projected that matches the current driving scenario based on the current navigation command; parsing the road surface parameters in the temporary road semantic map; determining the projection coordinates of the target navigation identifier on the road surface based on the installation parameters of the projection headlight assembly and the road surface parameters; and controlling the projection headlight assembly to project the target navigation identifier onto the road surface according to the projection coordinates of the target navigation identifier on the road surface.

[0103] Among them, the projection headlight control parameters include the projection coordinates of the navigation sign on the road surface in front of the vehicle.

[0104] The current navigation instruction is a specific driving instruction issued by the navigation system, such as "300 meters ahead, turn left onto XX Road", etc.

[0105] The target navigation markers are navigation patterns dynamically generated based on the current navigation instructions and projected onto the road surface. Examples include turn arrows, lane markings, distance indicators, or lane selection markers. The style of the target navigation markers can be matched to the current driving scenario.

[0106] Among them, road surface parameters are physical three-dimensional characteristic parameters used to describe the road surface, such as road surface slope, curve curvature, and road surface smoothness.

[0107] The installation parameters of the projection vehicle light assembly may include the inherent physical parameters of the projection vehicle light assembly, such as installation height, pitch angle, horizontal deflection angle, and focal length.

[0108] In practice, when the vehicle's control unit drives the projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched with the current driving scenario, the vehicle's control unit can generate a target navigation sign to be projected that matches the current driving scenario based on the current navigation command. For example, when the vehicle is on a highway exit ramp and the current navigation command is "drive to the right and enter the ramp", the control unit can query the target navigation sign of "exit instruction arrow" from the preset navigation sign library.

[0109] Then, the vehicle's control unit can parse the road surface parameters in the temporary road semantic map and determine the projected coordinates of the target navigation sign on the road surface based on the installation parameters of the projection headlight assembly and the road surface parameters. For example, if the vehicle's control unit determines that the road surface in front of the vehicle is uphill, the control unit reads the installation parameters of the DLP projection module, such as installation height and pitch angle. The vehicle's control unit can use a perspective projection transformation model (a mapping model that records the virtual coordinates of the navigation sign and the actual projected coordinates of the road surface) to determine the projected coordinates of the target navigation sign on the road surface. For example, to cope with uphill roads, the vehicle's control unit can use the perspective projection transformation model to stretch the projected pattern forward and upward, so that the visual effect of the right-turn arrow projected on the slope is a standard right-turn arrow.

[0110] Then, the vehicle's control unit can control the projection headlight assembly to project the target navigation sign onto the road surface according to the projection coordinates of the target navigation sign on the road surface.

[0111] The technical solution of this embodiment obtains the vehicle's current navigation command, generates a target navigation sign matching the current driving scenario based on the current navigation command, and parses the road surface parameters in the temporary road semantic map. Based on the installation parameters of the projection headlight assembly and the road surface parameters, the projection coordinates of the target navigation sign on the road surface are determined. According to the projection coordinates of the target navigation sign on the road surface, the projection headlight assembly is controlled to project the target navigation sign onto the road surface. This allows the driving guidance information projected by the projection headlight assembly to adapt to different road surfaces, avoids visual misalignment caused by road surface deformation, and improves the usability of the projected navigation information.

[0112] In an exemplary embodiment, after the step of driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched with the current driving scenario, the method further includes: acquiring a projection effect image through an external camera; determining projection error description information of the projection headlight assembly based on the difference between the feature points of the driving instruction information in the projection effect image and the feature points of the actual lane road surface in the projection effect image; if the projection error description information meets preset calibration conditions, performing a calibration operation on the projection headlight assembly based on the projection error description information; the calibration operation sequentially includes a projection angle calibration operation, a projection position calibration operation, a projection distortion calibration operation, and a projection brightness calibration operation; returning to the step of acquiring the projection effect image through the external camera until the projection error description information no longer meets the preset calibration conditions.

[0113] The projected image is a superimposed image of driving instruction information and the actual road surface. Specifically, the projected image refers to a superimposed image captured by an external camera outside the vehicle, which includes driving instruction information projected onto the road surface (such as light carpets, arrows, and warning strips) and the actual road surface (such as lane lines, curbs, and obstacles).

[0114] In practice, after the vehicle's control unit drives the projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface, the control unit can perform closed-loop calibration and optimization of the driving instruction information to correct the projection error of the projection headlight assembly. Specifically, the vehicle's control unit can acquire images (i.e., projection effect images) of the area in front of the vehicle through an external camera mounted behind the windshield at a preset acquisition frequency. Then, taking the driving instruction information in the projection effect image as a light carpet as an example, the vehicle's control unit can extract the left edge feature points of the light carpet in the projection effect image and the left edge feature points of the lane line projection effect image. By comparing the coordinate deviation of these two left edge feature points, the projection error description information of the projection headlight assembly is determined.

[0115] Among them, projection error description information is a quantitative indicator that characterizes the deviation between the current projection effect and the ideal projection state. Examples include indicators such as lateral deviation, distortion rate, and brightness uniformity.

[0116] The preset calibration conditions determine whether calibration should be initiated. For example, any one of the following conditions must be met: the lateral deviation of the projection headlight assembly exceeds a preset first threshold; the distortion rate of the projection headlight assembly exceeds a preset second threshold; or the brightness uniformity of the projection headlight assembly exceeds a preset third threshold.

[0117] Once the vehicle's control unit determines that the projection error description information of the projection headlight assembly meets the preset calibration conditions, the control unit can perform calibration operations on the projection headlight assembly based on the projection error description information. In practical applications, the projection headlight assembly can be calibrated sequentially according to four dimensions: projection angle, projection position, projection distortion, and projection brightness. Specifically, the projection angle can be adjusted by driving the motor of the projection headlight assembly to rotate; the projection position can be adjusted by adjusting the projection coordinates of the target navigation mark on the road surface; the distortion rate of the projection headlight assembly can be adjusted by controlling the flip frequency and pixel distribution of the DMD micromirrors; and the brightness uniformity of the projection headlight assembly can be adjusted by adjusting the brightness of the edge area of ​​the light carpet.

[0118] After the calibration operation is completed, the vehicle's control unit can return to the step of acquiring the projected image through the external camera to form a closed loop until the projection error description information no longer meets the preset calibration conditions.

[0119] The technical solution of this embodiment acquires a projection effect image through an external camera; based on the difference between the feature points of the driving instruction information in the projection effect image and the feature points of the actual lane road surface in the projection effect image, the projection error description information of the projection headlight assembly is determined; if the projection error description information meets the preset calibration conditions, the projection headlight assembly is calibrated according to the projection error description information; then the process returns to the step of acquiring the projection effect image through the external camera until the projection error description information no longer meets the preset calibration conditions. This effectively achieves closed-loop calibration and optimization of the projection effect of the projection headlight assembly, dynamically correcting the projection error of the projection headlight assembly.

[0120] In another embodiment, such as Figure 3 As shown, a method for controlling the projection headlights of a vehicle is provided, which is applied to... Figure 1 Taking the vehicle in question as an example, the steps include:

[0121] Step S302: Obtain multimodal road condition perception data of the vehicle's external surrounding environment.

[0122] Step S304: Based on the multimodal road condition perception data, draw a temporary road semantic map of the surrounding environment outside the vehicle; the temporary road semantic map is used to mark the passable roads in the surrounding environment outside the vehicle, as well as the road condition information of the passable roads.

[0123] Step S306: Determine the current driving scenario that matches the temporary road semantic map; the scenario label associated with the current driving scenario matches the road condition information associated with the temporary road semantic map.

[0124] Step S308: According to the projection headlight control parameters that match the current driving scenario, drive the vehicle's projection headlight assembly to project driving instruction information that matches the current driving scenario onto the road surface.

[0125] Step S310: Acquire a projection effect image using an external camera; the projection effect image is a superimposed image of the driving instruction information and the actual road surface.

[0126] Step S312: Based on the difference between the feature points of the driving instruction information in the projected image and the feature points of the actual road surface in the projected image, determine the projection error description information of the projection headlight assembly.

[0127] Step S314: If the projection error description information meets the preset calibration conditions, perform a calibration operation on the projection vehicle lamp assembly according to the projection error description information; the calibration operation includes, in sequence, a projection angle calibration operation, a projection position calibration operation, a projection distortion calibration operation, and a projection brightness calibration operation.

[0128] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a projection headlight control method for a vehicle described above, and will not be repeated here.

[0129] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0130] Based on the same inventive concept, this application also provides a vehicle projection headlight control device for implementing the above-described vehicle projection headlight control method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more vehicle projection headlight control device embodiments provided below can be found in the limitations of the vehicle projection headlight control method described above, and will not be repeated here.

[0131] In one exemplary embodiment, such as Figure 4 As shown, a vehicle projection headlight control device is provided, comprising:

[0132] The data acquisition module 410 is used to acquire multimodal road condition perception data of the vehicle's external surrounding environment;

[0133] The map drawing module 420 is used to draw a temporary road semantic map of the surrounding environment outside the vehicle based on the multimodal road condition perception data; the temporary road semantic map is used to mark the passable roads in the surrounding environment outside the vehicle, as well as the road condition information of the passable roads.

[0134] The scene matching module 430 is used to determine the driving scene that matches the temporary road semantic map as the current driving scene; the scene tag associated with the current driving scene matches the road condition information associated with the temporary road semantic map;

[0135] The information projection module 440 is used to drive the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters that match the current driving scenario.

[0136] In an exemplary embodiment, the device is further configured to: acquire high-precision positioning data of the vehicle output by the vehicle navigation system when the operating status of the vehicle's navigation system meets preset availability conditions; query scene labels corresponding to the geographical locations represented by the high-precision positioning data in preset high-precision map resources to obtain target scene labels; the high-precision map resources record a preset mapping relationship between geographical locations and preset scene labels; and determine the driving scene associated with the target scene label as the new current driving scene when the driving scene associated with the target scene label is inconsistent with the driving scene matched by the temporary road semantic map.

[0137] In an exemplary embodiment, the device is further configured to query scene labels corresponding to the geographical locations represented by the high-precision positioning data of the vehicle in a preset high-precision map resource to obtain candidate scene labels; acquire real-time traffic data and real-time environmental data collected by the vehicle; and adjust the candidate scene labels according to the real-time traffic data and real-time environmental data to obtain the target scene label.

[0138] In an exemplary embodiment, the projection headlight control parameters include at least the road surface light carpet width parameter. The information projection module 440 is used to, when the current driving scenario is a driving scenario with lane markings, obtain the lane marking spacing of the lane where the vehicle is currently located, and drive the projection headlight assembly to project a first road surface light carpet onto the road surface in front of the vehicle according to the road surface light carpet width parameter that matches the lane marking spacing; or, when the current driving scenario is a driving scenario without lane markings, obtain the maximum vehicle width, and drive the projection headlight assembly to project a second road surface light carpet onto the road surface in front of the vehicle according to the road surface light carpet width parameter that matches the maximum vehicle width.

[0139] In an exemplary embodiment, the projection headlight control parameters include the projection coordinates of a navigation identifier on the road surface in front of the vehicle. The information projection module 440 is used to acquire the vehicle's current navigation command, generate a target navigation identifier to be projected that matches the current driving scenario based on the current navigation command, parse the road surface parameters in the temporary road semantic map, determine the projection coordinates of the target navigation identifier on the road surface based on the installation parameters of the projection headlight assembly and the road surface parameters, and control the projection headlight assembly to project the target navigation identifier onto the road surface according to the projection coordinates of the target navigation identifier on the road surface.

[0140] In an exemplary embodiment, the device is further configured to acquire a projection effect image via an external vehicle camera; the projection effect image is a superimposed image of the driving instruction information and the actual road surface; based on the difference between the feature points of the driving instruction information in the projection effect image and the feature points of the actual road surface in the projection effect image, projection error description information of the projection headlight assembly is determined; if the projection error description information meets preset calibration conditions, a calibration operation is performed on the projection headlight assembly based on the projection error description information; the calibration operation sequentially includes a projection angle calibration operation, a projection position calibration operation, a projection distortion calibration operation, and a projection brightness calibration operation; the device returns to the step of acquiring the projection effect image via the external vehicle camera until the projection error description information no longer meets the preset calibration conditions.

[0141] The modules in the aforementioned vehicle projection headlight control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0142] In one exemplary embodiment, a vehicle is provided, the internal structure of which can be as follows: Figure 5 As shown, the vehicle includes a processor and a memory. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium storing a computer program. When executed by the processor, the computer program implements a method for controlling the projected headlights of the vehicle.

[0143] Those skilled in the art will understand that Figure 5 The structure shown is a block diagram of a partial structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0144] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the vehicle projection headlight control method described above. The steps of the vehicle projection headlight control method described here can be the steps in the vehicle projection headlight control method of the various embodiments described above.

[0145] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the steps of the vehicle projection headlight control method described above. The steps of the vehicle projection headlight control method described here can be the steps from the vehicle projection headlight control methods of the various embodiments described above.

[0146] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, causes the processor to perform the steps of the vehicle projection headlight control method described above. The steps of the vehicle projection headlight control method described here can be the steps in the vehicle projection headlight control method of the various embodiments described above.

[0147] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0148] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic resistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0149] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0150] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for controlling the projection headlights of a vehicle, characterized in that, The method includes: Acquire multimodal road condition perception data of the vehicle's external surrounding environment; Based on the multimodal road condition perception data, a temporary road semantic map of the surrounding environment outside the vehicle is drawn; the temporary road semantic map is used to mark the passable roads in the surrounding environment outside the vehicle, as well as the road condition information of the passable roads; The driving scenario that matches the temporary road semantic map is identified as the current driving scenario; the scenario label associated with the current driving scenario matches the road condition information associated with the temporary road semantic map; According to the projection headlight control parameters matched with the current driving scenario, the vehicle's projection headlight assembly is driven to project driving instruction information that matches the current driving scenario onto the road surface.

2. The method according to claim 1, characterized in that, After the step of determining that the driving scenario matching the temporary road semantic map is the current driving scenario, the method further includes: When the operating status of the vehicle navigation system meets the preset availability conditions, acquire the high-precision positioning data of the vehicle output by the vehicle navigation system; The scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data is retrieved from the preset high-precision map resources to obtain the target scene label; the high-precision map resources record the mapping relationship between preset geographical locations and preset scene labels; If the driving scenario associated with the target scenario label is inconsistent with the driving scenario matched by the temporary road semantic map, the driving scenario associated with the target scenario label is determined as the new current driving scenario.

3. The method according to claim 2, characterized in that, The step of retrieving the scene label corresponding to the geographical location represented by the vehicle's high-precision positioning data from a preset high-precision map resource to obtain the target scene label includes: The scene labels corresponding to the geographical locations represented by the vehicle's high-precision positioning data are retrieved from the preset high-precision map resources to obtain candidate scene labels; Acquire real-time road condition data and real-time environmental data collected by the vehicle; Based on the real-time traffic data and real-time environmental data, the candidate scene labels are adjusted to obtain the target scene labels.

4. The method according to claim 1, characterized in that, The projection headlight control parameters include at least the road surface light carpet width parameter. Driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched to the current driving scenario includes: When the current driving scenario is a driving scenario with lane markings, the lane marking spacing of the lane where the vehicle is currently located is obtained, and the road light carpet width parameter that matches the lane marking spacing is used to drive the projection headlight assembly to project a first road light carpet onto the road surface in front of the vehicle. or, When the current driving scenario is a driving scenario without lane markings, the maximum vehicle width is obtained, and the projection headlight assembly is driven to project a second road surface light blanket onto the road surface in front of the vehicle according to the road surface light blanket width parameter that matches the maximum vehicle width.

5. The method according to claim 1, characterized in that, The projection headlight control parameters include the projection coordinates of navigation markers on the road surface in front of the vehicle. Driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters matched to the current driving scenario includes: Obtain the current navigation command of the vehicle, and generate a target navigation identifier to be projected that matches the current driving scenario based on the current navigation command; The road surface parameters in the temporary road semantic map are analyzed, and the projection coordinates of the target navigation mark on the road surface are determined based on the installation parameters of the projection headlight assembly and the road surface parameters. According to the projection coordinates of the target navigation mark on the road surface, the projection headlight assembly is controlled to project the target navigation mark onto the road surface.

6. The method according to any one of claims 1 to 5, characterized in that, After the step of driving the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to projection headlight control parameters matched with the current driving scenario, the method further includes: The projected image is captured by an external camera; the projected image is a superimposed image of the driving instruction information and the actual road surface. Based on the difference between the feature points of the driving instruction information in the projected image and the feature points of the actual lane road surface in the projected image, the projection error description information of the projection headlight assembly is determined; If the projection error description information meets the preset calibration conditions, the projection vehicle headlight assembly is calibrated according to the projection error description information; the calibration operation includes, in sequence, projection angle calibration, projection position calibration, projection distortion calibration, and projection brightness calibration. Return to the step of acquiring the projection effect image through the vehicle's external camera until the projection error description information no longer meets the preset calibration conditions.

7. A vehicle projection headlight control device, characterized in that, The device includes: The data acquisition module is used to acquire multimodal road condition perception data of the vehicle's external surrounding environment; The map drawing module is used to draw a temporary road semantic map of the surrounding environment outside the vehicle based on the multimodal road condition perception data; the temporary road semantic map is used to mark the passable roads in the surrounding environment outside the vehicle, as well as the road condition information of the passable roads; The scene matching module is used to determine the driving scene that matches the temporary road semantic map as the current driving scene; the scene tag associated with the current driving scene matches the road condition information associated with the temporary road semantic map; The information projection module is used to drive the vehicle's projection headlight assembly to project driving instruction information matching the current driving scenario onto the road surface according to the projection headlight control parameters that match the current driving scenario.

8. An intelligent vehicle, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images