A coupling and decoupling control method, device, medium and equipment for vehicle-mounted sensor

Abstract

The present application discloses a coupling-decoupling control method, device, medium and equipment for vehicle-mounted sensors, which obtain scene information of a current scene in which a target vehicle is located; based on the scene information, obtain the confidence of the sensor of the target vehicle; based on the scene information, calculate the demand of the target vehicle; based on the confidence of the sensor, the coupling degree of the sensor and the demand of the target vehicle, determine the coupling-decoupling strategy of multiple sensors; wherein the coupling-decoupling strategy of the sensor includes decoupling sensors in a coupled state and coupling sensors in a decoupled state; based on the demand of the target vehicle, the confidence and coupling degree of the sensor, comprehensively determine the coupling-decoupling strategy of the sensor, thereby meeting the current scene requirements while optimizing the coupling state of the sensor, so as to reduce the complexity of the system, thereby improving the computing efficiency of the system, and then providing accurate and efficient perception information for autonomous driving.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle-mounted sensor coupling, and in particular to a coupling and decoupling control method, device, medium and equipment for a vehicle-mounted sensor. Background Art

[0002] As the intelligence of automobiles continues to develop, on-board sensors have become a key component for autonomous navigation and control of vehicles. They enable vehicles to understand their surroundings and make decisions on their own without driver intervention. On-board sensors can monitor the vehicle's surroundings in real time, including obstacle detection, road conditions, traffic sign recognition, etc., to prevent traffic accidents. On-board sensors can also provide various driving assistance functions, such as automatic parking, lane keeping, adaptive cruise control, etc., which greatly improve the convenience and comfort of driving. As the intelligence of automobiles continues to increase, smart sensors ensure safe and efficient operation while providing these driving services. More and more different types of sensors are coupled, such as combining data from cameras, millimeter-wave radars, and lidars to obtain more comprehensive environmental perception capabilities.

[0003] However, as the degree of coupling of vehicle-mounted sensors increases, the system's perception accuracy is indeed improved, but the system's complexity is also higher, and the requirements for computing power are also higher. Since different scenarios have different requirements for the perception accuracy of vehicle-mounted sensors, how to balance the system's computing power and perception accuracy is a technical challenge. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a coupling and decoupling control method, device, medium and equipment for a vehicle-mounted sensor.

[0005] According to one aspect of the present application, a coupling-decoupling control method for a vehicle-mounted sensor is provided, comprising: acquiring scene information of a current scene in which a target vehicle is located; obtaining the confidence of the sensor of the target vehicle based on the scene information; wherein the confidence of the sensor represents the accuracy of the data acquired by the sensor in the current scene; calculating the demand of the target vehicle based on the scene information; wherein the demand of the target vehicle represents the degree of demand of the sensor by the target vehicle in the current scene; determining a coupling-decoupling strategy for a plurality of the sensors based on the confidence of the sensor, the coupling degree of the sensor and the demand of the target vehicle; wherein the coupling degree of the sensor represents the number and degree of the sensors in a coupled state, and the coupling-decoupling strategy of the sensor comprises decoupling sensors in a coupled state and coupling sensors in a decoupled state.

[0006] In one embodiment, the scene information includes any one or more combinations of the following information: location information, weather information, brightness information, and road condition information; wherein, obtaining the confidence of the sensor of the target vehicle based on the scene information includes: obtaining the confidence of the sensor of the target vehicle by comprehensive calculation based on the scene information.

[0007] In one embodiment, the calculation of the demand of the target vehicle based on the scenario information includes: calculating the complexity, urgency and coverage of the perception data required by the target vehicle based on the scenario information; calculating the demand of the target vehicle based on the complexity, urgency and coverage of the perception data required by the target vehicle.

[0008] In one embodiment, the coupling-decoupling strategy of the multiple sensors is determined based on the confidence of the sensor, the coupling degree of the sensor, and the demand degree of the target vehicle, including: if the coupling degree of the sensor is within the demand range corresponding to the demand degree of the target vehicle, the coupling-decoupling state of the multiple sensors is maintained unchanged.

[0009] In one embodiment, the coupling and decoupling strategies of the multiple sensors are determined based on the confidence of the sensor, the coupling degree of the sensor, and the demand degree of the target vehicle, including: if there are sensors whose confidence is less than a preset confidence threshold, or the coupling degree of the sensor is greater than the demand upper limit corresponding to the demand degree of the target vehicle, then one or more sensors with the smallest confidence are decoupled.

[0010] In one embodiment, the coupling-decoupling strategy of the multiple sensors is determined based on the confidence of the sensor, the coupling degree of the sensor, and the demand degree of the target vehicle, including: if the coupling degree of the sensor is less than the lower limit of the demand corresponding to the demand degree of the target vehicle, coupling one or more sensors in a decoupled state.

[0011] In one embodiment, coupling one or more sensors in a decoupled state includes: obtaining category information of sensors to be coupled; and based on the category information, highly integrating sensors of the same category and coupling perception information obtained by sensors of different categories.

[0012] According to another aspect of the present application, a coupling-decoupling control device for a vehicle-mounted sensor is provided, comprising: a scene information acquisition module, for acquiring scene information of a current scene in which a target vehicle is located; a confidence determination module, for obtaining the confidence of the sensor of the target vehicle based on the scene information; wherein the confidence of the sensor represents the accuracy of the data acquired by the sensor in the current scene; a demand calculation module, for calculating the demand of the target vehicle based on the scene information; wherein the demand of the target vehicle represents the degree of demand of the target vehicle for the sensor in the current scene; a coupling-decoupling strategy determination module, for determining a coupling-decoupling strategy of a plurality of the sensors based on the confidence of the sensor, the coupling degree of the sensor, and the demand of the target vehicle; wherein the coupling degree of the sensor represents the number and degree of the sensors in a coupled state, and the coupling-decoupling strategy of the sensor includes decoupling sensors in a coupled state and coupling sensors in a decoupling state.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above-mentioned coupling and decoupling control methods for vehicle-mounted sensors.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is used to execute any of the coupling and decoupling control methods for vehicle-mounted sensors described above.

[0015] The present application provides a coupling-decoupling control method, device, medium and equipment for vehicle-mounted sensors, which obtains scene information of the current scene in which the target vehicle is located; based on the scene information, obtains the confidence of the sensor of the target vehicle; wherein the confidence of the sensor indicates the accuracy of the data obtained by the sensor in the current scene; based on the scene information, calculates the demand of the target vehicle; wherein the demand of the target vehicle indicates the degree of demand of the target vehicle for the sensor in the current scene; based on the confidence of the sensor, the coupling degree of the sensor and the demand of the target vehicle, determines the coupling-decoupling strategy of multiple sensors; wherein the coupling degree of the sensor indicates the degree of demand of the target vehicle in the current scene. The number and degree of sensors in a coupled state. The coupling-decoupling strategy of sensors includes decoupling sensors in a coupled state and coupling sensors in a decoupled state. That is, by acquiring scene information of the scene in which the target vehicle is located, the confidence of each sensor and the demand of the target vehicle are determined based on the scene information. Based on the demand of the target vehicle, the confidence and coupling degree of the sensor, the coupling-decoupling strategy of multiple sensors is comprehensively determined. This can optimize the coupling state of the sensor while meeting the current scene requirements, thereby reducing the complexity of the system and improving the computing efficiency of the system, thereby providing accurate and efficient perception information for autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flow chart of a coupling-decoupling control method of a vehicle-mounted sensor provided by an exemplary embodiment of the present application.

[0018] Figure 2 It is a structural schematic diagram of a coupling and decoupling control device of a vehicle-mounted sensor provided by an exemplary embodiment of the present application.

[0019] Figure 3 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0020] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0021] Figure 1 FIG. 1 is a flow chart of a coupling and decoupling control method of a vehicle-mounted sensor provided by an exemplary embodiment of the present application. Figure 1 As shown, the coupling-decoupling control method of the vehicle-mounted sensor includes the following steps:

[0022] Step 110: Obtain scene information of the current scene where the target vehicle is located.

[0023] Specifically, the present application obtains the driving state and driving environment information of the target vehicle through sensors, and determines the current scene and corresponding scene information of the target vehicle based on the driving state and driving environment, such as driving in an underground parking lot, driving in adverse conditions (rainy and snowy weather, etc.).

[0024] Step 120: Based on the scene information, obtain the confidence of the sensor of the target vehicle.

[0025] Among them, the confidence of the sensor represents the accuracy of the data obtained by the sensor in the current scene. After determining the scene information of the current scene where the target vehicle is located, this application determines the confidence of each sensor of the target vehicle based on the scene information to determine the accuracy of the data obtained by each sensor in the current scene, thereby better providing an accurate perception data basis for subsequent driving decisions.

[0026] Step 130: Calculate the demand of the target vehicle based on the scenario information.

[0027] The target vehicle's need degree indicates the target vehicle's need degree for sensors in the current scene. This application calculates the target vehicle's need degree for sensors based on the scene information of the current scene in which the target vehicle is located, that is, the target vehicle's need degree for sensor data in the current scene, corresponding to the type and accuracy of sensor data required by the target vehicle.

[0028] Step 140: Determine the coupling and decoupling strategies of the multiple sensors based on the confidence level of the sensors, the coupling level of the sensors, and the demand level of the target vehicle.

[0029] The coupling degree of the sensor indicates the number and degree of the sensors in the coupled state, and the coupling-decoupling strategy of the sensor includes decoupling the sensors in the coupled state and coupling the sensors in the decoupled state.

[0030] This application determines the coupling and decoupling strategy of the target vehicle's sensor based on the target vehicle's demand, combined with the sensor's confidence and coupling degree. Specifically, this application determines the required number of sensors and the accuracy of the sensed data based on the target vehicle's demand, and then determines the corresponding number of sensors and the corresponding coupling degree based on the target vehicle's demand, and adjusts the number and coupling degree of sensors based on the current sensor coupling degree to meet the current needs of the target vehicle, thereby minimizing the system's computing power requirements while meeting the target vehicle's needs.

[0031] The present application provides a coupling-decoupling control method for a vehicle-mounted sensor, which obtains scene information of a current scene in which a target vehicle is located; based on the scene information, obtains the confidence of the sensor of the target vehicle; wherein the confidence of the sensor indicates the accuracy of the data obtained by the sensor in the current scene; based on the scene information, calculates the demand of the target vehicle; wherein the demand of the target vehicle indicates the degree of demand of the target vehicle for the sensor in the current scene; based on the confidence of the sensor, the coupling degree of the sensor, and the demand of the target vehicle, determines the coupling-decoupling strategy of multiple sensors; wherein the coupling degree of the sensor indicates the number and degree of sensors in a coupled state, and the coupling-decoupling strategy of the sensor includes decoupling sensors in a coupled state and coupling sensors in a decoupling state; that is, by obtaining the scene information of the scene in which the target vehicle is located, determining the confidence of each sensor and the demand of the target vehicle based on the scene information, and comprehensively determining the coupling-decoupling strategy of multiple sensors based on the demand of the target vehicle, the confidence and coupling degree of the sensor, so that the coupling state of the sensor can be optimized while meeting the current scene requirements, so as to reduce the complexity of the system, thereby improving the computing efficiency of the system, and then providing accurate and efficient perception information for autonomous driving.

[0032] In one embodiment, the scene information includes any one or more combinations of the following information: location information, weather information, brightness information, and road condition information; wherein, the specific implementation method of the above step 120 may be: based on the scene information, comprehensively calculate the confidence level of the sensor of the target vehicle.

[0033] Specifically, smart driving vehicles rely on sensor information coupling to achieve perception of the surrounding environment. After the automatic driving system is turned on, the sensors begin to collect data. After time alignment, the confidence list of various sensors that change with the scene is calculated. The confidence list contains the confidence of each sensor under different scene information (including light visibility, rain, snow, fog, haze, temperature and humidity, etc.), and the confidence list is obtained through large model training. After determining the scene information, this application obtains the confidence of each sensor based on the scene information by looking up the table.

[0034] For example, in tunnel scenarios or underground parking lot scenarios, the confidence of GPS sensors and GNSS sensors is low, while in open environments, the confidence of GPS sensors and GNSS sensors is high; in forward collision scenarios, the confidence of the front-view camera is high; for another example, in severe weather conditions (such as rain, snow or fog), the field of view of the sensor may be limited, and millimeter-wave radar can provide stable performance due to its strong penetration ability, so its confidence in this scenario is high; at night or in low-light environments, the effect of the visual camera will be affected, and its confidence is low, while the combined use of infrared or thermal imaging cameras can improve night vision capabilities, and its confidence is high; the visual camera can assist in the identification of traffic signs and traffic lights, and its confidence is high in this scenario.

[0035] Preferably, the present application can verify the confidence of sensors with the same principle to ensure the correctness of the confidence; specifically, the present application can use multiple sensors to detect the same value, and calculate the average value based on the results of the detection of multiple sensors. The confidence level is lower when the deviation from the average value is larger, and the confidence level is higher when the deviation from the average value is smaller.

[0036] In one embodiment, the specific implementation method of the above step 130 can be: based on the scene information, calculate the complexity, urgency and coverage of the perception data required by the target vehicle; based on the complexity, urgency and coverage of the perception data required by the target vehicle, calculate the demand of the target vehicle.

[0037] After determining the scene information of the target vehicle, the present application calculates the complexity, urgency and coverage of the perception data required by the target vehicle based on the scene information, that is, the scope, quantity, accuracy, urgency requirements, etc. of the perception data required by the target vehicle are determined according to the driving scene of the target vehicle, and the requirement of the target vehicle is determined based on the complexity, urgency and coverage. Specifically, the present application calculates the complexity of the required perception data for different scenes. S(t) , Urgency E(t) , coverage C(t) , and based on complexity S(t) , Urgency E(t) , coverage C(t) Computational sensing data needs D(t) , specifically: D(t)=f(S,E,C) ,in, f is the relationship function between the demand degree of the target vehicle and complexity, urgency, and coverage, which can be calculated through a large amount of measured data; this application divides complexity, urgency, and coverage into 4 levels. When the demand degree of the target vehicle reaches D(t) When the value reaches a preset value (for example, 10), the corresponding demand degree is set to be the highest.

[0038] In one embodiment, the specific implementation of the above step 140 may be: if the coupling degree of the sensor is within the required range corresponding to the required degree of the target vehicle, the coupling and decoupling states of the multiple sensors are maintained unchanged.

[0039] Specifically, the present application determines whether the coupling degree of the sensor matches the demand degree of the target vehicle for scenarios with different demand degrees. If not, a coupling or decoupling operation is required to achieve a state in which the coupling degree of the sensor matches the demand degree of the target vehicle. For example, if the coupling degree of the sensor is within the range of [95%, 105%] of the demand degree of the target vehicle, it is determined that the coupling degree of the sensor matches the demand degree of the target vehicle, that is, the current coupling degree of the sensor meets the demand degree requirements of the current scenario, and the current coupling and decoupling state of the sensor is maintained unchanged.

[0040] In one embodiment, the specific implementation method of the above step 140 may be: if there is a sensor whose confidence is less than a preset confidence threshold, or the coupling degree of the sensor is greater than the upper limit of the demand corresponding to the demand degree of the target vehicle, then decouple one or more sensors with the smallest confidence.

[0041] Specifically, if the coupling degree of the sensor is greater than the upper limit of the demand corresponding to the demand degree of the target vehicle, for example, the coupling degree of the sensor is greater than 105% of the demand degree of the target vehicle, it means that the coupling degree of the sensor is greater than the actual demand of the current scene. In order to save computing power, this application can release computing power by decoupling one or more sensors. Specifically, this application can decouple the sensor with the lowest confidence to ensure perception accuracy. If there is a sensor with a confidence level less than the confidence threshold (for example, 0.5) among the coupled sensors, it means that the accuracy of the data perceived by the sensor in the current scene is low. At this time, the sensor is decoupled to improve the perception accuracy.

[0042] Preferably, when determining whether decoupling is needed, decoupling is not performed immediately when the driving scene appears, but decoupling is started after the demand degree of the current scene passes through a specific integrator.

[0043] In one embodiment, the specific implementation of the above step 140 may be: if the coupling degree of the sensor is less than the lower limit of the demand corresponding to the demand degree of the target vehicle, one or more sensors in a decoupled state are coupled.

[0044] Specifically, if the coupling degree of the sensor is less than the lower limit of the demand corresponding to the demand degree of the target vehicle, for example, the coupling degree of the sensor is less than 95% of the demand degree of the target vehicle, it means that the coupling degree of the sensor is less than the actual demand of the current scene. In order to ensure the perception accuracy, the present application can improve the perception accuracy by coupling one or more sensors. Specifically, the present application can couple the uncoupled sensor with the highest confidence to ensure the perception accuracy.

[0045] Preferably, when determining whether coupling is needed, coupling is not performed immediately when the driving scene occurs, but coupling is performed after the demand degree of the current scene passes through a specific integrator. The transition time between the current state and the decoupling or coupling is called the cooling state, and the sensor perception state can be divided into four stages: complete decoupling state, partial decoupling state (there are still more than two sensor couplings), coupling state, and cooling state (maintaining the previous coupling or decoupling state).

[0046] When the decoupling or coupling conditions are met, this application adopts cooling treatment within the specified time (for example, the cooling time is 30 minutes), and keeps the original perception data state unchanged (i.e., cooling state) during the cooling process to observe whether the decoupling or coupling conditions are still met during the cooling period, whether there are interference and other external factors, and avoid the system frequently switching back and forth between several states, causing unnecessary computing power and resource loss. Specifically, by determining whether the integrator of the current scene meets a certain threshold, the sensor will be coupled or decoupled only when it is met. This application mainly relates to intelligent driving vehicles and various sensors thereof (including lidar, millimeter-wave radar, camera, ultrasonic radar, etc.), among which the performance and functions of each sensor are shown in the following table:

[0047] Table 1 Sensor performance and function comparison

[0048]

[0049] This application can determine the demand degree and required sensors for the current scene based on the functions required in the current scene and in combination with the above table.

[0050] In one embodiment, a specific implementation method of coupling one or more sensors in a decoupled state may be: obtaining category information of the sensors to be coupled; based on the category information, highly integrating sensors of the same category and coupling perception information obtained by sensors of different categories.

[0051] This application targets different types of sensors, and selects coupling methods of different strategies according to the similarities and differences in their working principles; the deeper the degree of coupling, the higher the complexity and computing power requirements of the system, so local coupling is preferred under the premise of meeting the needs of the current scene. If the requirements are not met, the degree of coupling is deepened; to ensure the speed and efficiency of execution, the coupling algorithms in different scenarios are trained and optimized. For sensors of the same type, tight coupling is used for coupling, that is, the data collected by the same type of sensors is processed through an optimized filter. Tight coupling is the process of adding environmental information features to the feature vector and finally obtaining the perception result information. For sensors of different types, loose coupling is used for coupling, that is, each sensor performs calculations to obtain its own perception information, and then transmits the perception information to the relevant domain controller for coupling processing. Among them, loose coupling maintains the module independence of each sensor, and couples after separate calculations; tight coupling is highly integrated to improve more accurate coupling results.

[0052] Figure 2 FIG. 1 is a schematic diagram of a coupling and decoupling control device for a vehicle-mounted sensor provided by an exemplary embodiment of the present application. Figure 2 As shown, the coupling-decoupling control device 20 of the vehicle-mounted sensor includes: a scene information acquisition module 21, which is used to obtain the scene information of the current scene in which the target vehicle is located; a confidence determination module 22, which is used to obtain the confidence of the sensor of the target vehicle based on the scene information; wherein the confidence of the sensor represents the accuracy of the sensor in acquiring data in the current scene; a demand calculation module 23, which is used to calculate the demand of the target vehicle based on the scene information; wherein the demand of the target vehicle represents the degree of demand for the sensor by the target vehicle in the current scene; a coupling-decoupling strategy determination module 24, which is used to determine the coupling-decoupling strategy of multiple sensors based on the confidence of the sensor, the coupling degree of the sensor, and the demand degree of the target vehicle; wherein the coupling degree of the sensor represents the number and degree of sensors in a coupled state, and the coupling-decoupling strategy of the sensor includes decoupling sensors in a coupled state and coupling sensors in a decoupling state.

[0053] The present application provides a coupling-decoupling control device for a vehicle-mounted sensor, which obtains scene information of a current scene in which a target vehicle is located through a scene information acquisition module 21; a confidence determination module 22 obtains the confidence of the sensor of the target vehicle based on the scene information; wherein the confidence of the sensor indicates the accuracy of the data acquired by the sensor in the current scene; a demand calculation module 23 calculates the demand of the target vehicle based on the scene information; wherein the demand of the target vehicle indicates the degree of demand of the target vehicle for the sensor in the current scene; a coupling-decoupling strategy determination module 24 determines the coupling-decoupling strategy of multiple sensors based on the confidence of the sensor, the coupling degree of the sensor, and the demand of the target vehicle. ; Among them, the coupling degree of the sensor represents the number and degree of the sensors in the coupled state, and the coupling-decoupling strategy of the sensor includes decoupling the sensors in the coupled state and coupling the sensors in the decoupled state; that is, by acquiring the scene information of the scene in which the target vehicle is located, the confidence of each sensor and the demand of the target vehicle are determined based on the scene information, and based on the demand of the target vehicle, the confidence and coupling degree of the sensor, the coupling-decoupling strategy of multiple sensors is comprehensively determined, so that the coupling state of the sensor can be optimized while meeting the current scene requirements, so as to reduce the complexity of the system, thereby improving the computing efficiency of the system, and then providing accurate and efficient perception information for autonomous driving.

[0054] In one embodiment, the scene information includes any one or more combinations of the following information: location information, weather information, brightness information, and road condition information; wherein the confidence determination module 22 may be further configured to: based on the scene information, comprehensively calculate the confidence of the sensor of the target vehicle.

[0055] In one embodiment, the demand calculation module 23 can be further configured to: calculate the complexity, urgency and coverage of the perception data required by the target vehicle based on the scene information; calculate the demand of the target vehicle based on the complexity, urgency and coverage of the perception data required by the target vehicle.

[0056] In one embodiment, the coupling-decoupling strategy determination module 24 may be further configured to: if the coupling degree of the sensor is within the required range corresponding to the required degree of the target vehicle, maintain the coupling-decoupling state of the multiple sensors unchanged.

[0057] In one embodiment, the coupling-decoupling strategy determination module 24 can be further configured as follows: if there is a sensor whose confidence is less than a preset confidence threshold, or the coupling degree of the sensor is greater than the upper limit of the demand corresponding to the demand degree of the target vehicle, then one or more sensors with the smallest confidence are decoupled.

[0058] In one embodiment, the coupling-decoupling strategy determination module 24 may be further configured to couple one or more sensors in a decoupled state if the coupling degree of the sensor is less than the lower limit of the demand degree corresponding to the target vehicle.

[0059] In one embodiment, the coupling-decoupling strategy determination module 24 may be further configured to: obtain category information of sensors to be coupled; based on the category information, highly integrate sensors of the same category and couple perception information obtained by sensors of different categories.

[0060] Below, reference Figure 3 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0061] Figure 3 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0062] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0063] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0064] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0065] In one example, the electronic device 10 may further include: an input device 13 and an output device 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0066] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0067] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0068] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0069] Of course, to simplify, Figure 3 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0070] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0071] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0072] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0073] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0074] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0075] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0076] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0077] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0078] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A coupling and decoupling control method for a vehicle-mounted sensor, characterized in that: include: Obtain scene information of the current scene where the target vehicle is located; Based on the scene information, the confidence of the sensor of the target vehicle is obtained; wherein the confidence of the sensor represents the accuracy of the data acquired by the sensor in the current scene; Based on the scenario information, the demand degree of the target vehicle is calculated; wherein the demand degree of the target vehicle represents the degree of demand of the target vehicle for the coupling degree of the sensor in the current scenario; Based on the confidence of the sensor, the current coupling degree of the sensor, and the demand degree of the target vehicle, the coupling-decoupling strategy of the multiple sensors is determined; wherein the current coupling degree of the sensor represents the number and degree of the sensors currently in a coupled state, and the coupling-decoupling strategy of the sensor includes decoupling the sensors in a coupled state and coupling the sensors in a decoupled state.

2. The coupling and decoupling control method of the vehicle-mounted sensor according to claim 1, characterized in that: The scene information includes any one or more combinations of the following information: location information, weather information, brightness information, and road condition information; wherein, based on the scene information, obtaining the confidence of the sensor of the target vehicle includes: Based on the scene information, the confidence level of the sensor of the target vehicle is obtained by comprehensive calculation.

3. The coupling-decoupling control method of the vehicle-mounted sensor according to claim 1, characterized in that: The calculating the demand degree of the target vehicle based on the scenario information includes: Based on the scene information, the complexity, urgency and coverage of the perception data required by the target vehicle are calculated; The demand degree of the target vehicle is calculated based on the complexity, urgency and coverage of the perception data required by the target vehicle.

4. The coupling and decoupling control method of the vehicle-mounted sensor according to claim 1, characterized in that: The step of determining the coupling and decoupling strategies of the plurality of sensors based on the confidence of the sensor, the current coupling degree of the sensor, and the demand degree of the target vehicle includes: If the current coupling degree of the sensor is within the coupling degree requirement range corresponding to the requirement degree of the target vehicle, the coupling and decoupling states of the plurality of sensors are maintained unchanged.

5. The coupling-decoupling control method of the vehicle-mounted sensor according to claim 1, characterized in that: The step of determining the coupling and decoupling strategies of the plurality of sensors based on the confidence of the sensor, the current coupling degree of the sensor, and the demand degree of the target vehicle includes: If there is a sensor whose confidence is less than a preset confidence threshold, or the current coupling degree of the sensor is greater than the coupling degree requirement upper limit corresponding to the requirement degree of the target vehicle, one or more sensors with the smallest confidence are decoupled.

6. The coupling-decoupling control method of the vehicle-mounted sensor according to claim 1, characterized in that: The step of determining the coupling and decoupling strategies of the plurality of sensors based on the confidence of the sensor, the current coupling degree of the sensor, and the demand degree of the target vehicle includes: If the current coupling degree of the sensor is less than the coupling degree requirement lower limit corresponding to the requirement degree of the target vehicle, one or more sensors in a decoupled state are coupled.

7. The coupling-decoupling control method of the vehicle-mounted sensor according to claim 6, characterized in that: The coupling of one or more sensors in a decoupled state comprises: Obtaining category information of the sensor to be coupled; Based on the category information, sensors of the same category are highly integrated and perception information obtained by sensors of different categories are coupled.

8. A coupling and decoupling control device for a vehicle-mounted sensor, characterized in that: include: A scene information acquisition module is used to obtain scene information of the current scene where the target vehicle is located; A confidence determination module, used to obtain the confidence of the sensor of the target vehicle based on the scene information; wherein the confidence of the sensor represents the accuracy of the data obtained by the sensor in the current scene; A demand degree calculation module, used to calculate the demand degree of the target vehicle based on the scenario information; wherein the demand degree of the target vehicle represents the degree of demand of the target vehicle for the coupling degree of the sensor in the current scenario; A coupling-decoupling strategy determination module is used to determine the coupling-decoupling strategies of the multiple sensors based on the confidence of the sensors, the current coupling degree of the sensors, and the demand degree of the target vehicle; wherein the current coupling degree of the sensors represents the number and degree of the sensors currently in a coupled state, and the coupling-decoupling strategy of the sensors includes decoupling sensors in a coupled state and coupling sensors in a decoupled state.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the coupling and decoupling control method of the vehicle-mounted sensor described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the coupling and decoupling control method of the vehicle-mounted sensor described in any one of claims 1 to 7.

Images