Light control method and device, vehicle and computer program product

Abstract

The invention discloses a light control method and device, a vehicle and a computer program product, and relates to the field of vehicle control. In response to the detected target shielding object, interference data in the sensing data collected by the vehicle is filtered out, and target sensing data representing the actual motion state of the target shielding object in the motion environment within the preset range is obtained; performing information fusion on the target sensing data and the high-precision map data to obtain target motion data representing the motion state of the target shielding object in the road environment; performing trajectory prediction processing on the target motion data to obtain a target motion trajectory of the target shielding object; and according to the target motion track corresponding to the target shielding object, light of the vehicle is controlled, so that the position of the target shielding object is a dark area. The accuracy of the trajectory prediction result of the shielded object is improved by improving the accuracy of the motion data used for predicting the motion trajectory of the shielded object, so that the accuracy of the light dark area range is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and more specifically, to a lighting control method, device, vehicle and computer program product. Background Art

[0002] The ADB (Adaptive Driving Beam) system is an intelligent vehicle lighting system. Its main function is to dynamically adjust the lighting according to road conditions, weather conditions, road conditions and the driver's operation when driving at night, and to shield the lights in specific areas. The dark areas generated by shielding can avoid glare to oncoming vehicles or drivers of the vehicles in front. At present, the ADB system has the problem of inaccurate shielding of dark areas, which is easy to cause driving safety problems. Summary of the invention

[0003] In view of the above problems, the present application provides a lighting control method, device, vehicle and computer program product to achieve the purpose of improving the accuracy of dark area shielding of the ADB system. The specific scheme is as follows:

[0004] The first aspect of the present application provides a lighting control method, comprising:

[0005] In response to detecting a target shielding object of a vehicle, acquiring perception data collected by the vehicle and high-precision map data corresponding to the road on which the vehicle is located, the perception data at least including: environmental data within a preset range and state data of the target shielding object, the target shielding object at least including vehicles in the same direction or opposite direction as the vehicle, and the high-precision map data at least including: road environment data of the road on which the vehicle is located;

[0006] Filter out interference data in the perception data to obtain target perception data representing an actual motion state of the target shielding object in a motion environment within the preset range;

[0007] The target perception data and the high-precision map data are subjected to information fusion to obtain target motion data representing the motion state of the target obscured object in the road environment;

[0008] Performing trajectory prediction processing on the target motion data to obtain the target motion trajectory of the target shielding object;

[0009] According to the target motion trajectory corresponding to the target shielding object, the light of the vehicle is controlled so that the position where the target shielding object is located is a dark area.

[0010] In a possible implementation, the target perception data and the high-precision map data are fused to obtain target motion data representing the motion state of the target obscured object in the road environment, including:

[0011] Extracting road geometry information from the high-precision map data;

[0012] Performing geometric shape linearization processing on the road geometric information to obtain road data in a preset format;

[0013] The road data is fused with the target perception data to obtain target motion data representing the motion state of the target shielding object in the road environment.

[0014] In a possible implementation, the fusing of the road data with the target perception data to obtain target motion data representing the motion state of the target obscured object in the road environment includes:

[0015] Based on the environmental data within the preset range contained in the target perception data, correcting the data within the preset range corresponding to the road data to obtain target road data;

[0016] The target state data is fused with the target road data to obtain target motion data representing the motion state of the target shielding object in the road environment.

[0017] In a possible implementation, filtering out interference data in the perception data to obtain target perception data representing an actual motion state of the target shielding object in a motion environment within the preset range includes:

[0018] The perception data is subjected to high-pass filtering and low-pass filtering to filter out data within a preset frequency range, thereby obtaining target perception data corresponding to the target shielding object.

[0019] In a possible implementation, performing trajectory prediction processing on the target motion data to obtain the target motion trajectory of the target shielding object includes:

[0020] An adaptive high beam algorithm is called to perform trajectory prediction on the target motion data to obtain a target motion trajectory of the target shielding object.

[0021] In a possible implementation, calling an adaptive high beam algorithm to perform trajectory prediction on the target motion data to obtain the target motion trajectory of the target shielding object includes:

[0022] Invoke an adaptive high beam algorithm to perform data analysis on the target motion data to obtain the vehicle state of the target obstructed object and the road environment information where the target obstructed object is located, wherein the vehicle state includes at least: driving speed, historical driving trajectory and turn signal state, and the road environment information includes at least: the number of lanes and signal light state;

[0023] According to the road environment information, the driving route of the target shielded object in the vehicle state is previewed to obtain the driving trajectory of the target shielded object in the next step as the target motion trajectory.

[0024] In a possible implementation, controlling the light of the vehicle according to the target motion trajectory corresponding to the target shielding object so that the position of the target shielding object is a dark area includes:

[0025] The distance information and angle information between the target shielding object and the vehicle are obtained based on the position information of the target shielding object at the next step included in the target motion trajectory;

[0026] Determine the lighting distance and lighting angle of the vehicle lights corresponding to the next step length according to the distance information and the angle information between the target shielding object and the vehicle in the next step length;

[0027] generating the lighting control instruction according to the lighting distance and the lighting angle;

[0028] The lights of the vehicle are controlled according to the control instruction.

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

[0030] A data acquisition unit, configured to acquire, in response to detecting a target shielding object of a vehicle, perception data collected by the vehicle and high-precision map data corresponding to the road on which the vehicle is located, wherein the perception data at least includes: environmental data within a preset range and state data of the target shielding object, the target shielding object at least includes vehicles in the same direction or opposite direction as the vehicle, and the high-precision map data at least includes: road environment data of the road on which the vehicle is located;

[0031] A data filtering unit, used to filter out interference data in the perception data, and obtain target perception data representing an actual motion state of the target shielding object in the motion environment within the preset range;

[0032] A data fusion unit, used for fusing the target perception data with the high-precision map data to obtain target motion data representing the motion state of the target shielding object in the road environment;

[0033] A trajectory prediction unit, used to perform trajectory prediction processing on the target motion data to obtain a target motion trajectory of the target shielding object;

[0034] A light control unit is used to control the light of the vehicle according to the target motion trajectory corresponding to the target shielding object, so that the position where the target shielding object is located is a dark area.

[0035] The third aspect of the present application provides a vehicle, comprising: an on-board controller and a headlight, wherein the on-board controller is used to implement the lighting control method of the above-mentioned first aspect or any implementation method of the first aspect, and the headlight is used to respond to the lighting control of the on-board controller.

[0036] A fourth aspect of the present application provides a computer program product, comprising computer-readable instructions, which, when executed on an electronic device, enables the electronic device to implement the lighting control method of the first aspect or any implementation of the first aspect.

[0037] By means of the above technical solution, the lighting control method provided in the embodiment of the present application, when the vehicle detects an obstructing object, obtains the perception data collected by the vehicle itself, and at the same time obtains the high-precision map data of the road where the vehicle is located. First, the perception data is filtered to reduce the impact of interference information on the perception data, so that the filtered target perception data is closer to the actual motion state of the obstructing object in the motion environment within a preset range, reducing uncertainty factors. Further, the target perception data is fused with the high-precision map data to obtain target motion data. Since the high-precision map data has high-precision road surface information, the collected target perception data is refined based on the high-precision map data, thereby improving the accuracy of the motion data related to the motion environment and motion state of the obstructing object. Call the trajectory prediction algorithm to perform trajectory prediction on the high-precision target motion data of the obstructing object, obtain the motion trajectory of the obstructing object in the future step length, and control the lighting range of the vehicle based on the motion trajectory.

[0038] This application improves the accuracy of motion data used to predict the motion trajectory of obscured objects by fusing the perception data collected by the vehicle with high-precision map data, thereby improving the accuracy of the trajectory prediction results of the obscured objects and thus improving the accuracy of the dark area range. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0040] Figure 1 A schematic diagram of a vehicle driving environment provided in an embodiment of the present application;

[0041] Figure 2 A schematic diagram of a flow chart of a method for implementing lighting control provided in an embodiment of the present application;

[0042] Figure 3 An example diagram of a vehicle motion trajectory provided in an embodiment of the present application;

[0043] Figure 4 An example diagram of an application lighting control method provided in an embodiment of the present application;

[0044] Figure 5 A schematic diagram of the structure of a lighting control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0046] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0047] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0048] The present application can be applied to the field of vehicle control. Figure 1 Taking the example of a vehicle driving environment provided in an embodiment of the present application, an application scenario of the product is introduced.

[0049] The lighting control method proposed in the present application can be applied to the on-board controller of a vehicle equipped with an ADB system, wherein the on-board controller can be a vehicle computer or an independently configured control unit for the ADB system, etc. When the vehicle is driving at night, in tunnels, and in low-light scenes, the ADB system of the vehicle will control the turning on of the high beam. When there is a vehicle opposite or in front of vehicle A, the driver of the opposite or front vehicle will be affected by the high beam and experience dazzle, affecting driving safety. If the high beam is turned off, the nighttime visibility of the driver of the vehicle itself will be affected. Therefore, the ADB system will control the lighting range, lighting brightness, lighting angle, etc. of the high beam of the vehicle itself according to the position of the front vehicle or the oncoming vehicle, such as Figure 1 As shown, after the high beam of vehicle A adjusts the lighting range, vehicles B and C are located in a dark area and are not within the lighting range of the high beam. Based on this, the night vision of vehicle A can be guaranteed and the impact of the high beam on the vision of drivers of surrounding vehicles can be avoided.

[0050] However, the current vehicle vision algorithms are all researching autonomous driving L3 and L4, and the overlap between autonomous driving scenes and ADB perception scenes is relatively low. Autonomous driving vision algorithms are more focused on scenes within 150m or even 100m during the day, while the vision algorithms used by the ADB system are more focused on scenes within 400m at night. Therefore, although the vehicle vision algorithm has been gradually optimized with the development of autonomous driving, it is not suitable for night scenes, which results in the ADB system's vision algorithm not being optimized when performing lighting control at night, and the problem of low accuracy in dark areas has repeatedly occurred, which not only affects the driver's night vision, but also has adverse effects on pedestrians and vehicles around the vehicle.

[0051] To solve the above technical problems, refer to Figure 2 , a flow chart of a method for implementing a lighting control method provided in an embodiment of the present application, a lighting control method applied to a vehicle-mounted controller of a vehicle provided in an embodiment of the present application is described, and the specific process may include the following steps:

[0052] Step S110, in response to detecting a target obstructing object of the vehicle, acquiring perception data collected by the vehicle and high-precision map data corresponding to the road on which the vehicle is located.

[0053] The perception data includes at least: environmental data within a preset range and status data of target obscured objects. The target obscured objects include at least vehicles in the same direction or opposite direction as the vehicle. The high-precision map data includes at least: road environment data of the road on which the vehicle is located.

[0054] It is understandable that when the vehicle is driving, the camera, millimeter wave radar, laser radar and other perception modules configured by the vehicle and the ADB system collect data about the vehicle's surrounding environment in real time, such as surrounding vehicle information, ambient lighting conditions, road structure information, vehicle status, etc. When a vehicle or pedestrian appears within the preset range in front of the vehicle, the vehicle or pedestrian can be used as the target shielding object of the high beam. Among them, the preset range mainly depends on the maximum sensing distance of the perception module. Considering that the maximum sensing distance of the perception module is limited, the target shielding object may not be perceived in time. Optionally, the status data of the target shielding object can also be collected through the perception module of the vehicle.

[0055] When the maximum sensing distance of the perception module meets the needs of long-distance detection, the preset range can be determined according to the high-beam lighting distance or range. For example, the maximum lighting distance of the vehicle's high-beam is 80-120 meters, and it is necessary to detect the vehicle, pedestrian or obstacle in front or oncoming in advance before the vehicle or pedestrian enters the high-beam lighting range. If the vehicle is traveling at a speed of 120km / h (33m / s), the 400-meter distance in front of the detection vehicle can provide about 12 seconds of reaction time to adjust the lights, while the detection of 120 meters only has a reaction time of 3.6 seconds. Therefore, when the maximum sensing distance meets the detection requirements, the preset range can be set according to the lighting requirements. The larger the perceived preset range, the better the lighting effect and the higher the driving safety.

[0056] In the embodiment of the present application, in response to detecting the presence of a target shielding object in the vehicle, the perception data of the target shielding object is further obtained, and the perception data may at least include: environmental data within a preset range and status data of the target shielding object. Among them, the status data may include: basic information of the vehicle shielding the object, such as model, body size, etc., driving speed, driving direction, current location information, etc. The environmental data within the preset range may include: coordinate positions of surrounding objects, road conditions of the lane, distance to the vehicle in front, etc.

[0057] In addition, the embodiment of the present application takes into account the limited amount of data and data accuracy that can be collected by the perception module of the vehicle. Therefore, a high-precision map of the location of the vehicle is obtained at the same time. A high-precision map is a high-precision map used for autonomous driving. The map range can usually cover the entire road where the vehicle is located. The map accuracy can be down to the centimeter level. It contains static information such as roads, lanes, and traffic signs. It can also update traffic conditions in real time and provide dynamic information of the vehicle. Based on this, the embodiment of the present application can use the acquired high-precision map data to supplement the status data of the target obscured object, and improve the accuracy and completeness of the data basis for the ADB system to adjust the lighting effect.

[0058] Step S120, filtering out interference data in the perception data to obtain target perception data representing the actual motion state of the target shielding object in a motion environment within a preset range.

[0059] It is understandable that when the perception module of the vehicle is collecting data, the electromagnetic interference between the perception modules may cause abnormal output data of the perception module, or the traffic noise such as vehicles driving on the road, horns, and electromagnetic radiation from other vehicles, road facilities or radio equipment may interfere with the perception module, resulting in a large number of interference signals in the collected perception data.

[0060] Therefore, in an embodiment of the present application, the interference data in the perception data is filtered out, and the perception data after filtering out the interference is closer to the actual situation of the current road and the actual state of the target obscured object. The target perception data after filtering out the interference data is used as reference data for subsequent lighting control to improve the accuracy of lighting control.

[0061] In a possible implementation, the target perception data corresponding to the target shielding object can be obtained by performing high-pass filtering and low-pass filtering on the perception data to filter out data within a preset frequency range.

[0062] Optionally, in the data processing flow after the perception data is collected, a filtering algorithm is configured, or a filtering circuit or filter is set in the output circuit of the perception module that collects the perception data, based on which the collected perception data is subjected to high-pass filtering and low-pass filtering, and the high-frequency noise and low-frequency noise in the perception data are filtered out to obtain target state data that are all within a preset frequency range. In the embodiment of the present application, the main function of filtering is to process the waveform of the collected data so that its data is stabilized in a constant waveform state, which can be closer to the target shielding object's own information.

[0063] In other possible implementations, data whose data values ​​do not meet the threshold conditions can be filtered out based on the size relationship between the data value of each data in the perception data and the preset threshold. For example, data whose data values ​​are not within the preset threshold range are interference data, which are filtered out to obtain interference-free target perception data.

[0064] Step S130, information fusion is performed on the target perception data and the high-precision map data to obtain target motion data representing the motion state of the target obscured object in the road environment.

[0065] Due to the functional limitations of the vehicle perception module, the state data of the target obscured object and the road environment data collected are limited, resulting in the inability to restore or represent the driving state of the target obscured object in the complete road environment based on the target perception data. Therefore, the embodiment of the present application uses the high-precision map data to compensate the target perception data by fusing the high-precision map data with the target perception data, so that the fused data can represent the motion state of the target obscured object in the road environment.

[0066] Optionally, the fusion method of high-precision map data and target perception data can be fused according to the data format applicable to the current ADB system of the vehicle. For example, the high-precision map data and target perception data are converted into the format applicable to the ADB system respectively, and the data of the same data type in the high-precision map data and the target perception data are merged according to the data type of each data, and the data of the same data type are saved independently. For example, the high-precision map data includes the historical trajectory, vehicle speed and traffic light data of the target obscured object, and the target perception data includes the vehicle speed, turn signal perception and traffic light data of the target obscured object at the fork in the road. The target perception data and the vehicle speed and traffic light data of the fork in the high-precision map data are merged, and the historical trajectory in the high-precision map data and the turn signal perception in the target perception data are saved separately. The fused target motion data includes: the historical trajectory, vehicle speed, turn signal perception and traffic light data of the target obscured object at the fork in the road. Based on this, the integrity of the data that can characterize the driving environment and driving perception of the target obscured object is improved, so as to monitor the driving perception of the target obscured object as accurately as possible, and improve the accuracy of the subsequent trajectory prediction of the target obscured object.

[0067] In one possible implementation, step S130 fuses the target perception data and the high-precision map data to obtain target motion data that characterizes the motion state of the target obscured object in the road environment, including: extracting road geometry information from the high-precision map data; performing geometric shape linearization processing on the road geometry information to obtain road data in a preset format; and fusing the road data with the target perception data to obtain target motion data that characterizes the motion state of the target obscured object in the road environment.

[0068] First, the road geometry model in the high-precision map data is extracted. The road geometry model can be understood as a data set or information set that characterizes the road environment. Further, the road geometry model is converted into road data in a preset format by using the method of geometric shape linearization. Specifically, geometric shape linearization can be understood as describing or modeling the geometric characteristics or attributes in the road geometry model in a linear relationship. This linear relationship may be based on the similarity, proportional relationship, positional relationship, etc. between geometric shapes. Based on this, the geometric road characteristics in the high-precision map data can be represented in the form of vectors or matrices, or considering the need to merge with the target perception data, the road geometry information can also be converted into a data format that is the same as or can be merged with the target perception data to describe the road environment. Furthermore, the converted road data is merged with the target perception data to obtain target motion data that integrates the road environment and the state of the target obstructing object itself.

[0069] Optionally, data errors are inevitable in both high-precision map data and target perception data. To further improve data accuracy, during data fusion processing, high-precision map data and target perception data can be used for data verification. High-precision map data can be used as standard data to correct target perception data before data fusion. In another possible implementation, based on the environmental data within a preset range contained in the target perception data, the data within the corresponding preset range in the road data is corrected to obtain target road data; the target state data is fused with the target road data to obtain target motion data that characterizes the motion state of the target obscured object in the road environment.

[0070] The perceived target perception data is taken as the correct data, and the road environment data within a preset range that overlaps with the target perception data in the high-precision map data is corrected. It can be understood that since the high-precision map data contains road environment data, driving status data, pedestrian location data and other data, the data type and data volume are more than the target status data. Therefore, only the data that is repeated in the target status data is corrected, and for other data that is not in the target perception data, the high-precision map data is taken as the correct data.

[0071] Step S140 , performing trajectory prediction processing on the target motion data to obtain the target motion trajectory of the target occluded object.

[0072] The target motion data integrates the high-precision road environment data in the HD map and the state data of the target obstructed object collected by the vehicle in real time. Based on this, the historical motion trajectory and current state of the target obstructed object at the current moment and before the current moment represented by the target motion data can be used. In addition, combined with the current road environment, the motion trajectory of the target obstructed object in the future can be predicted in advance.

[0073] In the embodiment of the present application, a neural network model that predicts the motion trajectory based on the target motion data can be pre-trained, and then the neural network can be directly called in step S140 to predict the motion trajectory corresponding to the target motion data, or the corresponding trajectory prediction algorithm or rule can be pre-configured. In one possible implementation, the ADB system is usually configured with a trajectory prediction algorithm to predict the position or trajectory of the next step of the shielding object in advance, and dynamically adjust the lighting range based on this. Based on this, the adaptive high beam algorithm configured in the ADB system of the vehicle can be called to perform trajectory prediction on the target motion data to obtain the target motion trajectory of the target shielding object.

[0074] Reference Figure 3 , an example diagram of a vehicle motion trajectory provided in an embodiment of the application is provided to illustrate the trajectory prediction method configured in the adaptive high beam algorithm. In an optional trajectory prediction method, the adaptive high beam algorithm is called to perform data analysis on the target motion data to obtain the vehicle state of the target obscured object and the road environment information where the target obscured object is located. The vehicle state includes at least: driving speed, historical driving trajectory and turn signal status, and the road environment information includes at least: the number of lanes and signal light status; based on the road environment information, the driving route of the target obscured object in the vehicle state is previewed to obtain the driving trajectory of the target obscured object in the next step as the target motion trajectory.

[0075] First, the target motion data of the target shielding object corresponding to the ADB vehicle, i.e. the vehicle itself, is analyzed. Figure 3 The target shielding object is the oncoming vehicle. The oncoming vehicle is located, as well as the speed, turn signal status, historical trajectory, and lateral and longitudinal offset of the oncoming vehicle during driving. The historical driving trajectory may include the driving trajectory of the oncoming vehicle before the current moment, and the historical driving trajectory of other vehicles that have passed the road. At the same time, the road environment information of the oncoming vehicle is determined, such as the number of lanes, the position of the lane, whether there are traffic lights, the status of traffic lights, road obstacles, etc.

[0076] Figure 3 In the example, the left turn signal of the oncoming vehicle in the right turning lane is on, and the vehicle's deviation direction is to the left. It can be predicted that the next action of the oncoming vehicle is a left turn. Furthermore, combined with the speed of the oncoming vehicle, the position change of the oncoming vehicle during the turning process is determined. Based on this, the target motion trajectory of the oncoming vehicle during the turning process is determined.

[0077] In another optional trajectory prediction method, the driving trajectory of the oncoming vehicle before the current moment can be compared with the similarity between the historical driving trajectories of other vehicles on the road, so that the future driving trajectory of the oncoming vehicle is similar to the historical driving trajectory, and the historical driving trajectory can be determined as the future driving trajectory of the oncoming vehicle, and further combined with the current speed, deviation direction, etc. of the oncoming vehicle, the position information of each time point in the historical driving trajectory can be corrected. Figure 3 The map trajectory can be regarded as the historical driving trajectory of other vehicles on the road recorded by the high-precision map. Although the historical driving trajectory is similar to the actual trajectory, the position of each trajectory point is not completely consistent due to the differences in the speed and lane offset position of the target obscured object. Therefore, the vehicle state data in the target motion data can be combined to correct each trajectory point of the historical driving trajectory to obtain a target motion trajectory that is closer to the actual trajectory.

[0078] Based on the above trajectory prediction method, the target motion data is predicted and processed to obtain the target motion trajectory of the target obscured object in the next step or the next prediction time period. It can be understood that the movement of the target obscured object may change at any time. Therefore, the above steps S110-S140 can form a trajectory prediction process. The vehicle executes the trajectory prediction process in a loop with a preset step length to obtain the motion trajectory of the target obscured object corresponding to each future step length.

[0079] Step S150, according to the target motion trajectory corresponding to the target shielding object, the vehicle light is controlled so that the position where the target shielding object is located is a dark area.

[0080] It can be understood that the target motion trajectory includes the position information corresponding to the target obscured object at different time points. Based on this, the lighting range, lighting distance, and lighting angle of the vehicle lights are also adjusted by following the position changes of the target obscured object in the target motion trajectory, so that the position of the target obscured object is always in a dark area.

[0081] It can be understood that based on the state data of the target obscured object corresponding to the next step length or the next time point contained in the target motion trajectory, such as the mean value and covariance matrix characterizing the vehicle state, a stable motion trajectory that can characterize the target obscured object in the next step length or a period of time in the future is determined, and the motion trajectory is input into the ADB algorithm to adaptively adjust the lighting range of the car lights.

[0082] In one possible implementation, based on the position information of the target obstructing object at the next step length contained in the target motion trajectory, the distance information and angle information between the target obstructing object and the vehicle at the next step length are determined; based on the distance information and angle information between the target obstructing object and the vehicle at the next step length, the lighting distance and lighting angle of the vehicle's lights corresponding to the next step length are determined; based on the lighting distance and lighting angle, a lighting control instruction is generated; and the vehicle's lights are controlled based on the control instruction.

[0083] The position information of the target obstructing object in the next step is obtained from the target motion trajectory, and the position information of the vehicle in the next step is determined according to the current position and speed of the vehicle, so as to calculate the next step length, the angle information and the distance information between the target obstructing object and the vehicle, such as Figure 1 In the figure, vehicle B is located 30° north of vehicle A, 200 meters away; vehicle C is located in front of vehicle A, 100 meters away. Optionally, light shielding also needs to consider basic information such as the width and length of the vehicle. Therefore, the required shielding width of the target shielding object can also be determined in combination with the perception data collected by the vehicle or the basic information of the target shielding object in the high-precision map data. Based on the distance information, angle information and basic information of the target shielding object obtained above, the lighting strategy such as the lighting distance, lighting angle and lighting range of the next step of the vehicle is determined. According to the lighting strategy, a control instruction for controlling the light is generated to control the vehicle's lights.

[0084] In summary, when a vehicle detects an obstructing object, it obtains the perception data collected by the vehicle and the high-precision map data of the road where the vehicle is located. First, the perception data is filtered to reduce the influence of interference information on the perception data, so that the filtered target perception data is closer to the actual motion state of the obstructing object in the motion environment within a preset range, reducing uncertainty factors. Further, the target perception data is fused with the high-precision map data to obtain the target motion data. Since the high-precision map data has high-precision road information, the collected target perception data is refined according to the high-precision map data, thereby improving the accuracy of the motion data related to the motion environment and motion state of the obstructing object. The trajectory prediction algorithm is called to perform trajectory prediction on the high-precision target motion data of the obstructing object, obtain the motion trajectory of the obstructing object in the future step length, and control the lighting range of the vehicle according to the motion trajectory. The embodiment of the present application improves the accuracy of the motion data used to predict the motion trajectory of the obstructing object by fusing the perception data collected by the vehicle with the high-precision map data, and improves the accuracy of the trajectory prediction results of the obstructing object, thereby improving the accuracy of the range of the dark area of ​​the light.

[0085] Next, refer to Figure 4, an example diagram of an application lighting control method provided in an embodiment of the present application is used to exemplarily illustrate the actual application process of the above lighting control method.

[0086] When vehicle A is driving at night, in tunnels, or in low-light scenarios, the perception system or perception module of vehicle A collects environmental data of the road ahead in real time. At the same time, vehicle A obtains high-precision map data of the current road from the high-precision map integrated in the vehicle's head unit. When a target obstruction object is detected, vehicle A collects status data of the target obstruction object, such as the size information of the vehicle, driving speed, and other data.

[0087] The perception data transmitted by the perception system or perception module of vehicle A is filtered to filter out the noise in the perception data and reduce the influence of uncertainty factors on the accuracy of the perception data. Further, the filtered perception data is fused with the high-precision map data. Specifically, the road model is extracted through the high-precision map data, and the road model is adapted to various road environments by using the method of geometric shape linearization. The road model is fused with the perception data, and the map prediction algorithm and the speed prediction algorithm are called to predict the dynamic trajectory of the target obscured object based on the map data and vehicle speed in the fused target motion data. It can be understood that the map prediction algorithm can predict the driving trajectory of the target obscured object based on the road environment, vehicle status and historical driving trajectory of the vehicle in the high-precision map data, and the speed prediction algorithm can accurately determine the position information of each track point of the driving trajectory based on the driving speed of the target obscured object, so as to obtain a more accurate motion trajectory of the target obscured object.

[0088] Based on the average value and covariance matrix of the vehicle state of the target obscured object characterizing the next step length obtained in this prediction, the average trajectory with stable motion corresponding to the target obscured object in the next step length is determined, and the position of the dark area illuminated by the vehicle's lights in the next step length is determined based on the average trajectory. Based on this, according to the above steps or processes, the motion trajectory of the target obscured object in future steps is continued to be predicted, so that the position of the dark area corresponding to the vehicle's lights changes with the movement of the target obscured object, thereby improving the flexibility of light control. Optionally, the range of the dark area can also be adjusted according to the size of the target obscured object, and scene compensation can be performed on the illumination effect of the high beam according to the road environment, the state of the vehicle ahead, etc. For example, when driving on a road section illuminated by street lights at night, the light intensity of the high beam is adjusted.

[0089] In summary, the embodiment of the present application optimizes the trajectory prediction function of the ADB system through the integration of the high-precision map algorithm and the dynamic algorithm, thereby improving the accuracy of the ADB system's trajectory prediction of the target obscured object, making the lighting effect adjusted according to the trajectory prediction results more accurate.

[0090] A lighting control method provided by an embodiment of the present application is introduced above, and a device for executing the lighting control method will be introduced below.

[0091] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a lighting control device provided in an embodiment of the present application. Figure 5 As shown, the 5 devices include:

[0092] The data acquisition unit 100 is used to acquire, in response to detecting a target shielding object of a vehicle, the perception data collected by the vehicle and the high-precision map data corresponding to the road where the vehicle is located, wherein the perception data at least includes: environmental data within a preset range and state data of the target shielding object, the target shielding object at least includes vehicles in the same direction or opposite direction as the vehicle, and the high-precision map data at least includes: road environment data of the road where the vehicle is located;

[0093] A data filtering unit 200 is used to filter out interference data in the perception data to obtain target perception data representing the actual motion state of the target shielding object in the motion environment within the preset range;

[0094] A data fusion unit 300 is used to fuse the target perception data with the high-precision map data to obtain target motion data representing the motion state of the target shielding object in the road environment;

[0095] A trajectory prediction unit 400 is used to perform trajectory prediction processing on the target motion data to obtain a target motion trajectory of the target shielding object;

[0096] The light control unit 500 is used to control the light of the vehicle according to the target motion trajectory corresponding to the target shielding object, so that the position where the target shielding object is located is a dark area.

[0097] In summary, when a vehicle detects an obstructing object, it obtains the perception data collected by the vehicle and the high-precision map data of the road where the vehicle is located. First, the perception data is filtered to reduce the impact of interference information on the perception data, so that the filtered target perception data is closer to the actual motion state of the obstructing object in the motion environment within a preset range, reducing uncertainty factors. Further, the target perception data is fused with the high-precision map data to obtain the target motion data. Since the high-precision map data has high-precision road information, the collected target perception data is refined according to the high-precision map data, thereby improving the accuracy of the motion data related to the motion environment and motion state of the obstructing object. The trajectory prediction algorithm is called to predict the trajectory of the high-precision target motion data of the obstructing object, obtain the motion trajectory of the obstructing object in the future step length, and control the lighting range of the vehicle according to the motion trajectory. This application improves the accuracy of the motion data used to predict the motion trajectory of the obstructing object by fusing the perception data collected by the vehicle with the high-precision map data, and improves the accuracy of the trajectory prediction results of the obstructing object, thereby improving the accuracy of the dark area range of the light.

[0098] In a possible implementation, the data fusion unit 300 includes:

[0099] An information extraction subunit, used to extract road geometry information from the high-precision map data;

[0100] A linearization subunit, used for performing geometric shape linearization processing on the road geometric information to obtain road data in a preset format;

[0101] The data fusion subunit is used to fuse the road data with the target perception data to obtain target motion data representing the motion state of the target shielding object in the road environment.

[0102] In a possible implementation, the data fusion subunit includes:

[0103] a data correction subunit, configured to correct the data within the preset range corresponding to the road data based on the environmental data within the preset range contained in the target perception data, so as to obtain target road data;

[0104] The correction data fusion subunit is used to fuse the target state data with the target road data to obtain target motion data representing the motion state of the target shielding object in the road environment.

[0105] In a possible implementation, the data filtering unit 200 includes:

[0106] The filtering subunit is used to perform high-pass filtering and low-pass filtering on the perception data, filter out data within a preset frequency range, and obtain target perception data corresponding to the target shielding object.

[0107] In a possible implementation, the trajectory prediction unit 400 includes:

[0108] The algorithm calling subunit is used to call the adaptive high beam algorithm to perform trajectory prediction on the target motion data to obtain the target motion trajectory of the target shielding object.

[0109] In a possible implementation, the algorithm calls a subunit, including:

[0110] A data analysis subunit is used to call an adaptive high beam algorithm to perform data analysis on the target motion data to obtain the vehicle state of the target shielding object and the road environment information where the target shielding object is located, wherein the vehicle state at least includes: driving speed, historical driving trajectory and turn signal state, and the road environment information at least includes: the number of lanes and signal light state;

[0111] The trajectory preview subunit is used to preview the driving route of the target shielded object in the vehicle state according to the road environment information, and obtain the driving trajectory of the target shielded object in the next step as the target motion trajectory.

[0112] In a possible implementation, the lighting control unit 500 includes:

[0113] a shielding information determining subunit, configured to determine the distance information and angle information between the target shielding object and the vehicle according to the position information of the target shielding object at the next step included in the target motion trajectory;

[0114] A lighting information determination subunit, configured to determine a lighting distance and a lighting angle of the vehicle's lights corresponding to the next step length according to the distance information and the angle information between the target shielding object and the vehicle at the next step length;

[0115] An instruction generation subunit, used for generating the lighting control instruction according to the lighting distance and the lighting angle;

[0116] A control subunit is used to control the lights of the vehicle according to the control instruction.

[0117] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the lighting control methods provided in the embodiments of the present application.

[0118] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0119] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0120] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0121] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. 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, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A lighting control method, characterized in that: include: In response to detecting a target shielding object of a vehicle, acquiring perception data collected by the vehicle and high-precision map data corresponding to the road on which the vehicle is located, the perception data at least including: environmental data within a preset range and state data of the target shielding object, the target shielding object at least including vehicles in the same direction or opposite direction as the vehicle, and the high-precision map data at least including: road environment data of the road on which the vehicle is located; Filter out interference data in the perception data to obtain target perception data representing an actual motion state of the target shielding object in a motion environment within the preset range; The target perception data and the high-precision map data are subjected to information fusion to obtain target motion data representing the motion state of the target obscured object in the road environment; Performing trajectory prediction processing on the target motion data to obtain the target motion trajectory of the target shielding object; According to the target motion trajectory corresponding to the target shielding object, the light of the vehicle is controlled so that the position where the target shielding object is located is a dark area.

2. The lighting control method according to claim 1, characterized in that: The target perception data and the high-precision map data are subjected to information fusion to obtain target motion data representing the motion state of the target shielding object in the road environment, including: Extracting road geometry information from the high-precision map data; Performing geometric shape linearization processing on the road geometric information to obtain road data in a preset format; The road data is fused with the target perception data to obtain target motion data representing the motion state of the target shielding object in the road environment.

3. The lighting control method according to claim 2, characterized in that: The step of fusing the road data with the target perception data to obtain target motion data representing the motion state of the target shielding object in the road environment includes: Based on the environmental data within the preset range contained in the target perception data, correcting the data within the preset range corresponding to the road data to obtain target road data; The target state data is fused with the target road data to obtain target motion data representing the motion state of the target shielding object in the road environment.

4. The lighting control method according to claim 1, characterized in that: The step of filtering out interference data in the perception data to obtain target perception data representing the actual motion state of the target shielding object in the motion environment within the preset range includes: The perception data is subjected to high-pass filtering and low-pass filtering to filter out data within a preset frequency range, thereby obtaining target perception data corresponding to the target shielding object.

5. The lighting control method according to claim 1, characterized in that: The performing trajectory prediction processing on the target motion data to obtain the target motion trajectory of the target shielding object includes: An adaptive high beam algorithm is called to perform trajectory prediction on the target motion data to obtain a target motion trajectory of the target shielding object.

6. The lighting control method according to claim 5, characterized in that: The calling of the adaptive high beam algorithm to perform trajectory prediction on the target motion data to obtain the target motion trajectory of the target shielding object includes: Invoke an adaptive high beam algorithm to perform data analysis on the target motion data to obtain the vehicle state of the target obstructed object and the road environment information where the target obstructed object is located, wherein the vehicle state includes at least: driving speed, historical driving trajectory and turn signal state, and the road environment information includes at least: the number of lanes and signal light state; According to the road environment information, the driving route of the target shielded object in the vehicle state is previewed to obtain the driving trajectory of the target shielded object in the next step as the target motion trajectory.

7. The lighting control method according to any one of claims 1 to 6, characterized in that: The controlling the light of the vehicle according to the target motion trajectory corresponding to the target shielding object so that the position of the target shielding object is a dark area includes: The distance information and angle information between the target shielding object and the vehicle are obtained based on the position information of the target shielding object at the next step included in the target motion trajectory; Determine the lighting distance and lighting angle of the vehicle lights corresponding to the next step length according to the distance information and the angle information between the target shielding object and the vehicle in the next step length; Generate a control instruction for the light according to the lighting distance and the lighting angle of the light; The lights of the vehicle are controlled according to the control instruction.

8. A lighting control device, characterized in that: include: A data acquisition unit, configured to acquire, in response to detecting a target shielding object of a vehicle, perception data collected by the vehicle and high-precision map data corresponding to the road on which the vehicle is located, wherein the perception data at least includes: environmental data within a preset range and state data of the target shielding object, the target shielding object at least includes vehicles in the same direction or opposite direction as the vehicle, and the high-precision map data at least includes: road environment data of the road on which the vehicle is located; A data filtering unit, used to filter out interference data in the perception data, and obtain target perception data representing an actual motion state of the target shielding object in the motion environment within the preset range; A data fusion unit, used for fusing the target perception data with the high-precision map data to obtain target motion data representing the motion state of the target shielding object in the road environment; A trajectory prediction unit, used to perform trajectory prediction processing on the target motion data to obtain a target motion trajectory of the target shielding object; A light control unit is used to control the light of the vehicle according to the target motion trajectory corresponding to the target shielding object, so that the position where the target shielding object is located is a dark area.

9. A vehicle, characterized in that: include: An on-board controller and a vehicle light, wherein the on-board controller is used to implement the light control method as described in any one of claims 1 to 7, and the vehicle light is used to respond to the light control of the on-board controller.

10. A computer program product, characterized in that The method comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the lighting control method as claimed in any one of claims 1 to 7.

Images