Method for determining occupancy situation of position, and related device

Abstract

A method for determining an occupancy situation of a position, and an apparatus. The method comprises: acquiring measurement data, the measurement data comprising a first distance and a first angle, and the first angle comprising a first azimuth angle and / or a first elevation angle (201); on the basis of the first distance, determining a first parameter value used for indicating an occupancy situation of a first position by an object (202); on the basis of the first angle, determining an angle adjustment factor corresponding to the first position (203); and on the basis of the first parameter value and the angle adjustment factor, determining a second parameter value of the first position (204), the second parameter value indicating the occupancy situation of the first position by the object. In the method, the occupancy situation of the first position by the object is determined by means of more information, and the impact of the distance and the angle on the occupancy situation of the first position by the object is separately independently determined, thereby improving the accuracy of the finally obtained occupancy situation of the position.

Description

Method for determining occupancy of a position and related device

[0001] The present application claims priority from the Chinese patent application No. 202410965450.8 filed on July 17, 2024, and entitled "Method for determining occupancy of a position and related device", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of computer, and in particular, to a method for determining occupancy of a position and related device. BACKGROUND

[0003] In the related art, the distance corresponding to the object in the field of view range can be measured by a sensor, and the object occupancy of a position in the surrounding environment is calculated according to the aforementioned distance. However, the accuracy of the object occupancy of the position obtained by the aforementioned method is not high enough, and therefore, a more accurate method for determining the occupancy of a position is urgently needed. SUMMARY

[0004] The present application provides a method for determining occupancy of a position and related device, which determines the object occupancy of a first position by means of more information, thereby improving the accuracy of the final obtained occupancy of a position. Moreover, the influence of the distance and the angle on the object occupancy of the first position is determined respectively and independently, thereby further improving the accuracy of the final obtained occupancy of a position.

[0005] The present application provides the following technical solutions:

[0006] In a first aspect, the present application provides a method for determining occupancy of a position, which can be used in the field of intelligent driving. In the method, a first device obtains measurement data, wherein the measurement data includes a first distance and an angle (hereinafter referred to as "first angle" for convenience of description), and the first angle includes a first azimuth angle and / or a first pitch angle. Exemplarily, the measurement data is obtained by a sensor. The first device determines a first parameter value indicating the object occupancy of a first position according to the first distance, determines an angle adjustment factor corresponding to the first position according to the first angle, and then determines a second parameter value corresponding to the first position according to the first parameter value and the angle adjustment factor, wherein the second parameter value indicates the object occupancy of the first position. Exemplarily, the first position can be a position in the field of view range of the sensor.

[0007] Exemplarily, the first device can be a vehicle, a mobile robot, or other types of devices, etc.

[0008] Exemplarily, in a case, the second parameter value can represent a probability that the first position is occupied by the object, and the first parameter value can be a first occupation probability of the first position, the first occupation probability refers to a probability that the first position is occupied by the object based on the distance in the measurement data, and the second occupation probability refers to a probability that the first position is occupied by the object based on the distance and the angle in the measurement data.

[0009] In another case, the second parameter value can be a parameter value obtained by transforming the second occupation probability, for example, the second parameter value can be a ratio equivalent form, represented as: odd=p r,a (r,a) / (1-p r,a (r,a)),wherein, odd is the second parameter value, p r,a (r,a) is the second occupation probability; for another example, the second parameter value can be a logarithmic equivalent form, represented as: log-odd=ln[p r,a (r,a) / (1-p r,a (r,a))],wherein, log-odd is the second parameter value, p r,a (r,a) is the second occupation probability, and the like, or other transformed second occupation probability, for example, can be 1-p r,a (r,a), i.e. the free probability, and correspondingly, there can be a corresponding ratio or logarithmic ratio form; or other equivalent forms derived in other ways, which generally satisfy one-to-one mapping relationship or one-to-one mapping relationship within a specified range, and the specific transformation manner can be determined in combination with actual application scenarios.

[0010] In the implementation manner, when each set of measurement data is acquired by the sensor, not only the distance but also the azimuth angle and / or the pitch angle are acquired, so that not only the first parameter value used to indicate the object occupation condition of the first position is determined according to the acquired distance, but also the angle adjustment factor is determined according to the aforementioned azimuth angle and / or the pitch angle, and then the second parameter value of the first position is finally determined according to the first parameter value and the aforementioned angle adjustment factor, the second parameter value indicating the object occupation condition of the first position, since more information is used to determine the object occupation condition of the first position, the accuracy of the finally obtained second parameter value is improved; and the first parameter value used to indicate the object occupation condition of the first position is determined based on the distance, the angle adjustment factor is determined according to the azimuth angle and / or the pitch angle, that is, the influence of the distance and the angle on the object occupation condition of the first position is respectively and independently determined, the first parameter value is adjusted based on the angle adjustment factor to determine the final object occupation condition of the first position, the precision of the process of determining the object occupation condition of the first position is improved, and the accuracy of the finally obtained second parameter value is further improved.

[0011] In a possible implementation, the first angle adjustment factor is determined based on the first azimuth angle and first quality information, the first quality information being used to reflect an error of the first azimuth angle in the measurement data, or the first quality information can also be understood as being used to reflect a quality of the first azimuth angle in the measurement data. And / or, the second angle adjustment factor is determined based on the first elevation angle and second quality information, the second quality information being used to reflect an error of the first elevation angle in the measurement data, or the first quality information can also be understood as being used to reflect a quality of the first elevation angle in the measurement data. The first angle adjustment factor and / or the second angle adjustment factor are used to determine the angle adjustment factor.

[0012] For example, the first quality information indicates a standard deviation and / or a variance and / or a root mean square error and / or a mean square error of the azimuth angle measurement error. It should be noted that the "azimuth angle measurement error" in the present application can also be referred to as "error of the azimuth angle dimension in the measurement data".

[0013] For example, the second quality information indicates a standard deviation and / or a variance and / or a root mean square error and / or a mean square error of the elevation angle measurement error. It should be noted that the "elevation angle measurement error" in the present application can also be referred to as "error of the elevation angle dimension in the measurement data".

[0014] In the present implementation, the first angle adjustment factor in the azimuth angle dimension is determined based on the first azimuth angle in the measurement data and first quality information reflecting an error of the azimuth angle in the measurement data obtained by the sensor, so that the first angle adjustment factor obtained can fully consider the influence of the error when the azimuth angle is measured by the sensor, which is not only beneficial to obtain a more accurate angle adjustment factor, and further beneficial to obtain a more accurate object occupancy, but also beneficial to make the present scheme self-adaptive to different specifications in the error dimension when the azimuth angle is measured, that is, beneficial to make the present scheme applicable to more sensors, and beneficial to expand the application range of the present scheme.

[0015] The first angle adjustment factor in the elevation angle dimension is determined based on the first elevation angle in the measurement data and second quality information reflecting an error of the elevation angle in the measurement data obtained by the sensor, so that the second angle adjustment factor obtained can fully consider the influence of the error when the elevation angle is measured by the sensor, which is not only beneficial to obtain a more accurate angle adjustment factor, and further beneficial to obtain a more accurate object occupancy, but also beneficial to make the present scheme self-adaptive to different specifications in the error dimension when the elevation angle is measured, that is, beneficial to make the present scheme applicable to more sensors, and beneficial to expand the application range of the present scheme.

[0016] In a possible implementation, the first angle adjustment factor is determined according to the first azimuth angle, the second azimuth angle, and the first quality information based on a first function, where the first function is a Gaussian function, or the first function is based on an error function erf, or the first function is based on an activation function sigmoid. And / or, the second angle adjustment factor is determined according to the first elevation angle, the second elevation angle, and the second quality information based on a second function, where the second function is a Gaussian function, or the second function is based on an error function erf, or the second function is based on an activation function sigmoid.

[0017] In the implementation, the first angle adjustment factor and the second angle adjustment factor are determined based on a function, which improves the realizability of the scheme, and the first function (or the second function) is a Gaussian function, or is based on an error function, or is based on an activation function, which provides a simple and effective implementation scheme.

[0018] In a possible implementation, the first parameter value is a first occupancy probability, the second parameter value is a second occupancy probability, and the second occupancy probability, the first occupancy probability, and the angle adjustment factor satisfy the following relationship: p r,a (r,a)=c0+(p r (r)-c1)·F(a) where p r,a (r,a) is the second occupancy probability, p r (r) is the first occupancy probability, F(a) is the angle adjustment factor, and the values of c0 and c1 are preset values.

[0019] In the implementation, the relationship between the second occupancy probability, the first occupancy probability, and the angle adjustment factor is disclosed, which improves the realizability of the scheme; the closer the relative position between the first position and the sensor to the measurement data, the greater the object occupancy probability of the first position, the second occupancy probability obtained by using the method provided in the application is expected, and since the relationship between the distance in the measurement data and the idle probability at the first position no longer needs to be modeled in the scheme provided in the application, the implementation difficulty of the scheme is greatly reduced.

[0020] In a possible implementation, c0 and c1 are both 0.5. In this implementation, the values of c0 and c1 are further disclosed, which further improves the realizability of the scheme, and the product of the difference between the first occupancy probability and 0.5 and the angle adjustment factor is added to 0.5 to obtain the final second occupancy probability, and the final value of the second occupancy probability fluctuates on the basis of 0.5, the occupancy probability of a region outside the predetermined range of the position corresponding to the measurement data and close to the sensor is lower than 0.5, and tends to a minimum value as the distance difference and the angle difference decrease, which meets the expectation that the occupancy state tends to be idle. In addition, the occupancy probability of a position outside the predetermined range of the position corresponding to the measurement data and far from the sensor tends to 0.5, which meets the expectation of uncertainty, because the occupancy probability of a position is 0.5, which means that it is completely uncertain whether the position is occupied by an object (the occupancy probability is 0.5 and the idle probability is also 0.5). More importantly, the occupancy probability of the position corresponding to the measurement data is the highest, and the occupancy probability of a position in the specified range near the position corresponding to the measurement data gradually decreases, which meets the expectation that the occupancy probability of the position corresponding to the measurement data is the highest. Because the occupancy probability of a position in the specified range near the position corresponding to the measurement data is generated depending on the measurement error, it is also expected that the occupancy probability of a position in the specified range near the position corresponding to the measurement data gradually decreases. The measurement data obtained based on the sensor can increase or decrease the probability that the position is occupied by an object, and the design that the values of c0 and c1 are both 0.5 is more conducive to making the final second occupancy probability meet the foregoing expectations, so as to be conducive to obtaining a more accurate second occupancy probability of a position through the formula, and to be conducive to more accurately determining the object occupancy of the position.

[0021] In a possible implementation, the first position and the measurement data satisfy a preset condition, and the preset condition includes at least one of the following: an absolute value of a difference between a distance corresponding to the first position (hereinafter referred to as a “second distance” for convenience of description) and the first distance is less than or equal to a distance threshold value, and / or an absolute value of a difference between an azimuth angle corresponding to the first position (hereinafter referred to as a “second azimuth angle” for convenience of description) and the first azimuth angle is less than or equal to a first angle value, and / or an absolute value of a difference between an elevation angle corresponding to the first position (hereinafter referred to as a “second elevation angle” for convenience of description) and the first elevation angle is less than or equal to a second angle value.

[0022] The second distance corresponding to the first position can be a distance between the first position and an origin of the sensor coordinate system or the carrier coordinate system, the second azimuth angle corresponding to the first position can be an azimuth angle of the first position relative to the sensor coordinate system or the carrier coordinate system, and the second pitch angle corresponding to the first position can be a pitch angle of the first position relative to the sensor coordinate system or the carrier coordinate system. It should be understood that the first distance, the second distance, the first azimuth angle, the second azimuth angle, the first pitch angle, and the second pitch angle are all relative to data in the same coordinate system.

[0023] Exemplarily, if the first device is a vehicle, the carrier coordinate system is a vehicle body coordinate system, and the origin of the vehicle body coordinate system can be located at the center of the rear axle of the vehicle body or the landing point of the center of the rear axle; if the first device is a mobile robot, the carrier coordinate system is a robot coordinate system, and the specific form of the carrier coordinate system can be determined in combination with an actual application scenario.

[0024] Since a specific measurement data is generated based on an object at a specific position in the surrounding environment, theoretically, it is meaningful to determine the object occupancy of the specific position based on the specific measurement data, and it is meaningless to determine the object occupancy of a position other than the specific position based on the specific measurement data. In this application, a preset condition is set, so that a specific measurement data in this application will only be used to determine the object occupancy of a first position that meets the preset condition with the measurement data. Compared with the case where each measurement data is used to determine the object occupancy of each position, the meaningless calculation is greatly reduced, thereby effectively reducing the computing power requirement of this application, and the effective utilization rate of computer resources is improved.

[0025] Further, the distance, azimuth angle, and / or pitch angle in the measurement data are used for screening, which provides a simple and easy-to-operate screening method. In addition, considering that the distance, azimuth angle, and / or pitch angle in the measurement data may have errors, so that there may be errors between the position of the object of the measurement data and the position pointed by the measurement data, the distance threshold value, the first angle value, and / or the second angle value are set in the preset condition. Compared with the case where the preset condition is set as “the distance corresponding to the first position is equal to the first distance, and / or, the azimuth angle corresponding to the first position is equal to the first azimuth angle, and / or, the pitch angle corresponding to the first position is equal to the first pitch angle”, the object occupancy of the position where the measurement data is generated can be determined by using a specific measurement data while avoiding wasting computer resources as much as possible.

[0026] In a possible implementation, the distance threshold value is determined based on a standard deviation or a root mean square error reflecting a distance measurement error, the first angle value is determined based on a standard deviation or a root mean square error reflecting an azimuth angle measurement error, and the second angle value is determined based on a standard deviation or a root mean square error reflecting a pitch angle measurement error.

[0027] Optionally, the distance threshold value can be a product of a standard deviation or a root mean square error reflecting a distance measurement error and a first multiple, for example, the first multiple can be 1.5 times, 2 times, 2.5 times, 2.6 times, 2.8 times, 3 times, 4 times, or other values.

[0028] Optionally, the first angle value can be a product of a standard deviation reflecting an azimuth angle measurement error and a second multiple, for example, the second multiple can be 2 times, 2.5 times, 2.6 times, 2.8 times, 3 times, 3.5 times, or other values. The second angle value can be a product of a standard deviation reflecting a pitch angle measurement error and a third multiple, the third multiple and the second multiple can be the same or different, for example, the third multiple can be 2 times, 2.5 times, 2.6 times, 2.8 times, 3 times, 3.5 times, or other values.

[0029] In the implementation, the standard deviation or the root mean square error reflecting the measurement distance error can indicate an error of the distance in the measurement data, the standard deviation or the root mean square error reflecting the measurement azimuth angle error can indicate an error of the azimuth angle in the measurement data, and the standard deviation or the root mean square error reflecting the measurement pitch angle error can indicate an error of the pitch angle in the measurement data. In the application, the distance threshold value is determined based on the standard deviation or the root mean square error reflecting the measurement distance error, the first angle value is determined based on the standard deviation or the root mean square error reflecting the measurement azimuth angle error, and the second angle value is determined based on the standard deviation or the root mean square error reflecting the measurement pitch angle error, thereby facilitating compatibility of sensors with different error specifications and expansion of application scenarios of the application.

[0030] In a possible implementation, the first parameter value is obtained based on the first distance and third quality information, and the third quality information is used to reflect an error of the first distance in the measurement data, or the third quality information can also be understood as quality used to reflect the first distance in the measurement data.

[0031] For example, the third quality information indicates a standard deviation and / or variance and / or root mean square error and / or mean square error of the distance measurement error. It should be noted that the "distance measurement error" in the application can also be referred to as "error of the distance dimension in the measurement data".

[0032] In the present implementation, the object occupancy of a certain position in the distance dimension (i.e., the first parameter value) is determined based on the first distance in the measurement data and the third quality information which can accurately reflect the error of the distance in the measurement data obtained by the sensor, so that the first parameter value obtained can fully consider the influence of the error of the sensor when measuring the distance, which is not only conducive to obtaining a more accurate first parameter value, and thus conducive to obtaining a more accurate object occupancy, but also conducive to making the present scheme adaptive to different specifications in the dimension of the error when measuring the distance, i.e., conducive to making the present scheme applicable to more sensors, and conducive to expanding the scope of application of the present scheme.

[0033] In a possible implementation, at least one measurement data is obtained by the sensor, and the at least one measurement data is used to obtain a map corresponding to the field of view range of the sensor, and each measurement data is used to obtain the second parameter value of one or more first positions in the map.

[0034] Optionally, the above map can be specifically represented as a grid map, and the positions in the map can be represented as grid units in the grid map. For example, the grid map can include a plurality of grids and the second parameter value of each grid.

[0035] In the present implementation, a specific application scenario of the occupancy of the position obtained based on the measurement data is provided, and the degree of combination between the present scheme and the specific application scenario is improved.

[0036] In a second aspect, the present application provides a determination apparatus of the occupancy of a position, which comprises: an acquisition module, configured to acquire measurement data, the measurement data comprising a first distance and an angle, the angle comprising a first azimuth angle and / or a first pitch angle; a determination module, configured to determine a first parameter value for indicating the object occupancy of a first position according to the first distance; the determination module is further configured to determine an angle adjustment factor corresponding to the first position according to the angle; and the determination module is further configured to determine a second parameter value corresponding to the first position according to the first parameter value and the angle adjustment factor, the second parameter value indicating the object occupancy of the first position.

[0037] In the second aspect of the present application, the determination apparatus of the occupancy of a position is further configured to perform the steps performed by the first device in the first aspect and the various possible implementation manners of the first aspect, and the meanings of the terms in the second aspect of the present application and the various possible implementation manners, and the beneficial effects brought by each possible implementation manner can be referred to the description in the various possible implementation manners of the first aspect, which will not be repeated here.

[0038] In a third aspect, an apparatus is provided, which includes a processor and a memory coupled to the processor, the memory storing a program; and the processor configured to execute the program in the memory to cause the apparatus to perform the method of the first aspect.

[0039] In a fourth aspect, a vehicle is provided, which includes a processor and a memory coupled to the processor, the memory storing a program; and the processor configured to execute the program in the memory to cause the vehicle to perform the method of the first aspect.

[0040] In a fifth aspect, a computer readable storage medium is provided, which stores a computer program, and when the computer program is run on a computer, the computer is caused to perform the method of the first aspect.

[0041] In a sixth aspect, a computer program product is provided, which includes a program, and when the program is run on a computer, the computer is caused to perform the method of the first aspect.

[0042] In a seventh aspect, a chip system is provided, which includes a processor configured to support the functions involved in the above aspects, such as sending or processing the data and / or information involved in the above method. In a possible design, the chip system further includes a memory configured to save the necessary program instructions and data of the terminal device or the communication device. The chip system can be composed of a chip, or include a chip and other discrete devices. BRIEF DESCRIPTION OF DRAWINGS

[0043] FIG. 1 is a structural schematic diagram of an artificial intelligence subject framework provided by the present application;

[0044] FIG. 2 is a schematic diagram of a method for determining the occupancy of a position provided by an embodiment of the present application;

[0045] FIG. 3 is a schematic diagram of a second function term provided by an embodiment of the present application;

[0046] FIG. 4 is a schematic diagram of a first occupancy probability provided by an embodiment of the present application;

[0047] FIG. 5 is a schematic diagram of a first function provided by an embodiment of the present application;

[0048] FIG. 6 is a schematic diagram of a second parameter value obtained by using the method provided by the present application provided by an embodiment of the present application;

[0049] FIG. 7 is another schematic diagram of a method for determining the occupancy of a position provided by an embodiment of the present application;

[0050] FIG. 8 is another schematic diagram of a method for determining an occupancy of a location according to an embodiment of the present application;

[0051] FIG. 9 is a schematic diagram of an apparatus for determining an occupancy of a location according to an embodiment of the present application;

[0052] FIG. 10 is a schematic diagram of an apparatus according to an embodiment of the present application;

[0053] FIG. 11 is a schematic diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] The embodiments of the present application will be described below in conjunction with the accompanying drawings. It is apparent that the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. It is obvious for those skilled in the art that the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems with the emergence of new application scenarios.

[0055] The terms "first", "second", etc. in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, which is only a distinguishing way used in the description of the embodiments of the present application for the same attribute objects in the description. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the processes, methods, systems, products or equipment containing a series of units do not have to be limited to those units, but can include other units not clearly listed or inherent to these processes, methods, products or equipment.

[0056] In the embodiments of the present application, "indication" can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by certain information (indication information as described below) is referred to as to-be-indicated information, and there are many ways to indicate the to-be-indicated information in the specific implementation process, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship; the to-be-indicated information can also be indicated only by a part, and the other part of the to-be-indicated information is known or agreed in advance, for example, the arrangement order of each information can be used to indicate a specific information by means of pre-agreement (for example, protocol definition), thereby reducing the indication overhead to a certain extent. The specific manner of indication is not limited in the present application. It can be understood that the indication information can be used to indicate the to-be-indicated information for the sender of the indication information, and the indication information can be used to determine the to-be-indicated information for the receiver of the indication information.

[0057] First, the overall workflow of the artificial intelligence system is described, please refer to FIG. 1, which is a structural schematic diagram of an artificial intelligence main framework provided by the present application. The following describes the artificial intelligence main framework from two dimensions of "intelligent information chain" (horizontal axis) and "IT value chain" (vertical axis). The "intelligent information chain" reflects a series of processes from data acquisition to processing. For example, it can be a general process of intelligent information perception, intelligent information representation and formation, intelligent reasoning, intelligent decision-making, intelligent execution and output. In this process, data undergoes a condensation process of "data-information-knowledge-wisdom". The "IT value chain" reflects the value brought by artificial intelligence to the information technology industry from the underlying infrastructure of human intelligence, information (provision and processing technology implementation) to the industrial ecological process of the system.

[0058] (1) Infrastructure

[0059] The infrastructure provides computing power support for the artificial intelligence system, realizes communication with the outside world, and realizes support through the underlying platform. Communication with the outside world through sensors; computing power is provided by intelligent chips, which can specifically use central processing units (CPU), embedded neural network processing units (NPU), graphics processing units (GPU), application specific integrated circuits (ASIC) or field programmable gate arrays (FPGA) and other hardware acceleration chips; the underlying platform includes distributed computing framework and network related platform guarantee and support, which can include cloud storage and computing, interconnection network, etc. For example, sensors and external communication acquire data, which are provided to intelligent chips in the distributed computing system provided by the underlying platform for calculation.

[0060] (2) Data

[0061] The data on the upper layer of the infrastructure is used to represent the data source in the field of artificial intelligence. Data involves graphics, images, voice, text, and also involves Internet of Things data of traditional devices, including business data of existing systems and sensing data such as force, displacement, liquid level, temperature, humidity, etc.

[0062] (3) Data processing

[0063] Data processing usually includes data training, machine learning, deep learning, search, reasoning, decision-making and other methods.

[0064] Among them, machine learning and deep learning can model, extract, preprocess, train, etc. of the symbolic and formalized intelligent information of the data.

[0065] Reasoning refers to simulating the intelligent reasoning mode of human beings in a computer or intelligent system, using formalized information to solve problems according to the reasoning control strategy, and the typical function is search and matching.

[0066] Decision-making refers to the process of decision-making after intelligent information is reasoned, and usually provides functions such as classification, sorting, and prediction.

[0067] (4) General ability

[0068] After the data is processed as mentioned above, some general abilities can be formed based on the results of the data processing, such as algorithms or a general system, for example, translation, text analysis, computer vision processing, speech recognition, image recognition, etc.

[0069] (5) Intelligent products and industry applications

[0070] Intelligent products and industry applications refer to the products and applications of artificial intelligence systems in various fields, which are the packaging of the overall solution of artificial intelligence, and realize the application of intelligent information decision-making products. The application fields mainly include: intelligent terminal, intelligent manufacturing, intelligent transportation, smart home, intelligent medical treatment, intelligent security, intelligent driving, smart city, etc.

[0071] The method provided in the present application can be applied to various application scenarios that need to determine the object occupancy of one or more positions; for example, the method provided in the present application can be used in an application scenario of obtaining measurement data through a sensor and determining the object occupancy of the aforementioned positions according to the measurement data, wherein the aforementioned positions can be located within the field of view of the sensor, and the "position" in the present application can also be referred to as a "position area". The various application scenarios of the method provided in the present application are exemplified as follows.

[0072] 1. Intelligent driving

[0073] For example, when the driving system in a vehicle needs to determine which objects exist in the surrounding environment, measurement data corresponding to the objects within the field of view can be obtained through a sensor, and the object occupancy of one or more positions within the field of view of the sensor can be determined based on the measurement data, so as to understand which objects exist in the surrounding environment; for example, the vehicle can be a car, a truck, a motorcycle, a bus, a ship, an airplane, a helicopter, an entertainment vehicle, an amusement park vehicle, a trolley, a golf cart, or a train, etc., which is not particularly limited in the present application.

[0074] For example, when a driving system in a vehicle needs to determine object occupancy at one or more positions, the sensor can obtain measurement data corresponding to objects in the field of view, determine object occupancy at the positions based on the measurement data, and the like.

[0075] 2. The intelligent terminal

[0076] For example, when a mobile robot or agent needs to determine which objects exist in the surrounding environment, the sensor can obtain measurement data corresponding to objects in the field of view, determine object occupancy at one or more positions in the field of view of the sensor based on the measurement data, and thus be able to understand which objects exist in the surrounding environment; for example, the mobile robot can be a floor cleaning robot, a food delivery robot, or another type of mobile robot, which can be determined in combination with an actual application scenario. It should be noted that the present application can also be applied to other application scenarios, which will not be enumerated one by one here.

[0077] In the related art, the distance measured by the sensor is generally used to calculate object occupancy at one or more positions in the field of view of the sensor, but the accuracy of the final object occupancy at the positions is not high. To solve the foregoing problem, the present application discloses obtaining measurement data obtained by a sensor, the measurement data including a first distance and an angle (hereinafter referred to as a "first angle" for convenience of description), the first angle including a first azimuth angle and / or a first pitch angle; determining a first parameter value indicating object occupancy at a first position based on the first distance, the first position being one position in the field of view of the sensor; determining an angle adjustment factor corresponding to the first position based on the first angle, and then determining a second parameter value of the first position based on the first parameter value and the angle adjustment factor, the second parameter value indicating object occupancy at the first position.

[0078] In the embodiments of the present application, more information is used to determine object occupancy at the first position, which is beneficial to improve the accuracy of the final second parameter value. The first parameter value indicating object occupancy at the first position is determined based on the distance, and the angle adjustment factor is determined based on the azimuth angle and / or the pitch angle, i.e., the influence of the distance and the angle on the object occupancy at the first position is determined independently, respectively. The first parameter value is adjusted based on the angle adjustment factor to determine the final object occupancy at the first position, which improves the degree of refinement of the process of determining the object occupancy at the first position, and is beneficial to further improve the accuracy of the final second parameter value.

[0079] In combination with the foregoing description, the detailed implementation process of the position occupancy determination method provided in the present application is described as follows. Specifically, refer to FIG. 2, which is a schematic diagram of the position occupancy determination method provided in an embodiment of the present application. As shown in FIG. 2, the position occupancy determination method provided in the present application can include the following steps.

[0080] 201. Obtain measurement data, the measurement data including a first distance and a first angle, the first angle including a first azimuth angle and / or a first pitch angle.

[0081] Exemplarily, the first device can obtain at least one measurement data obtained by a sensor, each of the at least one measurement data including a first distance and a first angle. The first device can be a vehicle, a mobile robot or other types of devices, etc., which can be determined according to actual application scenarios.

[0082] Specifically, in one case, the measurement data obtained by the sensor is point cloud data, for example, the sensor can be an ultrasonic sensor, a laser radar sensor, a millimeter wave radar sensor or other sensors capable of measuring point cloud data, etc. Then, step 201 can include that the first device can obtain at least one measurement data measured by the sensor, so that the measurement data obtained by the sensor can be a distance and an angle in a sensor coordinate system.

[0083] In another case, the distance and the angle measured by the first device through the sensor can be in a sensor coordinate system, and the first device can also convert the distance and the angle in the sensor coordinate system to a carrier coordinate system to obtain a distance and an angle in the carrier coordinate system, so that the measurement data obtained by the sensor can also be a distance and an angle in the carrier coordinate system.

[0084] In another case, the measurement data obtained by the sensor can be an image, for example, the sensor can be a photoelectric sensor, for example, the photoelectric sensor can be a camera or an event camera. Before step 201 is performed, the first device can also collect an image through the sensor. Step 201 can include that the first device obtains at least one measurement data according to the image collected by the sensor. For example, the first device can perform post-processing on the collected image to indirectly obtain the distance and the angle in the measurement data. It should be noted that the distance and the angle in the measurement data can be in a sensor coordinate system or in a carrier coordinate system.

[0085] Optionally, the first device can obtain the distance and the angle based on signal processing and / or methods of computer vision or view geometry, etc. from the image collected by the sensor; optionally, the first device can input the image collected by the sensor into a first machine learning model to obtain at least one measurement data output by the first machine learning model. For example, the first machine learning model can be a convolutional neural network, a residual neural network, a neural network based on an attention mechanism, a multiple layer perceptron (MLP), or other types of first machine learning models, etc. which can be determined in combination with actual application scenarios.

[0086] For example, the first distance and the first angle can be the distance and the angle of a position on an object within the field of view of the sensor relative to the sensor coordinate system or the carrier coordinate system; that is, the first distance can be the distance between the position on the object within the field of view of the sensor and the origin of the sensor coordinate system, and the first azimuth angle can be the azimuth angle of the position relative to the sensor coordinate system; or the first distance can be the distance between the position on the object within the field of view of the sensor and the origin of the carrier coordinate system, and the first azimuth angle can be the azimuth angle of the position relative to the carrier coordinate system. The sensor coordinate system can be a spherical coordinate system or a rectangular coordinate system.

[0087] For example, if the first device is a vehicle and the carrier coordinate system is a vehicle body coordinate system, the origin of the vehicle body coordinate system can be located at the center of the rear axle of the vehicle body or the landing point of the center of the rear axle; if the first device is a mobile robot and the carrier coordinate system is a robot coordinate system, etc., the specific form of the carrier coordinate system can be determined in combination with actual application scenarios.

[0088] The first pitch angle can be the pitch angle of the position relative to the sensor coordinate system or the carrier coordinate system; for example, the first pitch angle can be the angle between the line connecting the position and the origin of the sensor coordinate system or the carrier coordinate system and the first plane, and the first plane can refer to the XOY plane of the sensor coordinate system or the carrier coordinate system, which can coincide with the ground plane where the first device is located, or can be a plane parallel to the ground plane where the first device is located, etc., which can be understood in combination with actual application scenarios.

[0089] 202. Determine a first parameter value for indicating the occupancy of the object at the first position according to the first distance.

[0090] For example, the first position can be a position within the field of view of the sensor.

[0091] Exemplarily, in an implementation, the first parameter value is based on the first distance and third quality information in the measurement data, and the third quality information is used to reflect the quality of the distance in the measurement data, or the third quality information can also be understood as being used to reflect the error of the distance in the measurement data. Then, the step 202 can include: determining, by the first device, the first parameter value used to indicate the object occupancy of the first position according to the first distance, the second distance and the third quality information.

[0092] The second distance is the distance between the first position and the origin of the coordinate system; for example, if the aforementioned coordinate system is the sensor coordinate system, the second distance can be the distance between the first position and the origin of the sensor coordinate system; if the aforementioned coordinate system is the carrier coordinate system, the second distance can be the distance between the first position and the origin of the carrier coordinate system, and the meaning of the carrier coordinate system can be referred to the description above, which will not be repeated here. Since the first parameter value is based on the distance included in the measurement data, the first parameter value can also be understood as the object occupancy of the first position based on the first distance; exemplarily, the first parameter value can be understood as the probability of the first position being occupied by the object, and the first parameter value can be the first occupancy probability of the first position, and further, the first occupancy probability can be understood as the probability of the first position being occupied by the object based on the first distance.

[0093] Exemplarily, the third quality information indicates the standard deviation and / or variance and / or root mean square error and / or mean square error of the distance measurement error; it should be noted that the "distance measurement error" in the present application can also be referred to as "error of the distance dimension in the measurement data", and there can be two concepts of "error of the azimuth angle dimension in the measurement data" and "error of the pitch angle dimension in the measurement data" in the future, which will appear in the subsequent description, which will not be further explained here.

[0094] Further, the third quality information can include the standard deviation and / or variance and / or root mean square error and / or mean square error reflecting the distance measurement error, or the third quality information can include the inverse of the standard deviation and / or variance and / or root mean square error and / or mean square error reflecting the distance measurement error, or the third quality information can include the inverse of the standard deviation and / or variance and / or root mean square error and / or mean square error reflecting the distance measurement error, or the third quality information can also include other information capable of calculating the standard deviation and / or variance and / or root mean square error and / or mean square error reflecting the distance measurement error, and the like, which will not be enumerated in the present application. It should be noted that the "distance measurement" in the present application not only includes the case of directly obtaining the distance through the information collected by the sensor, but also includes the case of indirectly obtaining the distance through processing the information collected by the sensor.

[0095] The standard deviation, variance, root mean square error and mean square error can reflect the quality or measurement accuracy or error of the measurement data obtained by the sensor. Generally, the standard deviation, variance, root mean square error and mean square error can reflect the dispersion degree of the sensor in measuring the distance of the same position multiple times, wherein multiple distance values can be obtained by the sensor in measuring the distance of the same position multiple times, and the greater the dispersion degree between the aforementioned multiple distance values, the greater the measurement distance error; the smaller the dispersion degree between the aforementioned multiple distance values, the smaller the measurement distance error.

[0096] Further, in the case that the sensor is an ultrasonic sensor, a laser radar sensor, a millimeter wave radar sensor or other sensors capable of measuring point cloud data, etc., the third quality information can include one quality information, and the aforementioned one quality information can include a standard deviation and / or variance for reflecting the distance measurement error; optionally, a root mean square error and / or a mean square error; it should be noted that the information collected by the sensor directly or indirectly obtained distance can be understood as measuring distance by the sensor, that is, the "distance measurement" in the present application includes the case of directly obtaining distance by using the information collected by the sensor, and also includes the case of indirectly obtaining distance by using the information collected by the sensor.

[0097] In the case that the sensor is a camera, since the measurement distance error of the camera becomes larger as the distance between the photographed object and the camera increases, the third quality information can include one quality information; or the third quality information can further include at least two quality information corresponding to at least two distance ranges, and each of the at least two quality information can include a standard deviation and / or variance for reflecting the distance error of the camera; optionally, a root mean square error and / or a mean square error. Then the first device can determine a target distance range containing the first distance from the at least two distance ranges, and then obtain one quality information corresponding to the target distance range from the at least two quality information, that is, one quality information corresponding to the first distance is obtained; and then determine the first parameter value according to the first distance, the second distance and the quality information corresponding to the first distance.

[0098] For further understanding of the present solution, exemplarily, the at least two distance ranges include a distance range 1, a distance range 2 and a distance range 3, the distance range 1 can be greater than or equal to 0 meters and less than 10 meters, the distance range 2 is greater than or equal to 10 meters and less than 30 meters, and the distance range 3 is greater than or equal to 30 meters. The distance range 1 corresponds to quality information 1, the quality information 1 includes a standard deviation 1 and a variance 1 reflecting the distance measurement error of the camera; the distance range 2 corresponds to quality information 2, the quality information 2 includes a standard deviation 2 and a variance 2 reflecting the distance measurement error of the camera; and the distance range 3 corresponds to quality information 3, the quality information 3 includes a standard deviation 3 and a variance 3 reflecting the distance measurement error of the camera. The first distance is 15 meters, since 15 meters is included in the distance range 2, the first device can obtain the standard deviation 2 and the variance 2 included in the quality information 2, and then determine the first parameter value according to the first distance, the second distance, the standard deviation 2 and the variance 2. It should be understood that the example here is only for the convenience of understanding the present solution, and is not used to limit the present solution.

[0099] Further, in one case, the third quality information can be pre-stored in the first device, for example, the third quality information can be stored in the first device in the process of deploying the sensor to the first device; optionally, the first device can also update the aforementioned third quality information once every period of time. In another case, the first device can obtain the third quality information through measurement before using the sensor, and the third quality information can also be obtained through other ways, which are not exhaustively listed in the embodiments of the present application.

[0100] Optionally, in one implementation, the first device can also obtain a first threshold value and a second threshold value, the purpose of setting the first threshold value includes avoiding the value of the first parameter value being equal to 0, and the purpose of setting the second threshold value includes avoiding the value of the first parameter value being equal to 1; the first parameter value can be determined based on the third function according to the first distance, the third quality information, the first threshold value and the second threshold value in the aforementioned measurement data. Exemplarily, the first device can determine the first parameter value for indicating the object occupancy of the first position according to the first distance, the second distance and the third quality information, which can include: the first device brings the first distance, the second distance, the third quality information, the first threshold value and the second threshold value into the third function to obtain the first parameter value.

[0101] The third function can include a first function term corresponding to the first threshold value and the second threshold value, and a second function term corresponding to the first distance and the third quality information (or the quality information corresponding to the first distance), the second function term can be a monotonically increasing function, and the value range of the second function term can be from 0 to 1.

[0102] In another implementation, the first device can store a first mapping relationship, and each of a plurality of sub-mapping relationships included in the first mapping relationship is a mapping relationship between a combination of a distance in the measurement data, a distance between a position in a field of view (FOV) range of the sensor and the sensor, and a standard deviation and / or variance reflecting a distance measurement error, and a first parameter value. For example, the first mapping relationship can be in a table, an array, or other data format. Illustratively, the first mapping relationship can be obtained based on experimental data statistics, can be obtained by a technician based on experience, or can be obtained by another device based on a third function, etc., which is not limited here. Then, based on the first distance, the second distance, and the third quality information in the measurement data, the first device can obtain a first parameter value corresponding to the combination of the first distance, the second distance, and the standard deviation and / or variance based on the third quality information from the first mapping relationship.

[0103] Optionally, a relationship between the second distance and the first parameter value obtained based on the first distance and the third quality information in the measurement data can be as shown in the following formula:

[0104] wherein p r (r) is a first occupancy probability of the first position, r is the second distance; lb and ub are two preset threshold values, lb is a lower limit of p r (r), which can be a first threshold value set to avoid p r (r) taking a value equal to or less than 0, and ub is an upper limit of p r (r), which can be a second threshold value set to avoid p r (r) taking a value equal to or greater than 1, for example, a value of lb can be 0.1, 0.15, 0.2, or other values, etc., for example, a value of ub can be 0.8, 0.85, 0.9, or other values, etc., which can be set in combination with actual application scenarios; σ r included in the third quality information can be a standard deviation or a root mean square error used to reflect a measurement error of the sensor in the distance dimension. f r = erf(·), that is, f r can be an error function, or f r = 2·sigmoid(·)-1, that is, f r can be obtained based on an activation function, wherein sigmoid(·) is an activation function.

[0105] In one case, L r is a preset parameter value, for example, L rL r is a function term constructed based on the standard deviation of the sensor in the distance dimension, for example, L r = σ r , or and the like, which can be set in combination with actual application scenarios.

[0106] r m is the first distance included in the measurement data, σ 2 is the variance or mean square error for reflecting the error of the distance in the measurement data, which can also be referred to as the variance or mean square error indicating the error of the measurement data; ln represents taking the natural logarithm. It should be understood that the examples in the above formula (1) and formula (2) are only one example proving the feasibility of the present application, and are not used to limit the present solution.

[0107] For a more intuitive understanding of the present solution, refer to FIG. 3 and FIG. 4, FIG. 3 is a schematic diagram of a second function term provided by an embodiment of the present application, and FIG. 4 is a schematic diagram of several first occupancy probabilities provided by an embodiment of the present application. First refer to FIG. 3, the second function term shown in FIG. 3 is a monotonically increasing function, and the value range of the second function term is from 0 to 1. It should be understood that the example in FIG. 3 is only for facilitating the understanding of the present solution, and is not used to limit the present solution.

[0108] Continue to refer to FIG. 4, the horizontal axis of FIG. 4 is the normalized value of the second distance (normalized by the standard deviation or mean square error reflecting the distance measurement error), and the second distance is the distance between a certain position and the sensor. The vertical axis of FIG. 4 represents the first occupancy probability of the position being occupied by an object. The three lines shown in FIG. 4 are all examples in which the relationship between the second distance and the first occupancy probability (which is an example of the first parameter value) satisfies the relationship in the above formula (1). The difference between the three lines is that they respectively correspond to different values of L r . The values of L r corresponded to the three lines from top to bottom are σ r , and As shown in FIG. 4, the position corresponding to the value 50 on the horizontal axis has the highest probability of being occupied by an object, and the probability of the position closer to the distance sensor being occupied by an object gradually decreases compared with the position corresponding to the value 50 on the horizontal axis, and finally approaches 0.1; and the probability of the position farther away from the distance sensor being occupied by an object gradually decreases compared with the position corresponding to the value 50 on the horizontal axis, and finally approaches 0.5. Since if there is an object (for convenience, referred to as a "target object" in the following) at the position corresponding to the value 50 on the horizontal axis, the object behind the target object will be blocked, therefore, the probability of the position farther away from the distance sensor being occupied by an object will gradually approach 0.5 (i.e. uncertain); since the sensor has detected the target object, it means that there is no other object blocking the position closer to the distance sensor, therefore, the probability of the position farther away from the distance sensor being occupied by an object will gradually approach 0.1 (i.e. no object). It should be understood that the example in FIG. 4 is only for the convenience of understanding the present scheme, and is not used to limit the present scheme.

[0109] In another implementation manner, the first device can also input the first distance, the second distance, and the standard deviation and / or variance of the sensor in the dimension of measuring distance into the second machine learning model, to obtain the first parameter value output by the second machine learning model.

[0110] For example, the second machine learning model can be a convolutional neural network, a support vector machine, a multilayer perceptron (MLP), a neural network based on an attention mechanism, or other types of machine learning models, etc., and the specific type can be determined in combination with the actual application scenario.

[0111] In the embodiments of the present application, the first distance and the third quality information in the measurement data are used to determine the object occupation in the dimension of distance (i.e. the first parameter value) at a certain position, and the third quality information can accurately reflect the error of the distance in the measurement data obtained by the sensor, so that the first parameter value obtained can fully consider the influence of the error of the sensor when measuring the distance, which is not only beneficial to obtain more accurate first parameter value, and further beneficial to obtain more accurate object occupation; and also beneficial to make the present scheme self-adaptive to different specifications in the dimension of error when measuring the distance, i.e. beneficial to make the present scheme applicable to more sensors, and beneficial to expand the application range of the present scheme.

[0112] In another implementation, the first device can store a second mapping relationship, the second mapping relationship including a plurality of sub-mapping relationships, each of the plurality of sub-mapping relationships being a mapping relationship between a combination of a distance of the measurement data and a distance between a location in the field of view of the sensor and the sensor and a first parameter value. The data format and source of the second mapping relationship can be referred to the description of the first mapping relationship, which will not be repeated here. After the first distance in the measurement data and the second distance between the first location and the sensor are determined, the first device can obtain the first parameter value corresponding to the combination of the first distance and the second distance from the second mapping relationship.

[0113] Alternatively, the first device can input the first distance and the second distance into a third machine learning model to obtain the first parameter value output by the third machine learning model. The specific form of the third machine learning model can be referred to the description of the second machine learning model, which will not be repeated here.

[0114] 203. Determine, according to the first angle, an angle adjustment factor corresponding to the first location.

[0115] The first angle includes a first azimuth angle and / or a first pitch angle. For example, the first azimuth angle is used to determine the first angle adjustment factor, and the second azimuth angle is used to determine the second angle adjustment factor. The first angle adjustment factor and / or the second angle adjustment factor are used to determine the angle adjustment factor, which is used to adjust the first parameter value to obtain a second parameter value corresponding to the first location. The second parameter value indicates the object occupancy of the first location determined based on the measurement data. The angle adjustment factor indicates the influence of the angle dimension on the object occupancy of the first location. The angle adjustment factor can also be referred to as an angle weight factor or other names.

[0116] Exemplarily, in one case, if the first angle only includes the first direction angle, the angle adjustment factor corresponding to the first position is the first angle adjustment factor. In another case, if the first angle only includes the first pitch angle, the angle adjustment factor corresponding to the first position is the second angle adjustment factor. In another case, if the first angle includes the first direction angle and the first pitch angle, the angle adjustment factor corresponding to the first position can be the product of the first angle adjustment factor and the second angle adjustment factor, or the angle adjustment factor corresponding to the first position can be the average of the first angle adjustment factor and the second angle adjustment factor, or the angle adjustment factor corresponding to the first position can be the minimum or maximum value between the first angle adjustment factor and the second angle adjustment factor.

[0117] Exemplarily, for the specific implementation manner that the first device determines the first angle adjustment factor according to the first azimuth angle, the first device can determine the first angle adjustment factor corresponding to the first position according to the first azimuth angle and a second azimuth angle, where the second azimuth angle is the azimuth angle of the first position relative to the sensor coordinate system or the carrier coordinate system; optionally, the second azimuth angle can be the azimuth angle of the first position relative to the sensor coordinate system, or the second azimuth angle can also be the azimuth angle of the first position relative to the carrier coordinate system. Optionally, the smaller the absolute value of the difference between the second azimuth angle and the first azimuth angle, the larger the value of the first angle adjustment factor can be; the larger the absolute value of the difference between the second azimuth angle and the first azimuth angle, the smaller the value of the first angle adjustment factor can be.

[0118] Optionally, the first angle adjustment factor is determined based on the first azimuth angle and first quality information, and the first quality information is used to reflect the quality of the azimuth angle in the measurement data, or it can also be understood that the first quality information is used to reflect the error of the azimuth angle in the measurement data. The first device determines the first angle adjustment factor corresponding to the first position according to the first azimuth angle can include that the first device determines the first angle adjustment factor according to the first azimuth angle, the second azimuth angle and the first quality information.

[0119] Exemplarily, the first quality information indicates the standard deviation and / or variance and / or root mean square error and / or mean square error of the azimuth angle measurement error, and it needs to be explained that the "azimuth angle measurement error" in the present application can also be replaced by "error of the azimuth angle dimension in the measurement data".

[0120] Further, the first quality information comprises a standard deviation and / or a variance and / or a root mean square error and / or a mean square error reflecting the azimuth measurement error, or the first quality information comprises an inverse of a standard deviation and / or a variance and / or a root mean square error and / or a mean square error reflecting the azimuth measurement error, or the first quality information comprises an inverse of a standard deviation and / or a variance and / or a root mean square error and / or a mean square error reflecting the azimuth measurement error, or the first quality information can also comprise other information capable of calculating a standard deviation and / or a variance and / or a root mean square error and / or a mean square error reflecting the azimuth measurement error, etc., which are not exhaustively listed in the present application. It should be noted that the "azimuth measurement" in the present application not only includes the case of directly obtaining the azimuth angle through the information collected by the sensor, but also includes the case of indirectly obtaining the azimuth angle through processing the information collected by the sensor.

[0121] Generally, the standard deviation and / or the variance and / or the root mean square error and / or the mean square error reflecting the azimuth measurement error can reflect the dispersion degree of the azimuth angle of the sensor when measuring the same position multiple times. The sensor can obtain multiple azimuth angles when measuring the same position multiple times. The greater the dispersion degree of the multiple azimuth angles, the greater the azimuth measurement error. The smaller the dispersion degree of the multiple azimuth angles, the smaller the azimuth measurement error.

[0122] Further, in one case, the first quality information can be pre-stored in the first device, for example, the first quality information can be stored in the first device during the process of deploying the sensor to the first device. Alternatively, the first device can also update the first quality information every certain period of time. In another case, the first device can obtain the first quality information through measurement before using the sensor, and the first quality information can also be obtained through other ways. Alternatively, the first quality information can be estimated in real time and provided one by one with the measurement data, which are not exhaustively listed in the embodiments of the present application.

[0123] Specifically, in one implementation, the first angle adjustment factor is determined based on a first function according to the first azimuth angle, the second azimuth angle and the first quality information; wherein the first function is a Gaussian function, or the first function is obtained based on an error (erf) function, or the first function is obtained based on a certain activation function (such as a sigmoid function); for example, the first function can be an axisymmetric function. Exemplarily, the first device can take the first azimuth angle and the standard deviation and / or the variance and / or the root mean square error and / or the mean square error reflecting the azimuth measurement error as parameters of the first function, so as to obtain the first angle adjustment factor corresponding to the second azimuth angle based on the first function.

[0124] In another implementation, the first device can store a third mapping relationship, and each of a plurality of sub-mapping relationships included in the third mapping relationship is a mapping relationship between a first azimuth angle in the measurement data, a second azimuth angle of a position in a field of view of the sensor relative to a coordinate system, and a combination of a standard deviation and / or a variance or a root mean square error or a mean square error reflecting an azimuth angle measurement error, and a first angle adjustment factor. The coordinate system can be a sensor coordinate system or a carrier coordinate system. The data format and source of the third mapping relationship can refer to the description of the first mapping relationship, and will not be described here. Based on the first azimuth angle in the measurement data, the second azimuth angle of the first position relative to the coordinate system, and the standard deviation and / or the variance and / or the root mean square error and / or the mean square error contained in the first quality information, the first device can obtain a first angle adjustment factor corresponding to the combination of the first azimuth angle, the second azimuth angle, and the standard deviation and / or the variance based on the first quality information from the third mapping relationship.

[0125] Optionally, based on the first azimuth angle in the measurement data, the relationship between the second azimuth angle and the first angle adjustment factor can be as follows:

[0126] wherein F θ (θ) is the first angle adjustment factor; f θ is an error function, that is, f θ = erf(·), or f θ is obtained based on a certain activation function, that is, f θ = 2·sigmoid(·)-1; the domain of sigmoid(·) is a real number, and sigmoid(·) is a certain activation function whose function value monotonically increases from 0 to 1, θ is the second azimuth angle corresponding to the first position; θ m is the first azimuth angle in the measurement data, and σ θ is the standard deviation of the azimuth angle measurement error of the sensor.

[0127] In one case, L θ is a preset parameter value, for example, the value of L θ may be 0.6, 0.1, or other values, etc. In another case, L θ is a function term constructed based on the standard deviation of the azimuth angle measurement error of the sensor, for example, or L θ = σ θ , or or L θ = 2σ θ , or L θ = 3σ θIt should be understood that the examples in formula (3) are only for facilitating the understanding of the present solution and are not used to limit the present solution.

[0128] For a more intuitive understanding of the present solution, please refer to FIG. 5, which is a schematic diagram of the first function according to an embodiment of the present application. FIG. 5 shows four examples of the first function, in which the first function is a single-peak function with axial symmetry. The four examples include an example in which the first function is a Gaussian function and three examples in which the first function is based on an activation function. The three examples in which the first function is based on an activation function are all based on the formula shown in formula (3) above. The difference between the three examples is the value of L θ . θ The values of L σ θ in the three examples are respectively. It should be understood that the examples in FIG. 5 are only for facilitating the understanding of the present solution and are not used to limit the present solution.

[0129] Alternatively, the first device can also store a fourth mapping relationship. The fourth mapping relationship includes a plurality of sub-mapping relationships, each of which is a mapping relationship between a combination of a pitch angle in the measurement data and a pitch angle in the position within the sensor field of view and a first angle adjustment factor. The data format and source used by the fourth mapping relationship can be referred to the description of the first mapping relationship above, which will not be repeated here. The first device can obtain the first angle adjustment factor corresponding to the combination of the first pitch angle and the second pitch angle from the fourth mapping relationship.

[0130] Alternatively, the first device can input the first pitch angle and the second pitch angle into a fourth machine learning model to obtain the first angle adjustment factor output by the fourth machine learning model. The specific form of the fourth machine learning model can be referred to the description of the second machine learning model above, which will not be repeated here. The first device determines the second angle adjustment factor corresponding to the first position according to the first pitch angle can include that the first device determines the second angle adjustment factor according to the first pitch angle, the second pitch angle and the first quality information.

[0131] According to the specific implementation manner of the first device determining the second angle adjustment factor according to the first pitch angle, the first device can determine the second angle adjustment factor corresponding to the first position according to the first pitch angle and a second pitch angle, where the second pitch angle is a pitch angle of the first position relative to the sensor coordinate system or the carrier coordinate system. For example, the second pitch angle can be an angle between a line connecting the first position and an origin of the sensor coordinate system or the carrier coordinate system and the first plane. The meaning of the first plane can be referred to the description above, and will not be described here. Optionally, the smaller the absolute value of the difference between the second pitch angle and the first pitch angle, the larger the value of the second angle adjustment factor can be; and the larger the absolute value of the difference between the second pitch angle and the first pitch angle, the smaller the value of the second angle adjustment factor can be.

[0132] Optionally, the second angle adjustment factor is determined based on the first pitch angle and second quality information, where the second quality information is used to reflect the quality of the pitch angle in the measurement data obtained by the sensor, and the second quality information can also be referred to as being used to reflect the error of the pitch angle in the measurement data obtained by the sensor.

[0133] For example, the second quality information indicates a standard deviation and / or a variance and / or a root mean square error and / or a mean square error of the pitch angle measurement error. It should be noted that the pitch angle measurement error in the present application can also be referred to as an error of the pitch angle in the measurement data.

[0134] Further, the second quality information includes a standard deviation and / or a variance and / or a root mean square error and / or a mean square error of the pitch angle measurement error, or the second quality information includes an inverse of a standard deviation and / or a variance and / or a root mean square error and / or a mean square error of the pitch angle measurement error, or the second quality information includes an inverse of a standard deviation and / or a variance and / or a root mean square error and / or a mean square error of the pitch angle measurement error, or the second quality information can also include other information capable of calculating a standard deviation and / or a variance and / or a root mean square error and / or a mean square error of the pitch angle measurement error, and the present application does not make an exhaustive list. It should be noted that the pitch angle measurement in the present application not only includes a case where the pitch angle is directly obtained through the information collected by the sensor, but also includes a case where the pitch angle is indirectly obtained through processing of the information collected by the sensor.

[0135] Optionally, the second angle adjustment factor is determined according to the first pitch angle, the second pitch angle and the second quality information based on a second function, wherein the second function is a Gaussian function, or the second function is based on an error function, or the second function is based on an activation function, the second function can be an axisymmetric function, the shape of the second function is similar to the shape of the first function shown in FIG. 5, and reference can be made for understanding. Exemplarily, the first device can take the first pitch angle and the standard deviation and / or variance and / or root mean square error and / or mean square error reflecting the pitch angle measurement error as parameters of the second function to obtain the second angle adjustment factor corresponding to the first pitch angle.

[0136] It should be noted that the specific implementation of the first device determining the second angle adjustment factor according to the first pitch angle can refer to the description of the specific implementation of the first device determining the first angle adjustment factor according to the first pitch angle, and the difference is that the pitch angle in the above description is replaced by the pitch angle, the first angle adjustment factor in the above description is replaced by the second angle adjustment factor, and the first function in the above description is replaced by the second function, which will not be described here.

[0137] Optionally, the relationship between the first pitch angle and the second angle adjustment factor can be as shown in the following formula:

[0138] wherein, the second angle adjustment factor is the second pitch angle is the error function is or, based on a certain activation function, exemplarily, the second pitch angle corresponding to the first position is the first pitch angle in the measurement data is the standard deviation or the root mean square error reflecting the pitch angle measurement error is

[0139] In one case, is a preset parameter value, for example, The value of can be 0.9, 0.6, 0.1 or other values, etc. In another case, is a function term constructed based on the standard deviation reflecting the pitch angle measurement error, for example, or, or, or, or, etc., it should be understood that the examples in formula (4) are only for the convenience of understanding the scheme and do not limit the scheme.

[0140] In the embodiments of the present application, the first angle adjustment factor in the azimuth dimension is determined based on the first azimuth in the measurement data and the first quality information reflecting the error of the azimuth in the measurement data obtained by the sensor, so that the first angle adjustment factor obtained can fully consider the influence of the error when the azimuth is measured by the sensor, which is not only conducive to obtaining more accurate angle adjustment factor, and thus conducive to obtaining more accurate object occupancy; but also conducive to making the present scheme adaptive to different specifications in the error dimension when the azimuth is measured, that is, conducive to making the present scheme applicable to more sensors, and conducive to expanding the applicable range of the present scheme.

[0141] The first angle adjustment factor in the pitch dimension is determined based on the first pitch in the measurement data and the second quality information reflecting the error of the pitch in the measurement data obtained by the sensor, so that the second angle adjustment factor obtained can fully consider the influence of the error when the pitch is measured by the sensor, which is not only conducive to obtaining more accurate angle adjustment factor, and thus conducive to obtaining more accurate object occupancy; but also conducive to making the present scheme adaptive to different specifications in the error dimension when the pitch is measured, that is, conducive to making the present scheme applicable to more sensors, and conducive to expanding the applicable range of the present scheme.

[0142] In addition, it is further disclosed that the first angle adjustment factor and the second angle adjustment factor are determined based on functions, which improves the realizability of the present scheme, and the first function (or the second function) is a Gaussian function, or is obtained based on an error function, or is obtained based on a certain activation function, which provides a simple and effective implementation scheme.

[0143] It should be noted that the execution order between step 202 and step 203 in the embodiments of the present application is not limited, and step 202 can be executed first, and then step 203 can be executed, or step 203 can be executed first, and then step 202 can be executed, or steps 202 and 203 can be executed simultaneously.

[0144] 204、According to the first parameter value and the angle adjustment factor, the second parameter value of the first position is determined.

[0145] Since the second parameter value is obtained based on the distance and the angle included in the measurement data, the second parameter value can also be understood as the object occupancy of the first position based on the first distance and the first angle.

[0146] Exemplarily, in one case, the second parameter value can represent a probability that the first position is occupied by the object, and the first parameter value can be a first occupation probability of the first position, the first occupation probability referring to a probability that the first position is occupied by the object determined based on the distance in the measurement data, and the second occupation probability referring to a probability that the first position is occupied by the object determined based on the distance and the angle in the measurement data. In another case, the second parameter value can be a parameter value obtained by transforming the second occupation probability, for example, the second parameter value can be a ratio equivalent form, represented as: odd = p r,a (r,a) / (1-p r,a (r,a)) where odd is the second parameter value, p r,a (r,a) is the second occupation probability; for another example, the second parameter value can be a logarithmic equivalent form, represented as: log-odd = ln[p r,a (r,a) / (1-p r,a (r,a))] where log-odd is the second parameter value, p r,a (r,a) is the second occupation probability, and the like, or a second parameter value obtained by transforming the second occupation probability in other manners, for example, can be 1-p r,a (r,a), i.e., a free probability, and correspondingly, there can be a corresponding ratio or logarithmic ratio form; or an equivalent form derived in other manners, which generally satisfies a one-to-one mapping relationship or a one-to-one mapping relationship within a specified range, and the specific transformation manner can be determined in combination with an actual application scenario.

[0147] Optionally, a free probability of the first position can also be obtained by calculating 1-p r,a (r,a), p r,a (r,a) being the second occupation probability.

[0148] Optionally, in one case, the second occupation probability satisfies the following relationship with the first occupation probability and the angle adjustment factor: p r,a (r,a) = c0 + (p r (r) - c1) · F(a); (5)

[0149] where p r,a (r,a) is the second occupation probability, p r (r) is the first occupation probability, F(a) is the angle adjustment factor, c0 is a first preset value, and c1 is a second preset value, and the values of c0 and c1 can be the same or different, and can be determined in combination with an actual application scenario.

[0150] Optionally, the values of c0 and c1 are both 0.5, that is, the values of the first preset value and the second preset value are both 0.5. It should be noted that the first preset value and the second preset value can also be other values, for example, c0 is 0.499 and c1 is 0.501, etc., which can be set according to actual application scenarios.

[0151] To more intuitively understand the scheme, please refer to FIG. 6, which is two schematic diagrams of the second parameter value obtained by using the method provided in the application, and FIG. 6 includes left and right two sub-schematic diagrams. The left sub-schematic diagram of FIG. 6 includes three axes: a distance corresponding to a certain position, an azimuth angle corresponding to the position, and a second occupancy probability of the position occupied by an object. The right sub-schematic diagram of FIG. 6 includes three axes: an x-axis coordinate corresponding to a certain position, a y-axis coordinate corresponding to the position, and a second occupancy probability of the position occupied by an object. That is, the left sub-schematic diagram and the right sub-schematic diagram of FIG. 6 are different forms of expression. As shown in FIG. 6, the second occupancy probability of the position corresponding to a distance of 50 and an azimuth angle of 0 is the highest, and the second occupancy probability of the positions near the foregoing position is also relatively high. Compared with the foregoing position, the second occupancy probability of the position closer and with an azimuth angle of 0 is very low. Since the position with a distance of 50 and an azimuth angle of 0 can be observed by the sensor, it is represented that the position closer and with an azimuth angle of 0 is probably free of an occlusion object, and therefore, the second occupancy probability calculated in FIG. 6 is as expected. The second occupancy probability of the remaining positions is 0.5, which represents that it is uncertain whether there is an object at the position, which is also as expected. In addition, it should be particularly pointed out that from the diagram, it can be seen that as the distance error standard deviation or the angle error standard deviation increases, the corresponding actual space area of the occupancy probability will also increase, thereby being able to adapt to different sensor error specifications and accurately reflect the uncertainty range of the occupancy probability. Therefore, the second occupancy probability obtained by using the method provided in the application can more accurately reflect the object occupancy situation in the sensor field of view. It should be understood that the example in FIG. 6 is only for the convenience of understanding the scheme and does not limit the scheme.

[0152] Exemplarily, in an implementation manner, step 204 can include that the first device obtains a product of a difference between the first parameter value and the first preset value (that is, c1) and the angle adjustment factor, and obtains a sum of the product and the second preset value (that is, c0) as the second parameter value.

[0153] In another implementation, the first device can store a fifth mapping relationship, and each of a plurality of sub-mapping relationships included in the fifth mapping relationship is a mapping relationship between a combination of an occupancy probability obtained based on a distance in the measurement data and an angle adjustment factor obtained based on an angle in the measurement data and a second parameter value. The second parameter value and the first occupancy probability and the angle adjustment factor in the third mapping relationship can satisfy the relationship shown in the above formula (5). Step 204 can include that after the first device determines one first occupancy probability and one specific angle adjustment factor, the first device can obtain, from the fifth mapping relationship, a second parameter value corresponding to a combination of the one first occupancy probability and the one specific angle adjustment factor.

[0154] To more intuitively understand the present scheme, the fifth mapping relationship is described in the form of a table as follows. Please refer to Table 1 as follows.

[0155] Table 1

[0156] As shown in Table 1, four rows of data are taken as an example for description, and each row of data represents a sub-mapping relationship in the fifth mapping relationship, so that after a specific first occupancy probability and a specific angle adjustment factor are obtained, a second parameter value can be obtained by table lookup. It should be noted that the example in Table 1 is only for the convenience of understanding the present scheme, and is not used to limit the present scheme.

[0157] In another implementation, the first device can obtain first rectangular coordinate data based on the measurement data, and obtain second rectangular coordinate data corresponding to the first position, wherein the first rectangular coordinate data and the second rectangular coordinate data are both coordinate data in a rectangular coordinate system, and the rectangular coordinate data includes an x-axis coordinate and a y-axis coordinate of a position relative to the rectangular coordinate system. Optionally, the rectangular coordinate data further includes a z-axis coordinate of a position relative to the rectangular coordinate system. The rectangular coordinate system can be a sensor coordinate system or a carrier coordinate system. The first device can store a sixth mapping relationship, and each of a plurality of sub-mapping relationships included in the sixth mapping relationship is a second parameter value corresponding to a combination of rectangular coordinate data obtained based on the measurement data and rectangular coordinate data of a position in a sensor field of view. Then, the first device can obtain, from the fifth mapping relationship, a second parameter value corresponding to a combination of the first rectangular coordinate data and the second rectangular coordinate data.

[0158] In the embodiments of the present application, the relationship between the second occupancy probability, the first occupancy probability and the angle adjustment factor is disclosed, which improves the realizability of the present scheme. As can be seen from the experimental data shown in FIG. 5, the second occupancy probability obtained by the method provided in the present application is as expected, that is, the closer the relative position between the first position and the sensor to the measurement data, the greater the object occupancy probability of the first position. Since the relationship between the distance in the measurement data and the free probability at the first position no longer needs to be modeled in the scheme provided in the present application, the implementation difficulty of the present scheme is greatly reduced.

[0159] In addition, the values of c0 and c1 are further disclosed, which further improves the realizability of the present scheme. The product of the difference between the first occupancy probability and 0.5 and the angle adjustment factor is added to 0.5 to obtain the final second occupancy probability. The final value of the second occupancy probability fluctuates around 0.5. The occupancy probability of the area outside the predetermined range of the position corresponding to the measurement data and close to the sensor is lower than 0.5 and tends to a minimum value as the distance difference and the angle difference decrease, which meets the expectation that the occupancy state tends to be free. In addition, the occupancy probability of the position outside the predetermined range of the position corresponding to the measurement data and far from the sensor tends to 0.5. Since the occupancy probability of a certain position being 0.5 indicates that it is completely uncertain whether the position is occupied by an object (the occupancy probability is 0.5 and the free probability is also 0.5), it meets the expectation of uncertainty. More importantly, the occupancy probability of the position corresponding to the measurement data is the highest, and the occupancy probability of the positions within the specified range near the position corresponding to the measurement data gradually decreases, which meets the expectation that the occupancy probability of the position corresponding to the measurement data is the highest. Since the occupancy probability of the positions within the specified range near the position corresponding to the measurement data is generated depending on the measurement error, it is also expected that the occupancy probability of the positions within the specified range near the position corresponding to the measurement data gradually decreases. The measurement data obtained based on the sensor can improve or reduce the probability that the position is occupied by an object. The design that the values of c0 and c1 are both 0.5 is more conducive to making the final second occupancy probability consistent with the aforementioned expectation, so as to obtain a more accurate second occupancy probability of a certain position through the formula, and to more accurately determine the object occupancy of the position.

[0160] Alternatively, the second occupancy probability can also be the product of the first occupancy probability and the angle adjustment factor. The relationship between the second occupancy probability, the first occupancy probability and the angle adjustment factor can be determined in combination with the actual application scenario.

[0161] In the embodiments of the present application, when each set of measurement data is obtained by the sensor, not only the distance but also the azimuth angle and / or the pitch angle are obtained, so that not only the first parameter value for indicating the object occupancy of the first position is determined according to the obtained distance, but also an angle adjustment factor is determined according to the aforementioned azimuth angle and / or the pitch angle, and then the second parameter value of the first position is finally determined according to the first parameter value and the aforementioned angle adjustment factor, and the second parameter value indicates the object occupancy of the first position. Since more information is used to determine the object occupancy of the first position, the accuracy of the finally obtained second parameter value is improved. Moreover, the first parameter value for indicating the object occupancy of the first position is determined based on the distance, and the angle adjustment factor is determined according to the azimuth angle and / or the pitch angle, that is, the influence of the distance and the angle on the object occupancy of the first position is determined respectively and independently, and the first parameter value is adjusted based on the angle adjustment factor to determine the final object occupancy of the first position, so that the precision of the process of determining the object occupancy of the first position is improved, and the accuracy of the finally obtained second parameter value is further improved.

[0162] Based on the embodiments corresponding to FIG. 3, optionally, in one application scenario, the first device obtains at least one measurement data by the sensor, and the at least one measurement data is used to obtain a map corresponding to the field of view range of the sensor, and each measurement data is used to obtain the second parameter value of one or more first positions in the map. In another application scenario, when the first device needs to determine the object occupancy at a specific first position, a plurality of measurement data are obtained by the sensor, and then the object occupancy at the specific first position is determined based on the aforementioned plurality of measurement data. Since the specific implementation manners in the aforementioned two application scenarios are different, the following will be described respectively.

[0163] I. The plurality of measurement data is used to obtain a map corresponding to the field of view range of the sensor

[0164] Exemplarily, referring to FIG. 7, which is another schematic diagram of the method for determining the occupancy of a position provided in the embodiments of the present application, as shown in FIG. 7, the method for determining the occupancy of a position provided in the present application can include:

[0165] 701. Obtain at least one measurement data obtained by the sensor, each measurement data includes a first distance and a first angle, the first angle includes a first azimuth angle and / or a first pitch angle, and the target measurement data is any one of the aforementioned at least one measurement data.

[0166] Exemplarily, in order to obtain a map corresponding to the field of view range of the sensor, the first device can obtain at least one measurement data by the sensor, and the specific implementation manner of the aforementioned step can refer to the description of step 201 in the embodiments corresponding to FIG. 2, which will not be described here.

[0167] The map is used to reflect the object occupancy of the environment within the sensor field of view, and the map can include a plurality of positions and the object occupancy of each position in the plurality of positions.

[0168] Optionally, the above-mentioned map can be embodied as a grid map (GM), and the positions in the map can be embodied as grid cells in the grid map. The grid map is a kind of grid representation of the surrounding environment. For example, the grid map can include a plurality of grids and a second parameter value of each grid. Optionally, the second parameter value of each grid can be understood as the probability of each grid being occupied by an object. For example, the environment within the sensor field of view can be gridded. If a certain grid is occupied by an object, the grid is filled with color. If a certain grid is not occupied by an object, the grid is not filled with color.

[0169] For example, different colors can be filled in the grid to represent different occupancy probabilities of the grid. For example, a red grid represents a high occupancy probability of the grid, and a blue grid represents a low occupancy probability of the grid. Alternatively, different shades of the same color can be used to represent different occupancy probabilities of the grid. For example, a grid filled with red represents that the grid is occupied. The deeper the red color, the higher the occupancy probability of the grid. The lighter the red color, the lower the occupancy probability of the grid. The specific implementation mode can be determined in combination with the actual application scenario.

[0170] For example, the grid map used to represent the environment within the sensor field of view can be a two-dimensional rectangular coordinate grid map. The two-dimensional grid map can include an x-axis and a y-axis. The plane formed by the x-axis and the y-axis can be parallel to the ground plane. The two-dimensional grid map can represent the environment within the sensor field of view from a top-down perspective. Alternatively, the grid map used to represent the environment within the sensor field of view can be a three-dimensional rectangular coordinate grid map. The three-dimensional grid map can include an x-axis, a y-axis, and a z-axis. The plane formed by the x-axis and the y-axis can be parallel to the ground plane. The z-axis can represent the height. The three-dimensional grid map can represent the surrounding environment from a three-dimensional perspective.

[0171] For example, the grid map used to represent the environment within the sensor field of view can be a two-dimensional polar coordinate (distance and azimuth angle representation) grid map or a three-dimensional spherical coordinate (distance, azimuth angle, and elevation angle representation) grid map. No further description is given.

[0172] It should be understood that the map can also not be a grid map, for example, instead of a regularly or irregularly discrete-valued position as described above, it can be a continuously-valued different position, and the specific type of map can be determined in combination with the actual application scenario.

[0173] 702、determining at least one first position corresponding to the target measurement data, wherein each first position is a position within the field of view of the sensor.

[0174] Exemplarily, after obtaining the target measurement data, the first device can determine at least one first position corresponding to the target measurement data. In one case, the field of view of the sensor is divided into a plurality of positions, the map includes the plurality of positions, and the at least one first position includes the plurality of positions, that is, the first device needs to determine the second occupancy probability of each position within the field of view of the sensor based on the target measurement data in the subsequent step.

[0175] In another case, each of the at least one first position satisfies a preset condition, and the preset condition includes at least one of the following: an absolute value of a difference between a second distance corresponding to the first position and a first distance is less than or equal to a distance threshold value, and / or an absolute value of a difference between a second azimuth angle corresponding to the first position and a first azimuth angle is less than or equal to a first angle value, and / or an absolute value of a difference between a second pitch angle corresponding to the first position and a first pitch angle is less than or equal to a second angle value. Wherein the second distance corresponding to the first position can be a distance between the first position and an origin of a sensor coordinate system or a carrier coordinate system, the second azimuth angle corresponding to the first position can be an azimuth angle of the first position relative to the sensor coordinate system or the carrier coordinate system, and the second pitch angle corresponding to the first position can be a pitch angle of the first position relative to the sensor coordinate system or the carrier coordinate system. It should be noted that the first distance, the second distance, the first azimuth angle, the second azimuth angle, the first pitch angle, and the second pitch angle are all relative to data in the same coordinate system.

[0176] For example, any one measurement data is called measurement data 1, and the map is specifically a grid map, the entire grid map includes 200 grids, and the at least one first position corresponding to the measurement data 1 can include grid 1, grid 2, grid 3, grid 4, and grid 5, the aforementioned grid 1, grid 2, grid 3, grid 4, and grid 5 are screened from the 200 grids by using the preset condition, then the measurement data 1 is used to determine the second parameter value of each grid in the grid 1, the grid 2, the grid 3, the grid 4, and the grid 5, it should be understood that the example here is only for the convenience of understanding the scheme, and is not used to limit the scheme.

[0177] Further, in one case, the distance threshold is determined based on a standard deviation reflecting a distance measurement error, the first angle value is determined based on a standard deviation reflecting an azimuth angle measurement error, and the second angle value is determined based on a standard deviation reflecting a pitch angle measurement error.

[0178] Exemplarily, the distance threshold can take a product between a standard deviation reflecting a distance measurement error and a first multiple, for example, the first multiple can be 1.5 times, 2 times, 2.5 times, 2.6 times, 2.8 times, 3 times, 4 times, or other values, etc., which can be determined in combination with actual application scenarios.

[0179] The first angle value can take a product between a standard deviation reflecting an azimuth angle measurement error and a second multiple, for example, the second multiple can be 2 times, 2.5 times, 2.6 times, 2.8 times, 3 times, 3.5 times, or other values, etc., which can be determined in combination with actual application scenarios. The second angle value can take a product between a standard deviation reflecting a pitch angle measurement error and a third multiple, the third multiple and the second multiple can be the same or different, for example, the third multiple can be 2 times, 2.5 times, 2.6 times, 2.8 times, 3 times, 3.5 times, or other values, etc., which can be determined in combination with actual application scenarios.

[0180] In another case, the distance threshold is determined based on a root mean square error reflecting a distance measurement error, the first angle value is determined based on a root mean square error reflecting an azimuth angle measurement error, and the second angle value is determined based on a root mean square error reflecting a pitch angle measurement error.

[0181] In another case, the distance threshold, the first angle value, and / or the second angle value can also be preset values, for example, the distance threshold can be 3 meters, 5 meters, 8 meters, 10 meters, or other values, etc.; the first angle value can be 15 degrees, 18 degrees, 20 degrees, 25 degrees, or other values, etc.; the second angle value can be 12 degrees, 15 degrees, 18 degrees, 20 degrees, or other values, etc., which can be determined in combination with actual application scenarios.

[0182] Exemplarily, step 702 can include: after determining the target measurement data, the first device can filter a plurality of positions included in the map according to the target measurement data and a preset condition, and each first position after filtering needs to satisfy the aforementioned preset condition.

[0183] 703. Determine a first parameter value for indicating an object occupancy of the first position according to a first distance in the target measurement data.

[0184] 704. Determine an angle adjustment factor corresponding to the first position according to a first angle in the target measurement data.

[0185] 705. determining a second parameter value of the first position according to the first parameter value and the angle adjustment factor.

[0186] In the embodiments of the present application, the first device can implement the specific implementation of steps 703 to 705 according to the description of steps 202 to 204 in the corresponding embodiments of FIG. 2, which will not be repeated here.

[0187] For example, the first device can repeatedly implement steps 703 to 705 to determine the second parameter value of each first position corresponding to the target measurement data by using the target measurement data.

[0188] The first device repeatedly implements steps 702 to 705 multiple times to determine the second parameter value of each first position corresponding to each measurement data, and further determines the object occupancy of each position in the above-mentioned map.

[0189] For example, if a position in the map corresponds to one second occupancy probability, the second occupancy probability can be determined as the final occupancy probability, and the occupancy probability represents the probability that the position is occupied by an object.

[0190] Alternatively, if a position in the map (for convenience of description, hereinafter referred to as "second position") corresponds to at least two second occupancy probabilities, the final occupancy probability of the second position can be determined according to the at least two second occupancy probabilities of the second position. Alternatively, the at least two second occupancy probabilities can be subjected to binary Bayesian filtering or weighted averaging to obtain the final occupancy probability of the second position; or weighted summation can be used instead of averaging, which is not limited here.

[0191] Alternatively, summing the log-odd corresponding to the at least two second occupancy probabilities of the second position can determine the log-odd value corresponding to the final occupancy probability of the second position.

[0192] Alternatively, if a position in the map (for convenience of description, hereinafter referred to as "third position") does not correspond to any second occupancy probability, the occupancy probability of the third position can be determined as 0.5 or the log-odd value corresponding to the occupancy probability of the third position can be determined as 0.

[0193] It should be noted that after determining the final occupancy probability or log-odd value of each position in the map, the final occupancy probability can also be deformed. The deformation method can refer to the description of step 204 in the corresponding embodiments of FIG. 2, which will not be repeated here.

[0194] In the above description, the map is obtained based on multiple pieces of measurement data collected by the sensor once. Alternatively, the first device can collect measurement data by the sensor multiple times, and continuously update the map by using the measurement data collected multiple times.

[0195] In the embodiments of the present application, a specific application scenario of the occupancy of the position obtained based on the measurement data is provided, and the combination degree between the present solution and the specific application scenario is improved.

[0196] Alternatively, the first device can further perform trajectory prediction on the object in the environment based on the latest obtained map; and / or, the first device can further determine the drivable area of the first device based on the latest obtained map; and / or, the first device can further determine the driving strategy of the first device based on the latest obtained map; and / or, the first device can further perform path planning on the first device based on the latest obtained map, and the like, and how to use the map can be determined in combination with the actual application scenario, which is not limited herein.

[0197] II. Multiple pieces of measurement data are used to obtain the occupancy of the object at a specific first position

[0198] Exemplarily, refer to FIG. 8, which is another schematic diagram of the method for determining the occupancy of the position provided in the embodiments of the present application, as shown in FIG. 8, the method for determining the occupancy of the position provided in the present application can include:

[0199] 801. Obtain at least one first measurement data corresponding to the first position, each first measurement data is obtained by the sensor, and each measurement data includes a first distance and a first angle, the first angle includes a first azimuth angle and / or a first pitch angle.

[0200] Exemplarily, after the first device determines the specific first position, the first device can obtain multiple pieces of measurement data by the sensor, and then determine at least one first measurement data corresponding to the specific first position from the multiple pieces of measurement data obtained by the sensor.

[0201] In one case, the at least one first measurement data corresponding to the specific first position can include all the measurement data obtained by the sensor, that is, the first device needs to determine a second parameter value of the first position according to each measurement data in all the measurement data obtained by the sensor in the subsequent steps.

[0202] In another case, a preset condition needs to be met between the first position and the first measurement data, the preset condition including at least one of: an absolute value of a difference between a second distance corresponding to the first position and the first distance is less than or equal to a distance threshold value, and / or an absolute value of a difference between a second azimuth angle corresponding to the first position and the first azimuth angle is less than or equal to a first angle value, and / or an absolute value of a difference between a second elevation angle corresponding to the first position and the first elevation angle is less than or equal to a second angle value. The second distance corresponding to the first position can be a distance between the first position and an origin of a sensor coordinate system or a carrier coordinate system, the second azimuth angle corresponding to the first position can be an azimuth angle of the first position relative to the sensor coordinate system or the carrier coordinate system, and the second elevation angle corresponding to the first position can be an elevation angle of the first position relative to the sensor coordinate system or the carrier coordinate system. It should be noted that the first distance, the second distance, the first azimuth angle, the second azimuth angle, the first elevation angle, and the second elevation angle are all relative to data in the same coordinate system.

[0203] After determining a specific first position, the first device can filter at least one first measurement data meeting the preset condition from all the measurement data obtained by the sensor, and then determine a second parameter value of the first position based on each of the at least one first measurement data corresponding to the specific first position in a subsequent step.

[0204] 802. Determine a first parameter value indicating an object occupancy of the first position according to the first distance in the first measurement data.

[0205] 803. Determine an angle adjustment factor corresponding to the first position according to the first angle in the first measurement data.

[0206] 804. Determine a second parameter value of the first position according to the first parameter value and the angle adjustment factor.

[0207] In the embodiments of the present application, the specific implementation of the first device performing steps 802 to 804 can refer to the description of steps 202 to 204 in the above-mentioned embodiments corresponding to FIG. 2, which will not be repeated here.

[0208] Exemplarily, after the first device repeatedly performs steps 802 to 804 at least once, a second occupancy probability of the first position can be determined according to each of the at least one first measurement data corresponding to the specific first position, that is, at least one second occupancy probability corresponding to the at least one first measurement data is obtained; and the first device determines a final occupancy probability of the first position according to the at least one second occupancy probability. Alternatively, if the first device obtains at least two second occupancy probabilities corresponding to the specific first position, the at least two second occupancy probabilities can be averaged to obtain the final occupancy probability of the specific first position; or, the averaging can be replaced by weighted summation, etc., which is not limited herein.

[0209] Since a specific measurement data is generated based on an object at a specific position in the surrounding environment, theoretically, it is meaningful to determine the object occupancy of the specific position based on the specific measurement data, and it is meaningless to determine the object occupancy of positions other than the specific position based on the specific measurement data. In the present application, a preset condition is set, so that in the present application, a specific measurement data is only used to determine the object occupancy of a first position that meets the preset condition with the measurement data. Compared with each measurement data being used to determine the object occupancy of each position, the present application greatly reduces meaningless calculations, thereby effectively reducing the computing power requirement of the present application, and is beneficial to improve the effective utilization rate of computer resources.

[0210] Further, the distance, azimuth angle and / or elevation angle in the measurement data are used for screening, which provides a simple and easy-to-operate screening method. In addition, considering that the distance, azimuth angle and / or elevation angle in the measurement data may have errors, so that there may be errors between the position of the object of the measurement data and the position pointed by the measurement data, the distance threshold value, the first angle value and / or the second angle value are set in the preset condition. Compared with setting the preset condition as “the distance corresponding to the first position is equal to the first distance, and / or, the azimuth angle corresponding to the first position is equal to the first azimuth angle, and / or, the elevation angle corresponding to the first position is equal to the first elevation angle”, the object occupancy of the position where the specific measurement data is generated can be determined while the computer resources are not wasted as much as possible.

[0211] In addition, the standard deviation or root mean square error reflecting the measurement distance error can indicate the error of the distance in the measurement data, the standard deviation or root mean square error reflecting the measurement azimuth angle error can indicate the error of the azimuth angle in the measurement data, the standard deviation or root mean square error reflecting the measurement elevation angle error can indicate the error of the elevation angle in the measurement data, the distance threshold value in the present application is determined based on the standard deviation or root mean square error reflecting the measurement distance error, the first angle value is determined based on the standard deviation or root mean square error reflecting the measurement azimuth angle error, and the second angle value is determined based on the standard deviation or root mean square error reflecting the measurement elevation angle error, thereby facilitating the compatibility of sensors with different error specifications and facilitating the expansion of the application scenarios of the present application.

[0212] On the basis of the embodiments corresponding to FIG. 1 to FIG. 8, in order to better implement the above-mentioned scheme of the embodiments of the present application, the following also provides a related device for implementing the above-mentioned scheme. Referring to FIG. 9, FIG. 9 is a structure schematic diagram of a position occupancy determination device provided by the embodiments of the present application, the position occupancy determination device 900 comprises: an acquisition module 901, configured to acquire measurement data, the measurement data comprising a first distance and an angle, the angle comprising a first azimuth angle and / or a first elevation angle; a determination module 902, configured to determine a first parameter value for indicating the object occupancy of the first position according to the first distance; the determination module 902 is further configured to determine an angle adjustment factor corresponding to the first position according to the angle; the determination module 902 is further configured to determine a second parameter value corresponding to the first position according to the first parameter value and the angle adjustment factor, the second parameter value indicating the object occupancy of the first position.

[0213] Optionally, the first angle adjustment factor is determined based on the first azimuth angle and first quality information, the first quality information being used to reflect the error of the first azimuth angle in the measurement data; and / or, the second angle adjustment factor is determined based on the first elevation angle and second quality information, the second quality information being used to reflect the error of the first elevation angle in the measurement data, wherein the first angle adjustment factor and / or the second angle adjustment factor are used to determine the angle adjustment factor.

[0214] Optionally, the first angle adjustment factor is determined based on a first function according to the first azimuth angle, a second azimuth angle and the first quality information, wherein the first function is a Gaussian function, or the first function is obtained based on an error erf function, or the first function is obtained based on an activation sigmoid function; and / or, the second angle adjustment factor is determined based on a second function according to the first elevation angle, a second elevation angle and the second quality information, wherein the second function is a Gaussian function, or the second function is obtained based on an error erf function, or the second function is obtained based on an activation sigmoid function.

[0215] Optionally, the first parameter value is a first occupancy probability, and the second parameter value is a second occupancy probability, and the second occupancy probability satisfies the following relationship with the first occupancy probability and an angle adjustment factor: p r,a (r, a) = c0+ (p r (r) - c 10 ) · F(a)

[0216] wherein p r,a (r, a) is the second occupancy probability, p r (r) is the first occupancy probability, F(a) is the angle adjustment factor, and values of c0and c 10 are preset values.

[0217] Optionally, c0and c 10 are both 0.5.

[0218] Optionally, the first position and the measurement data satisfy a preset condition, and the preset condition comprises at least one of the following: an absolute value of a difference between a distance corresponding to the first position and the first distance is less than or equal to a distance threshold value, and / or an absolute value of a difference between an azimuth angle corresponding to the first position and the first azimuth angle is less than or equal to a first angle value, and / or an absolute value of a difference between an elevation angle corresponding to the first position and the first elevation angle is less than or equal to a second angle value.

[0219] Optionally, the distance threshold value is determined based on a standard deviation or a root mean square error reflecting a distance measurement error, the first angle value is determined based on a standard deviation or a root mean square error reflecting an azimuth angle measurement error, and the second angle value is determined based on a standard deviation or a root mean square error reflecting an elevation angle measurement error.

[0220] Optionally, the first parameter value is obtained based on the first distance and third quality information, and the third quality information is used to reflect an error of the first distance in the measurement data.

[0221] Optionally, the at least one measurement data is obtained by a sensor, and the at least one measurement data is used to obtain a map corresponding to a field of view range of the sensor, and each measurement data is used to obtain the second parameter value of one or more first positions in the map.

[0222] It should be noted that the information interaction and execution process between the modules / units in the position occupancy determination apparatus 900 are based on the same concept as the various method embodiments corresponding to FIGS. 1 to 8 of the present application, and the specific content can be referred to the description in the foregoing method embodiments, which will not be described here again.

[0223] Next, a device provided by an embodiment of the present application is introduced. In the case where the device specifically represents an execution device, refer to FIG. 10, which is a structural schematic diagram of the device provided by an embodiment of the present application. Specifically, the device 1000 includes a receiver 1001, a transmitter 1002, a processor 1003, and a memory 1004 (wherein the number of processors 1003 in the device 1000 can be one or more, and one processor is taken as an example in FIG. 10). The processor 1003 can include an application processor 10031 and a communication processor 10032. In some embodiments of the present application, the receiver 1001, the transmitter 1002, the processor 1003, and the memory 1004 can be connected through a bus or other means.

[0224] The memory 1004 can include a read-only memory and a random access memory, and provide the processor 1003 with instructions and data. A part of the memory 1004 can also include a non-volatile random access memory (NVRAM). The memory 1004 stores processor and operation instructions, executable modules or data structures, or a subset thereof, or an expanded set thereof, wherein the operation instructions can include various operation instructions for implementing various operations.

[0225] The processor 1003 controls the operation of the device. In a specific application, various components of the device are coupled together through a bus system, which can include a data bus, a power supply bus, a control bus, and a status signal bus, etc. in addition to a data bus. However, for the sake of clarity, all kinds of buses are referred to as a bus system in the figure.

[0226] The method disclosed in the embodiments of the present application can be applied to the processor 1003 or implemented by the processor 1003. The processor 1003 can be an integrated circuit chip having a signal processing capability. In the implementation process, the steps of the method can be completed by the integrated logic electric circuit or the instruction in the form of software in the processor 1003. The processor 1003 can be a general processor, a digital signal processor (DSP), a microprocessor or a microcontroller. The processor 1003 can further include an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The processor 1003 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor can be a microprocessor or the processor can also be any conventional processor or the like. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor to execute, or executed by a combination of hardware and software modules in the code processor. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable read only memory, a register, or other mature storage medium in the art. The storage medium is located in the storage 1004, and the processor 1003 reads the information in the storage 1004 and combines the hardware to complete the steps of the method.

[0227] The receiver 1001 can be used to receive input digital or character information, and generate signal input related to the relevant settings and function control of the device. The transmitter 1002 can be used to output digital or character information through the first interface; the transmitter 1002 can also be used to send instructions to the disk group through the first interface to modify the data in the disk group; the transmitter 1002 can also include a display device such as a display screen.

[0228] In the embodiments of the present application, the processor 1003 is used to execute the method executed by the first device in the corresponding embodiments of FIGS. 1 to 8. It should be noted that the application processor 10031 in the processor 1003 executes the specific mode of each step, and the method embodiments corresponding to each method in FIGS. 1 to 8 of the present application are based on the same concept, and the technical effects brought by the method embodiments corresponding to each method in FIGS. 1 to 8 of the present application are the same. The specific content can be referred to the description of the method embodiments in the foregoing description of the present application, and will not be described here.

[0229] The embodiments of the present application also provide a vehicle. Referring to FIG. 11, FIG. 11 is a schematic diagram of a structure of a vehicle provided by the embodiments of the present application. The vehicle 100 is configured to operate in a fully or partially autonomous mode. For example, the vehicle 100 can control itself while in the autonomous mode, and can determine a current state of the vehicle and its surrounding environment, determine a possible behavior of at least one other vehicle in the surrounding environment, and determine a confidence level corresponding to a likelihood that the other vehicle will perform the possible behavior based on the determined information, and control the vehicle 100 based on the determined information. The vehicle 100 can also be configured to operate without human interaction while in the autonomous mode.

[0230] The vehicle 100 can include various subsystems, such as a propulsion system 102, a sensor system 104, a control system 106, one or more peripheral devices 108, a power source 110, a computer system 112, and a user interface 116. Alternatively, the vehicle 100 can include more or fewer subsystems, and each subsystem can include multiple components. Additionally, each subsystem and component of the vehicle 100 can be interconnected by wires or wirelessly.

[0231] The propulsion system 102 can include components that provide powered movement for the vehicle 100. In one embodiment, the propulsion system 102 can include an engine 118, an energy source 119, a transmission 120, and wheels / tires 121.

[0232] The engine 118 can be an internal combustion engine, an electric motor, an air compression engine, or other types of engine combinations, such as a hybrid engine that includes a gasoline engine and an electric motor, or a hybrid engine that includes an internal combustion engine and an air compression engine. The engine 118 converts the energy source 119 into mechanical energy. Examples of the energy source 119 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electrical power. The energy source 119 can also provide energy for other systems of the vehicle 100. The transmission 120 can transmit mechanical power from the engine 118 to the wheels 121. The transmission 120 can include a gearbox, a differential, and a drive shaft. In one embodiment, the transmission 120 can also include other devices, such as a clutch. The drive shaft can include one or more shafts that can be coupled to one or more wheels 121.

[0233] The sensor system 104 can include several sensors that sense information about the environment surrounding the vehicle 100. For example, the sensor system 104 can include a positioning system 122 (which can be a global positioning GPS system, a Beidou system, or other positioning system), an inertial measurement unit (IMU) 124, a radar 126, a laser rangefinder 128, and a camera 130. The sensor system 104 can also include sensors that monitor internal systems of the vehicle 100 (e.g., in-vehicle air quality monitors, fuel gauges, oil temperature gauges, etc.). Sensor data from one or more of these sensors can be used to detect objects and their respective characteristics (location, shape, direction, velocity, etc.). Such detection and identification is a critical function for the safe operation of the autonomous vehicle 100.

[0234] The positioning system 122 can be used to estimate the geographic location of the vehicle 100. The IMU 124 is used to perceive changes in the position and orientation of the vehicle 100 based on inertial acceleration. In one embodiment, the IMU 124 can be a combination of an accelerometer and a gyroscope. The radar 126 can utilize radio signals to perceive objects within the environment surrounding the vehicle 100, which can be manifested as a millimeter wave radar or a laser radar. In some embodiments, in addition to perceiving objects, the radar 126 can also be used to perceive the velocity and / or heading of the objects. The laser rangefinder 128 can utilize laser light to perceive objects in the environment in which the vehicle 100 is located. In some embodiments, the laser rangefinder 128 can include one or more laser sources, a laser scanner, and one or more detectors, among other system components. The camera 130 can be used to capture multiple images of the environment surrounding the vehicle 100. The camera 130 can be a still camera or a video camera.

[0235] The control system 106 controls the operation of the vehicle 100 and its components. The control system 106 can include various components, including a steering system 132, a throttle 134, a braking unit 136, a computer vision system 140, a line control system 142, and an obstacle avoidance system 144.

[0236] The steering system 132 is operable to adjust the heading of the vehicle 100. In one embodiment, the steering system 132 can be a steering wheel system. The throttle 134 is used to control the speed of the engine 118 and, in turn, the speed of the vehicle 100. The braking unit 136 is used to control the deceleration of the vehicle 100. The braking unit 136 can use friction to slow the wheels 121. In other embodiments, the braking unit 136 can convert the kinetic energy of the wheels 121 into electrical current. The braking unit 136 can also take other forms to slow the wheels 121 and, in turn, control the speed of the vehicle 100. The computer vision system 140 is operable to process and analyze images captured by the cameras 130 to identify objects and / or features in the environment surrounding the vehicle 100. The objects and / or features can include traffic signals, road boundaries, and obstacles. The computer vision system 140 can use object recognition algorithms, Structure from Motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, the computer vision system 140 can be used to map the environment, track objects, estimate the speed of objects, and the like. The route control system 142 is used to determine the route and speed of travel of the vehicle 100. In some embodiments, the route control system 142 can include a lateral planning module 1421 and a longitudinal planning module 1422 that are used to determine the route and speed of travel of the vehicle 100 in conjunction with data from the obstacle avoidance system 144, the GPS 122, and one or more predetermined maps, respectively. The obstacle avoidance system 144 is used to identify, evaluate, and avoid or otherwise navigate around obstacles in the environment of the vehicle 100, which can be actual obstacles and virtual moving obstacles that can collide with the vehicle 100. In one instance, the control system 106 can include additional components in addition to those shown and described, or some of the components shown can be reduced.

[0237] The vehicle 100 interacts with external sensors, other vehicles, other computer systems, or users through the peripherals 108. The peripherals 108 can include a wireless communication system 146, an on-board computer 148, a microphone 150, and / or a speaker 152. In some embodiments, the peripherals 108 provide a means for a user of the vehicle 100 to interact with the user interface 116. For example, the on-board computer 148 can provide information to a user of the vehicle 100. The user interface 116 can also operate the on-board computer 148 to receive input from the user. The on-board computer 148 can be operated through a touch screen. In other cases, the peripherals 108 can provide a means for the vehicle 100 to communicate with other devices located within the vehicle. For example, the microphone 150 can receive audio (e.g., voice commands or other audio input) from a user of the vehicle 100. Similarly, the speaker 152 can output audio to a user of the vehicle 100. The wireless communication system 146 can wirelessly communicate with one or more devices, either directly or via a communication network. For example, the wireless communication system 146 can use 3G cellular communication, such as CDMA, EVDO, GSM / GPRS, or 4G cellular communication, such as LTE. Or 5G cellular communication. The wireless communication system 146 can utilize wireless local area network (WLAN) communication. In some embodiments, the wireless communication system 146 can utilize an infrared link, Bluetooth, or ZigBee to communicate directly with devices. Other wireless protocols, such as various vehicle communication systems, for example, the wireless communication system 146 can include one or more dedicated short range communications (DSRC) devices, which can include public and / or private data communication between vehicles and / or roadside stations.

[0238] The power supply 110 can provide power to various components of the vehicle 100. In one embodiment, the power supply 110 can be a rechargeable lithium-ion or lead-acid battery. One or more battery packs of such a battery can be configured as the power supply to provide power to various components of the vehicle 100. In some embodiments, the power supply 110 and the energy source 119 can be implemented together, such as in some all-electric vehicles.

[0239] Some or all of the functionality of vehicle 100 is controlled by computer system 112. Computer system 112 can include at least one processor 113 that executes instructions 115 stored in a non-transitory computer readable medium such as memory 114. Computer system 112 can also be a plurality of computing devices that control individual components or subsystems of vehicle 100 in a distributed manner. Processor 113 can be any conventional processor such as a commercially available central processing unit (CPU). Alternatively, processor 113 can be a dedicated device such as an application specific integrated circuit (ASIC) or other hardware-based processor. Although FIG. 11 functionally illustrates the processor, memory, and other components of computer system 112 within the same block, it will be understood by those skilled in the art that the processor, or memory, can actually comprise a plurality of processors, or memories, that can or can not be stored within the same physical housing. For example, memory 114 can be a hard drive or other storage media located in a housing different from that of computer system 112. Accordingly, references to processor 113 or memory 114 will be understood to include references to a collection of processors or memories that can or can not operate in parallel. Rather than using a single processor to perform the steps described herein, some components such as the steering assembly and the deceleration assembly can each have their own processor that only performs calculations related to the functionality specific to that component.

[0240] In various aspects described herein, processor 113 can be located remotely from vehicle 100 and in wireless communication with vehicle 100. In other aspects, some of the processes described herein are performed on processor 113 disposed within vehicle 100 while others are performed by a remote processor 113, including taking the necessary steps to perform a single maneuver.

[0241] In some embodiments, the memory 114 can include instructions 115 (e.g., program logic) that can be executed by the processor 113 to perform various functions of the vehicle 100, including those described above. The memory 114 can also include additional instructions, including instructions to send data to, receive data from, interact with, and / or control one or more of the travel system 102, the sensor system 104, the control system 106, and the peripherals 108. In addition to the instructions 115, the memory 114 can also store data, such as road maps, route information, the vehicle's location, direction, speed, and other such vehicle data, and other information. Such information can be used by the vehicle 100 and the computer system 112 during operation of the vehicle 100 in autonomous, semi-autonomous, and / or manual modes. The user interface 116 is used to provide information to or receive information from a user of the vehicle 100. Optionally, the user interface 116 can include one or more input / output devices within the set of peripherals 108, such as the wireless communication system 146, the on-board computer 148, the microphone 150, and the speaker 152.

[0242] The computer system 112 can control the functions of the vehicle 100 based on inputs received from various subsystems (e.g., the travel system 102, the sensor system 104, and the control system 106), as well as from the user interface 116. For example, the computer system 112 can utilize inputs from the control system 106 in order to control the steering system 132 to avoid obstacles detected by the sensor system 104 and the obstacle avoidance system 144. In some embodiments, the computer system 112 can be operable to provide control over many aspects of the vehicle 100 and its subsystems.

[0243] Optionally, one or more of the above-described components can be installed separately from or associated with the vehicle 100. For example, the memory 114 can exist partially or entirely separately from the vehicle 100. The above-described components can be communicatively coupled together in a wired and / or wireless manner.

[0244] Optionally, the above-described components are just one example, and in actual applications, components in each of the above-described modules can be added or deleted according to actual needs, and FIG. 11 should not be understood as a limitation on the embodiments of the present application. A vehicle traveling on a road, such as the vehicle 100 above, can identify objects within its surrounding environment to determine an adjustment to a current speed. The objects can be other vehicles, traffic control devices, or other types of objects. In some examples, each identified object can be considered independently, and based on respective characteristics of the object, such as its current speed, acceleration, spacing from the vehicle, etc., can be used to determine a speed at which the vehicle is to adjust.

[0245] Optionally, the vehicle 100 or a computing device associated with the vehicle 100, such as the computer system 112, the computer vision system 140, the memory 114 of FIG. 11, can predict the behavior of the identified object based on the characteristics of the identified object and the state of the surrounding environment (e.g., traffic, rain, ice on the road, etc.). Optionally, each identified object is dependent on the behavior of the other identified objects, so all of the identified objects can also be considered together to predict the behavior of a single identified object. The vehicle 100 can adjust its speed based on the predicted behavior of the identified object. In other words, the vehicle 100 can determine what steady state the vehicle will need to adjust to (e.g., accelerate, decelerate, or stop) based on the predicted behavior of the object. Other factors can also be considered in determining the speed of the vehicle 100 during this process, such as the lateral position of the vehicle 100 in the road, the curvature of the road, the proximity of static and dynamic objects, etc. In addition to providing instructions to adjust the speed of the vehicle, the computing device can also provide instructions to modify the steering angle of the vehicle 100 to cause the vehicle 100 to follow a given trajectory and / or maintain a safe lateral and longitudinal distance from objects in the vicinity of the vehicle 100 (e.g., a car in the adjacent lane on the road).

[0246] In embodiments of the present application, the processor 113 in the vehicle 100 is configured to perform the method performed by the first device in the embodiments corresponding to FIGS. 1 to 8. It should be noted that the specific manners in which the processor 113 performs the various steps described above are based on the same concept as the various method embodiments corresponding to FIGS. 1 to 8 of the present application, and bring about the same technical effects as the various method embodiments corresponding to FIGS. 1 to 8 of the present application. For specific content, reference can be made to the descriptions of the method embodiments described above in the present application, and thus will not be described here again.

[0247] In embodiments of the present application, a computer readable storage medium is also provided, which stores a program, and when the program is run on a computer, causes the computer to perform the steps performed by the first device in the method described in the embodiments of FIGS. 1 to 8 described above.

[0248] In embodiments of the present application, a computer program product is also provided, which includes a program, and when the program is run on a computer, causes the computer to perform the steps performed by the first device in the method described in the embodiments of FIGS. 1 to 8 described above.

[0249] In embodiments of the present application, a circuit system is also provided, which includes processing circuitry configured to perform the steps performed by the first device in the method described in the embodiments of FIGS. 1 to 8 described above.

[0250] The first device or the determination apparatus of the occupancy of the location provided by the embodiments of the present application can be a chip, which includes a processing unit, for example, a processor, and a communication unit, for example, an input / output interface, a pin, or a circuit, etc. The processing unit can execute computer execution instructions stored in a storage unit, so that the chip executes the method described in the embodiments shown in FIG. 1 to FIG. 8. Alternatively, the storage unit is a storage unit in the chip, such as a register, a cache, etc., and the storage unit can also be a storage unit outside the chip in the wireless access device, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), etc.

[0251] The processor mentioned in any of the above can be a general central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the programs of the method of the first aspect.

[0252] In addition, it should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the embodiments. In addition, the connection relationship between the modules in the apparatus embodiments provided by the present application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines.

[0253] Those skilled in the art can clearly understand that the application can be implemented by means of software plus necessary universal hardware, and of course can also be implemented by means of dedicated hardware including special integrated circuit, special CLU, special memory, special component, etc. Generally, any function completed by computer program can be easily implemented by corresponding hardware, and the specific hardware structure for implementing the same function can also be various, such as analog circuit, digital circuit or special circuit, etc. However, for the application, the software program implementation is a better embodiment. Based on such understanding, the technical solution of the application or the part of the application which makes contribution to the prior art can be embodied in the form of software product, which is stored in readable storage medium, such as floppy disk, U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a plurality of instructions for making a computer device (which can be personal computer, server or network device, etc.) execute the method described in various embodiments of the application.

[0254] In the above embodiments, the implementation can be achieved by software, hardware, firmware or any combination thereof, entirely or partially. When implemented by software, the implementation can be in the form of computer program product entirely or partially.

[0255] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the flow or function described in the embodiments of the application is entirely or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be stored by the computer or a data storage device such as server, data center, etc. integrated with one or more available media. The available medium can be magnetic medium (such as floppy disk, hard disk, magnetic tape), optical medium (such as DVD) or semiconductor medium (such as solid state disk (SSD)) etc.

Claims

1. A method of determining occupancy of a location, characterized by, The method comprises: obtaining measurement data, the measurement data comprising a first distance and an angle, the angle comprising a first azimuth angle and / or a first elevation angle; determining, according to the first distance, a first parameter value for indicating an object occupancy of a first position; determining, according to the angle, an angle adjustment factor corresponding to the first position; determining, according to the first parameter value and the angle adjustment factor, a second parameter value corresponding to the first position, the second parameter value indicating the object occupancy of the first position.

2. The method of claim 1, wherein, The first angle adjustment factor is determined based on the first azimuth angle and first quality information, the first quality information being used to reflect an error of the first azimuth angle in the measurement data; and / or, The second angle adjustment factor is determined based on the first elevation angle and second quality information, the second quality information being used to reflect an error of the first elevation angle in the measurement data, wherein the first angle adjustment factor and / or the second angle adjustment factor are used to determine the angle adjustment factor.

3. The method of claim 2, wherein: The first angle adjustment factor is determined based on a first function according to the first azimuth angle, a second azimuth angle and the first quality information, wherein the first function is a Gaussian function, or the first function is based on an error erf function, or the first function is based on an activation sigmoid function; and / or The second angle adjustment factor is determined based on a second function according to the first elevation angle, a second elevation angle and the second quality information, wherein the second function is a Gaussian function, or the second function is based on an error erf function, or the second function is based on an activation sigmoid function.

4. The method according to any one of claims 1 to 3, characterized in that, The first parameter value is a first occupation probability, the second parameter value is a second occupation probability, and the second occupation probability and the first occupation probability and the angle adjustment factor satisfy the following relationship: p r,a (r, a) = c0+ (p r (r) - c1) · F(a) where p r,a (r,a) is the second occupancy probability, p r (r) is the first occupancy probability, F(a) is an angle adjustment factor, and the values of c0 and c1 are preset values.

5. The method of claim 4, wherein, c0 and c1 are both 0.

5.

6. The method according to any one of claims 1 to 3, characterized in that, The first position and the measurement data satisfy a preset condition, the preset condition comprising at least one of the following: an absolute value of a difference between a distance corresponding to the first position and the first distance is less than or equal to a distance threshold value, and / or an absolute value of a difference between an azimuth angle corresponding to the first position and the first azimuth angle is less than or equal to a first angle value, and / or an absolute value of a difference between an elevation angle corresponding to the first position and the first elevation angle is less than or equal to a second angle value.

7. The method of claim 6, wherein, The distance threshold value is determined based on a standard deviation or a root mean square error reflecting a distance measurement error, the first angle value is determined based on a standard deviation or a root mean square error reflecting an azimuth angle measurement error, and the second angle value is determined based on a standard deviation or a root mean square error reflecting an elevation angle measurement error.

8. The method according to any one of claims 1 to 3, characterized in that, The first parameter value is obtained based on the first distance and third quality information, the third quality information being used to reflect an error of the first distance in the measurement data.

9. The method according to any one of claims 1 to 3, characterized in that, At least one of the measurement data is obtained by a sensor, the at least one measurement data being used to obtain a map corresponding to a field of view range of the sensor, and each of the measurement data being used to obtain a second parameter value of one or more first positions in the map.

10. An arrangement for determining occupancy of a location, characterized by The device comprises: obtain measurement data, the measurement data comprising a first distance and an angle, the angle comprising a first azimuth angle and / or a first elevation angle; determine, according to the first distance, a first parameter value indicating an object occupancy of a first position; determine, according to the angle, an angle adjustment factor corresponding to the first position; determine, according to the first parameter value and the angle adjustment factor, a second parameter value corresponding to the first position, the second parameter value indicating the object occupancy of the first position.

11. The apparatus of claim 10, wherein, the first angle adjustment factor is determined based on the first azimuth angle and first quality information, the first quality information reflecting an error of the first azimuth angle in the measurement data; and / or, the second angle adjustment factor is determined based on the first elevation angle and second quality information, the second quality information reflecting an error of the first elevation angle in the measurement data, wherein the first angle adjustment factor and / or the second angle adjustment factor are used to determine the angle adjustment factor.

12. The apparatus of claim 11, wherein the first angle adjustment factor is determined based on a first function according to the first azimuth angle, a second azimuth angle and the first quality information, wherein the first function is a Gaussian function, or the first function is based on an error function erf, or the first function is based on an activation function sigmoid; and / or the second angle adjustment factor is determined based on a second function according to the first elevation angle, a second elevation angle and the second quality information, wherein the second function is a Gaussian function, or the second function is based on an error function erf, or the second function is based on an activation function sigmoid.

13. The apparatus of any one of claims 10 to 12, wherein, The first parameter value is a first occupation probability, the second parameter value is a second occupation probability, and the second occupation probability and the first occupation probability and the angle adjustment factor satisfy the following relationship: p r,a (r,a) = c0+ (p r (r) - c 10 ) · F(a) where p r,a (r,a) is the second occupancy probability, p r (r) is the first occupancy probability, F(a) is an angle adjustment factor, c0 and c 10 are preset values.

14. The apparatus of claim 13, wherein, c0and c 10 are both 0.

5.

15. The apparatus of any one of claims 10 to 12, wherein, a preset condition is satisfied between the first position and the measurement data, the preset condition comprising at least one of the following: an absolute value of a difference between a distance corresponding to the first position and the first distance is less than or equal to a distance threshold value, and / or an absolute value of a difference between an azimuth angle corresponding to the first position and the first azimuth angle is less than or equal to a first angle value, and / or an absolute value of a difference between an elevation angle corresponding to the first position and the first elevation angle is less than or equal to a second angle value.

16. The apparatus of claim 15, wherein, the distance threshold value is determined based on a standard deviation or a root mean square error reflecting a distance measurement error, the first angle value is determined based on a standard deviation or a root mean square error reflecting an azimuth angle measurement error, and the second angle value is determined based on a standard deviation or a root mean square error reflecting an elevation angle measurement error.

17. The apparatus of any one of claims 10 to 12, wherein, the first parameter value is determined based on the first distance and third quality information, the third quality information reflecting an error of the first distance in the measurement data.

18. The apparatus of any one of claims 10 to 12, wherein, at least one of the measurement data is obtained by a sensor, the at least one measurement data being used to obtain a map corresponding to a field of view range of the sensor, each of the measurement data being used to obtain a second parameter value of one or more first positions in the map.

19. An apparatus, comprising: A computer program product comprising a program which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 9.

20. A vehicle characterized by A computer program product comprising a program which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 9.

21. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 9.

22. A computer program product, characterised in that, The computer program product comprises a program which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 9.

Images