Unmanned vehicle positioning method

Abstract

The embodiment of the present invention relates to the field of unmanned driving technology, and discloses a method for positioning an unmanned vehicle. The method comprises: when the unmanned vehicle is in an open-air area, obtaining environmental data of the open-air area, wherein the environmental data comprises rain degree data or snow degree data; calculating the confidence of autonomous positioning according to the environmental data; if the confidence is greater than a preset confidence threshold, determining that the positioning mode is an autonomous positioning mode. The embodiment of the present invention increases the flexibility of switching positioning modes.

Description

Technical Field

[0001] The present invention relates to the field of unmanned driving technology, and in particular to an unmanned vehicle positioning method. Background Art

[0002] At present, unmanned vehicles generally use GPS communication systems for positioning. However, in areas such as high-rise buildings, tunnels or underground parking lots, the positioning error is large, which greatly affects the normal driving of unmanned vehicles. Summary of the invention

[0003] The embodiments of the present invention aim to provide an unmanned vehicle positioning method and an unmanned vehicle, which can improve the positioning accuracy of the unmanned vehicle.

[0004] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention provides an unmanned vehicle positioning method, comprising:

[0006] Obtaining the initial position of the unmanned vehicle when it enters a preset area, and controlling the unmanned vehicle to enter an autonomous positioning mode;

[0007] According to the autonomous positioning mode, respectively obtaining a first point cloud and a second point cloud of the unmanned vehicle at any two adjacent moments in the preset area;

[0008] Calculating the distance difference between the unmanned vehicle and any two adjacent moments according to the first point cloud and the second point cloud;

[0009] Accumulate the distance difference corresponding to each two adjacent moments within the target duration to obtain a total distance difference, wherein the target duration is the duration from the entry moment when the unmanned vehicle enters the preset area to the current moment;

[0010] The current position of the unmanned vehicle is located according to the initial position and the total distance difference.

[0011] In some embodiments, the first point cloud is obtained at a known position, and the second point cloud is obtained at an unknown position, and the calculating the distance difference of the unmanned vehicle at any two adjacent moments according to the first point cloud and the second point cloud comprises:

[0012] Constructing a map of the unmanned vehicle at the unknown location based on the first point cloud and the second point cloud in combination with a SLAM algorithm;

[0013] Calculate the unknown position based on the known position and the map;

[0014] A distance difference is calculated according to the known position and the unknown position.

[0015] In some embodiments, the distance difference includes a first distance difference in the X-axis direction and a second distance difference in the Y-axis direction in the world coordinate system of the unmanned vehicle.

[0016] In some embodiments, before obtaining the initial position of the unmanned vehicle when entering the preset area, the method further includes:

[0017] Obtaining the geographic location of the unmanned vehicle;

[0018] Determining whether the geographical location is within the area of ​​the preset area;

[0019] If yes, proceed to the step of obtaining the initial position of the unmanned vehicle when it enters the preset area;

[0020] If not, continue to navigate the unmanned vehicle according to the real-time geographic location received by the positioning device of the unmanned vehicle.

[0021] In some embodiments, the predetermined area includes an open-air area and / or a closed area;

[0022] The open-air area includes a complex of high-rise buildings;

[0023] The enclosed area includes a tunnel and an underground parking lot.

[0024] In some embodiments, controlling the unmanned vehicle to enter the autonomous positioning mode includes:

[0025] When the preset area where the unmanned vehicle is located is an open-air area, obtaining environmental data of the open-air area;

[0026] When the environmental data is rain degree data or snow degree data, calculating the confidence of the autonomous positioning according to the environmental data;

[0027] According to the confidence level, a positioning mode of the unmanned vehicle is controlled, where the positioning mode includes an autonomous positioning mode or a navigation positioning mode.

[0028] In some embodiments, calculating the confidence of autonomous positioning according to the environmental data includes:

[0029] Using the camera of the unmanned vehicle to shoot the surrounding environment to obtain an environmental image;

[0030] Extracting characteristic connected regions of all raindrops or snowflakes in the environmental image;

[0031] Calculate the area of ​​the characteristic connected region of each raindrop or snowflake;

[0032] Calculating the average area of ​​the raindrops or snowflakes in the environment image according to the area of ​​the characteristic connected area of ​​each raindrop or snowflake;

[0033] The confidence level of autonomous positioning is calculated based on the average area value of the region and a preset confidence score table.

[0034] In some embodiments, the preset confidence score table includes a number of confidence levels, each of which corresponds to a type of confidence;

[0035] The calculating the confidence of autonomous positioning according to the average area of ​​the region and the preset confidence score table includes:

[0036] According to the preset confidence score table, traverse the target confidence level including the average area value of the region;

[0037] The confidence level of the target confidence level is selected as the confidence level of autonomous positioning.

[0038] In some embodiments, controlling the positioning mode of the unmanned vehicle according to the confidence level includes:

[0039] Determining whether the confidence level is greater than a preset confidence threshold;

[0040] If so, determining that the positioning mode is an autonomous positioning mode;

[0041] If not, it is determined that the positioning mode is a navigation positioning mode.

[0042] In a second aspect, an embodiment of the present invention provides an unmanned vehicle, including:

[0043] at least one processor; and,

[0044] a memory communicatively connected to the at least one processor; wherein,

[0045] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the unmanned vehicle positioning method as described in any one of the above items.

[0046] In a third aspect, an embodiment of the present invention provides an unmanned vehicle positioning device, comprising:

[0047] A first acquisition module is used to acquire the initial position of the unmanned vehicle when it enters a preset area, and control the unmanned vehicle to enter an autonomous positioning mode;

[0048] A second acquisition module is used to respectively acquire a first point cloud and a second point cloud of the unmanned vehicle at any two adjacent moments in the preset area according to the autonomous positioning mode;

[0049] A calculation module, configured to calculate a distance difference between the unmanned vehicle and any two adjacent moments according to the first point cloud and the second point cloud;

[0050] An accumulation module, used to accumulate the distance difference corresponding to each two adjacent moments within a target duration to obtain a total distance difference, wherein the target duration is the duration from the entry moment when the unmanned vehicle enters the preset area to the current moment;

[0051] A positioning module is used to locate the current position of the unmanned vehicle based on the initial position and the total distance difference.

[0052] In some embodiments, the first point cloud is obtained at a known position, and the second point cloud is obtained at an unknown position, and the calculation module includes:

[0053] A construction unit, configured to construct a map of the unmanned vehicle at the unknown location according to the first point cloud and the second point cloud in combination with a SLAM algorithm;

[0054] A first calculation unit, configured to calculate the unknown position according to the known position in combination with the map;

[0055] The second calculation unit is used to calculate the distance difference according to the known position and the unknown position.

[0056] In some embodiments, the distance difference includes a first distance difference in the X-axis direction and a second distance difference in the Y-axis direction in the world coordinate system of the unmanned vehicle.

[0057] In some embodiments, before obtaining the initial position of the unmanned vehicle when entering the preset area, the device further includes:

[0058] A third acquisition module is used to obtain the geographic location of the unmanned vehicle;

[0059] A determination module, used to determine whether the geographical location is within the area range of the preset area;

[0060] If the geographical location is within the area of ​​the preset area, the step of obtaining the initial position of the unmanned vehicle when it enters the preset area is performed;

[0061] The navigation module is used to continue navigating the unmanned vehicle according to the real-time geographical location received by the positioning device of the unmanned vehicle if the geographical location is not within the area range of the preset area.

[0062] In some embodiments, the predetermined area includes an open-air area and / or a closed area;

[0063] The open-air area includes a complex of high-rise buildings;

[0064] The enclosed area includes a tunnel and an underground parking lot.

[0065] In some embodiments, the first acquisition module includes:

[0066] an acquisition unit, configured to acquire environmental data of an open-air area when the preset area where the unmanned vehicle is located is an open-air area;

[0067] a third calculation unit, configured to calculate the confidence of the autonomous positioning according to the environmental data when the environmental data is rain degree data or snow degree data;

[0068] A control unit is used to control a positioning mode of the unmanned vehicle according to the confidence level, wherein the positioning mode includes an autonomous positioning mode or a navigation positioning mode.

[0069] In some embodiments, the third computing unit includes:

[0070] A shooting subunit, used to use the camera of the unmanned vehicle to shoot the surrounding environment to obtain an environmental image;

[0071] An extraction subunit, used to extract characteristic connected areas of all raindrops or snowflakes in the environment image;

[0072] A first calculation subunit, used for calculating the area of ​​the characteristic connected region of each raindrop or snowflake;

[0073] A second calculation subunit, configured to calculate an average area of ​​raindrops or snowflakes in the environment image according to the area of ​​each characteristic connected area of ​​the raindrops or snowflakes;

[0074] The third calculation subunit is used to calculate the confidence of autonomous positioning according to the average area value of the region and a preset confidence score value table.

[0075] In some embodiments, the preset confidence score table includes a number of confidence levels, each of which corresponds to a type of confidence;

[0076] The third computing subunit is specifically used for:

[0077] According to the preset confidence score table, traverse the target confidence level including the average area value of the region;

[0078] The confidence level of the target confidence level is selected as the confidence level of autonomous positioning.

[0079] In some embodiments, the control unit comprises:

[0080] A judging subunit, used to judge whether the confidence level is greater than a preset confidence threshold;

[0081] A first determination subunit, configured to determine that the positioning mode is an autonomous positioning mode if the confidence level is greater than the preset confidence threshold;

[0082] The second determination subunit is used to determine that the positioning mode is the navigation positioning mode if the confidence level is less than or equal to the preset confidence threshold.

[0083] In a fourth aspect, an embodiment of the present invention further provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable an unmanned vehicle to execute the unmanned vehicle positioning method as described in any one of the above items.

[0084] The beneficial effect of the embodiments of the present invention is as follows: different from the prior art, the embodiments of the present invention provide an unmanned vehicle positioning method and an unmanned vehicle, which obtain the initial position of the unmanned vehicle when it enters a preset area, and control the unmanned vehicle to enter an autonomous positioning mode. According to the autonomous positioning mode, the first point cloud and the second point cloud of the unmanned vehicle at any two adjacent moments in the preset area are respectively obtained, and the distance difference of the unmanned vehicle at any two adjacent moments is calculated according to the first point cloud and the second point cloud, and the distance difference corresponding to each two adjacent moments within the target duration is accumulated to obtain the total distance difference. The target duration is the time from the entry moment to the current moment when the unmanned vehicle enters the preset area. According to the initial position and the total distance difference, the current position of the unmanned vehicle is located. Therefore, the embodiments of the present invention improve the positioning accuracy of the unmanned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0086] Figure 1 It is a schematic diagram of one application scenario of the unmanned vehicle positioning method provided by an embodiment of the present invention;

[0087] Figure 2 is a method flow chart of one of the unmanned vehicle positioning methods provided by an embodiment of the present invention;

[0088] Figure 3 yes Figure 2 A flowchart of one method of step S11;

[0089] Figure 4 yes Figure 3 A method flow chart of step S112;

[0090] Figure 5 yes Figure 3 A method flow chart of step S113;

[0091] Figure 6 yes Figure 2 A method flow chart of step S13;

[0092] Figure 7 is a method flow chart of one of the unmanned vehicle positioning methods provided by an embodiment of the present invention;

[0093] Figure 8 is a structural schematic diagram of one of the unmanned vehicle positioning devices provided by an embodiment of the present invention;

[0094] Fig. 9 is a structural schematic diagram of one of the unmanned vehicle positioning devices provided by an embodiment of the present invention;

[0095] Fig.10 It is a structural schematic diagram of an unmanned vehicle provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0096] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0097] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flow chart. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0098] Since unmanned vehicles can replace drivers to perform "boring, harsh, dangerous, and deep" tasks, they have many advantages such as strong mobility, high adaptability and survivability, and reduced risk of casualties. Therefore, they have broad application prospects in military and civilian fields. Unmanned vehicle positioning and navigation based on unmanned vehicle positioning are the most basic requirements for unmanned vehicles to be able to drive normally in unknown or known environments. At present, unmanned vehicles use GPS (Global Positioning System) for positioning, and the vehicle positioning accuracy is within 10 meters. When the unmanned vehicle is on a city road or a canyon, the GPS signal will be blocked by high-rise buildings, trees, tunnels, etc., so that the vehicle positioning accuracy will be further reduced, which will have a great impact on the normal driving of the unmanned vehicle. In order to solve the problem of poor positioning accuracy of unmanned vehicles based on traditional GPS positioning in a preset area, an embodiment of the present invention proposes a method for positioning an unmanned vehicle.

[0099] See also Figure 1 , is a schematic diagram of one application scenario of the unmanned vehicle positioning method provided by an embodiment of the present invention. Specifically, the application scenario includes an unmanned vehicle 10, a GPS satellite 20 and a server 30.

[0100] The unmanned vehicle 10 is connected to the GPS satellite 20, which includes 24 global positioning satellites, and is used to provide three-dimensional position information and three-dimensional speed information to all parts of the world around the clock. The server 30 is connected to the GPS satellite 20, and includes one or more of a system application server, a database server, and an electronic map server.

[0101] The unmanned vehicle 10 is a smart car, including a GPS receiving antenna, a computer system and a display device.

[0102] The GPS receiving antenna is used to receive data information transmitted by at least 3 GPS satellites among the 24 GPS satellites, and obtain the distance between the GPS satellite 20 and the unmanned vehicle 10, clock correction, atmospheric correction and other parameters. The computer system is used to process the distance, clock correction and atmospheric correction and other parameters to determine the position of the unmanned vehicle 10, and send the position to the server 30 through the GPS satellite 20, so that the terminal device can obtain the real-time position information of the unmanned vehicle 10 through the network. The display device is used to display the position on the electronic map stored in the unmanned vehicle 10 and the position, dynamically plan the route of the unmanned vehicle 10, and display the road conditions ahead, gas stations, restaurants, hotels and other information.

[0103] In some embodiments, the GPS receiving antenna is also used to obtain the electronic map updated by the server 30 and load it to the display device.

[0104] In this embodiment, the preset area includes an open-air area and / or a closed area, the open-air area includes a high-rise building complex, and the closed area includes a tunnel and an underground parking lot. The unmanned vehicle 10 should include a laser radar 101, which is specifically used to generate a first point cloud and a second point cloud at any two adjacent moments in the preset area in the autonomous positioning mode of the unmanned vehicle 10, so that the computer system can locate the current position of the unmanned vehicle 10 based on the first point cloud and the second point cloud at any two adjacent moments, and the initial position of the unmanned vehicle 10 entering the preset area.

[0105] It can be understood that the unmanned vehicle 10 corresponds to different positions at any time, such as Figure 1 As shown, the entry time T0 of the unmanned vehicle 10 when entering the preset area corresponds to the initial position S0. In the preset area, the first adjacent time T1 adjacent to the entry time T0 corresponds to the first adjacent position S1, the second adjacent time T2 adjacent to the first adjacent time T1 corresponds to the second adjacent position S2, the third adjacent time T3 adjacent to the first adjacent time T2 corresponds to the third adjacent position S3... The exit time Tn adjacent to the first adjacent time Tn-1 corresponds to the end position Sn.

[0106] Specifically, the distance difference S01 corresponding to the entry time T0 and its adjacent time T1 is equal to the absolute value of the difference between the first adjacent position S1 and the initial position S0. According to the initial position S0 and the distance difference S01 corresponding to the entry time T0 and its adjacent time T1, the current position of the unmanned vehicle 10 is located, and the current position is equal to the initial position S0 plus the distance difference S01. By analogy, the position of the unmanned vehicle 10 in the preset area can be accurately located. For example, at the fourth adjacent time T4, the current position of the unmanned vehicle 10 is equal to the cumulative value of the initial position S0, the distance difference S01, the distance difference S12, the distance difference S23 and the distance difference S34.

[0107] Specifically, the embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0108] See also Figure 2 , is a flowchart of a method for positioning an unmanned vehicle provided by an embodiment of the present invention. Figure 2 As shown, the unmanned vehicle positioning method includes but is not limited to the following steps:

[0109] Step S11: obtaining the initial position of the unmanned vehicle when it enters a preset area, and controlling the unmanned vehicle to enter an autonomous positioning mode.

[0110] In this embodiment, the positioning mode of the unmanned vehicle includes at least an autonomous positioning mode and a navigation positioning mode.

[0111] Specifically, outside the preset area, the GPS signal is strong, and the control is switched to the navigation positioning mode. Based on the vehicle-mounted GPS system, the vehicle-mounted positioning navigation of the unmanned vehicle can be realized. In the preset area, the GPS signal is weak, so that the positioning accuracy of the unmanned vehicle is poor. Therefore, when the unmanned vehicle enters the preset area, the initial position of the unmanned vehicle when entering the preset area is obtained, and the unmanned vehicle is controlled to enter the autonomous positioning mode, wherein the initial position can be obtained through the vehicle-mounted GPS system.

[0112] Step S12: According to the autonomous positioning mode, a first point cloud and a second point cloud of the unmanned vehicle at any two adjacent moments in the preset area are respectively obtained.

[0113] Point cloud is a collection of massive points that express the spatial distribution and surface characteristics of the target in the same spatial reference system. After obtaining the spatial coordinates of each sampling point on the surface of the object, a collection of points is obtained. The point cloud obtained according to the principle of laser measurement includes three-dimensional coordinates (XYZ) and laser reflection intensity (Intensity). The intensity information is related to the surface material, roughness, incident angle direction of the target, as well as the emission energy of the instrument and the laser wavelength. The point cloud obtained according to the principle of photogrammetry includes three-dimensional coordinates (XYZ) and color information (RGB). The point cloud obtained by combining the principles of laser measurement and photogrammetry includes three-dimensional coordinates (XYZ), laser reflection intensity (Intensity) and color information (RGB).

[0114] For example, the laser radar carried by the unmanned vehicle scans the surrounding environment by rotating 360 degrees. For example, a 64-line laser radar means that 64 laser radars are arranged longitudinally with different pitch angles, and then rotate to sample the 360-degree environment to obtain the first point cloud and the second point cloud. Step S13: Calculate the distance difference of the unmanned vehicle at any two adjacent moments according to the first point cloud and the second point cloud.

[0115] In this embodiment, the first point cloud and the second point cloud are converted into cylindrical coordinates, and the first point cloud and the second point cloud are expanded into depth images according to the cylindrical coordinates. The depth images are processed based on a deep learning algorithm to obtain the distance difference of the unmanned vehicle at any two adjacent moments.

[0116] Step S14: Accumulate the distance difference corresponding to each two adjacent moments within the target duration to obtain a total distance difference, wherein the target duration is the duration from the entry moment when the unmanned vehicle enters the preset area to the current moment.

[0117] Among them, assuming that the time when the unmanned vehicle passes through the preset area is the elapsed time, the minimum value of the target duration is equal to the entry time, and the maximum value of the target duration is equal to the entry time plus the elapsed time. According to the scanning cycle of the laser radar carried by the unmanned vehicle, the distance difference corresponding to each two adjacent moments within the target duration can be calculated. By adjusting the scanning cycle of the laser radar carried by the unmanned vehicle, the distance between any two adjacent moments can be adjusted, thereby adjusting the positioning accuracy of the unmanned vehicle. It can be understood that the smaller the distance between any two adjacent moments, the higher the positioning accuracy of the unmanned vehicle.

[0118] Step S15: Locate the current position of the unmanned vehicle according to the initial position and the total distance difference.

[0119] In some embodiments, see Figure 3 , which shows Figure 2 One of the method flow charts of step S11 in Figure 2 In the method shown, controlling the unmanned vehicle to enter the autonomous positioning mode includes:

[0120] Step S111: When the preset area where the unmanned vehicle is located is an open-air area, environmental data of the open-air area is obtained.

[0121] The preset area includes an open-air area and / or a closed area. The open-air area includes a high-rise building complex, and the closed area includes a tunnel and an underground parking lot.

[0122] Step S112: When the environmental data is rain degree data or snow degree data, the confidence of the autonomous positioning is calculated according to the environmental data.

[0123] Step S113: According to the confidence level, controlling the positioning mode of the unmanned vehicle, the positioning mode including an autonomous positioning mode or a navigation positioning mode.

[0124] In some cases, when the preset area where the unmanned vehicle is located is an open-air area, the open-air area is more susceptible to environmental factors. When the environmental data is rain degree data or snow degree data, the GPS signal in the open-air area is uncertain.

[0125] If the rain or snow is light, or even non-existent, the GPS signal in the open-air area is not much different from the signal level in other road areas outside the preset area. At this time, the value of the confidence of autonomous positioning calculated based on the environmental data is small, and the positioning mode of the unmanned vehicle needs to be controlled to switch to the navigation positioning mode based on the confidence. If the rain or snow is severe, the GPS signal in the open-air area may be greatly attenuated or interrupted. At this time, the value of the confidence of autonomous positioning calculated based on the environmental data is large. In order to ensure the reliable driving of the unmanned vehicle, the positioning mode of the unmanned vehicle needs to be controlled to switch to the autonomous positioning mode based on the confidence.

[0126] In summary, the embodiments of the present invention not only ensure the positioning accuracy of the unmanned vehicle, but also increase the flexibility of switching positioning modes.

[0127] In some embodiments, see Figure 4 , which shows Figure 3 One of the method flow charts of step S112 in Figure 3 The method shown, wherein calculating the confidence of autonomous positioning according to the environmental data comprises:

[0128] Step S1121: Use the camera of the unmanned vehicle to capture the surrounding environment to obtain an environmental image.

[0129] Step S1122: extracting the characteristic connected areas of all raindrops or snowflakes in the environmental image.

[0130] Step S1123: Calculate the area of ​​the characteristic connected region of each raindrop or snowflake.

[0131] Step S1124: Calculate the average area of ​​the raindrops or snowflakes in the environment image according to the area of ​​each characteristic connected area of ​​the raindrops or snowflakes.

[0132] Step S1125: Calculate the confidence of autonomous positioning according to the average area value of the region and a preset confidence score table.

[0133] In this embodiment, the preset confidence score table includes several confidence levels, each of which corresponds to a type of confidence. The calculation of the confidence of autonomous positioning based on the average area value of the area and the preset confidence score table includes: traversing the target confidence levels including the average area value of the area according to the preset confidence score table; and selecting the confidence of the target confidence level as the confidence of autonomous positioning.

[0134] It can be understood that the unmanned vehicle is equipped with a camera, and the camera is used to capture the surrounding environment and obtain an environmental image. The computer system of the unmanned vehicle is used to obtain the environmental image and calculate the confidence of autonomous positioning based on the environmental image. The preset confidence score table is pre-stored in the computer system of the unmanned vehicle, or can also be downloaded from a server via the network.

[0135] As mentioned above, the degree of rain or snow may affect the confidence of the autonomous positioning. Specifically, the greater the degree of rain or snow, the greater the confidence of the autonomous positioning, and the smaller the degree of rain or snow, the smaller the confidence of the autonomous positioning. In this embodiment, the size of the characteristic connected area of ​​raindrops or snowflakes is used to represent the degree of rain or snow. Generally speaking, the greater the degree of rain or snow, the greater the unit rainfall or precipitation, and the larger the characteristic connected area of ​​raindrops or snowflakes around the unmanned vehicle.

[0136] In some embodiments, see Figure 5 , which shows Figure 3 One of the method flow charts of step S113 in Figure 3 In the method shown, controlling the positioning mode of the unmanned vehicle according to the confidence level includes:

[0137] Step S1131: Determine whether the confidence level is greater than a preset confidence threshold.

[0138] Step S1132: If yes, determine that the positioning mode is the autonomous positioning mode.

[0139] Step S1133: If not, determine that the positioning mode is the navigation positioning mode.

[0140] In some embodiments, the first point cloud is obtained at a known position and the second point cloud is obtained at an unknown position. Figure 6 , which shows Figure 2 One of the method flow charts of step S13 in Figure 2 In the method shown, the calculating the distance difference between the unmanned vehicle at any two adjacent moments according to the first point cloud and the second point cloud includes:

[0141] Step S131: Based on the first point cloud and the second point cloud, in combination with the SLAM algorithm, a map of the unmanned vehicle at the unknown position is constructed. Step S132: Based on the known position, in combination with the map, the unknown position is calculated.

[0142] Step S133: Calculate the distance difference according to the known position and the unknown position.

[0143] The SLAM algorithm is also called the simultaneous localization and mapping algorithm. It regards the preset area as an unknown environment. The unmanned vehicle starts to move from an unknown position in the unknown environment. During the movement, it locates itself based on the position estimation and map. At the same time, it can build an incremental map based on its own positioning to achieve autonomous positioning and navigation of the unmanned vehicle.

[0144] The distance difference includes a first distance difference in the X-axis direction and a second distance difference in the Y-axis direction in the world coordinate system of the unmanned vehicle.

[0145] In some embodiments, see Figure 7 , which shows a method flow chart of one of the unmanned vehicle positioning methods provided by an embodiment of the present invention, based on Figures 2 to 6 The method shown in the figure, before obtaining the initial position of the unmanned vehicle when entering the preset area, the method also includes:

[0146] Step S16: Obtain the geographic location of the unmanned vehicle.

[0147] Step S17: Determine whether the geographical location is within the area range of the preset area.

[0148] If so, the process proceeds to the step of obtaining the initial position of the unmanned vehicle when it enters the preset area (ie, step S11 ).

[0149] Step S18: If not, continue to navigate the unmanned vehicle according to the real-time geographic location received by the positioning device of the unmanned vehicle.

[0150] An unmanned vehicle positioning method provided by an embodiment of the present invention obtains the initial position of the unmanned vehicle when it enters a preset area, and controls the unmanned vehicle to enter an autonomous positioning mode. According to the autonomous positioning mode, a first point cloud and a second point cloud of the unmanned vehicle at any two adjacent moments in the preset area are respectively obtained. According to the first point cloud and the second point cloud, the distance difference of the unmanned vehicle at any two adjacent moments is calculated, and the distance difference corresponding to each two adjacent moments within a target duration is accumulated to obtain a total distance difference. The target duration is the duration from the entry moment to the current moment when the unmanned vehicle enters the preset area. According to the initial position and the total distance difference, the current position of the unmanned vehicle is located. Therefore, the embodiment of the present invention improves the positioning accuracy of the unmanned vehicle.

[0151] See also Figure 8 , is a structural diagram of one of the unmanned vehicle positioning devices provided in an embodiment of the present invention. The unmanned vehicle positioning device 800 includes a first acquisition module 81, a second acquisition module 82, a calculation module 83, an accumulation module 84 and a positioning module 85.

[0152] The first acquisition module 81 is used to acquire the initial position of the unmanned vehicle when it enters a preset area, and control the unmanned vehicle to enter an autonomous positioning mode.

[0153] The preset area includes an open-air area and / or a closed area. The open-air area includes a high-rise building complex, and the closed area includes a tunnel and an underground parking lot.

[0154] See also Fig. 9 The first acquisition module 81 includes an acquisition unit 811, a third calculation unit 812 and a control unit 813.

[0155] The acquisition unit 811 is used to acquire environmental data of the open-air area when the preset area where the unmanned vehicle is located is an open-air area.

[0156] The third calculation unit 812 is used to calculate the confidence of autonomous positioning according to the environmental data when the environmental data is rain degree data or snow degree data.

[0157] In some embodiments, the third computing unit 812 includes a photographing subunit 8121 , an extracting subunit 8122 , a first computing subunit 8123 , a second computing subunit 8124 and a third computing subunit 8125 .

[0158] The shooting subunit 8121 is used to use the camera of the unmanned vehicle to shoot the surrounding environment to obtain an environmental image.

[0159] The extraction subunit 8122 is used to extract the characteristic connected areas of all raindrops or snowflakes in the environmental image.

[0160] The first calculation subunit 8123 is used to calculate the area of ​​the characteristic connected region of each raindrop or snowflake.

[0161] The second calculation subunit 8124 is used to calculate the average area of ​​the raindrops or snowflakes in the environment image according to the area of ​​the characteristic connected area of ​​each raindrop or snowflake.

[0162] The third calculation subunit 8125 is used to calculate the confidence of autonomous positioning according to the average area value of the region and a preset confidence score table.

[0163] Among them, the preset confidence score table includes several confidence levels, each of which corresponds to a type of confidence, and the third calculation subunit is specifically used to: traverse the target confidence level containing the average area value of the region according to the preset confidence score table; select the confidence of the target confidence level as the confidence of autonomous positioning.

[0164] The control unit 813 is used to control the positioning mode of the unmanned vehicle according to the confidence level, and the positioning mode includes an autonomous positioning mode or a navigation positioning mode.

[0165] See also Fig. 9 The control unit 813 includes a judging subunit 8131, a first determining subunit 8132 and a second determining subunit 8133.

[0166] The judging subunit 8131 is used to judge whether the confidence level is greater than a preset confidence threshold.

[0167] The first determination subunit 8132 is used to determine that the positioning mode is the autonomous positioning mode if the confidence level is greater than the preset confidence threshold.

[0168] The second determination subunit 8133 is used to determine that the positioning mode is the navigation positioning mode if the confidence level is less than or equal to the preset confidence threshold.

[0169] The second acquisition module 82 is used to respectively acquire the first point cloud and the second point cloud of the unmanned vehicle at any two adjacent moments in the preset area according to the autonomous positioning mode.

[0170] The calculation module 83 is used to calculate the distance difference between the unmanned vehicle and any two adjacent moments according to the first point cloud and the second point cloud.

[0171] See also Fig. 9 , the first point cloud is obtained at a known position, the second point cloud is obtained at an unknown position, and the calculation module 83 includes a construction unit 831, a first calculation unit 832 and a second calculation unit 833.

[0172] The construction unit 831 is used to construct a map of the unmanned vehicle at the unknown location based on the first point cloud and the second point cloud in combination with a SLAM algorithm.

[0173] The first calculation unit 832 is used to calculate the unknown position according to the known position in combination with the map.

[0174] The second calculation unit 833 is used to calculate a distance difference according to the known position and the unknown position.

[0175] The distance difference includes a first distance difference in the X-axis direction and a second distance difference in the Y-axis direction in the world coordinate system of the unmanned vehicle.

[0176] The accumulation module 84 is used to accumulate the distance difference corresponding to each two adjacent moments within the target duration to obtain a total distance difference. The target duration is the duration from the entry moment when the unmanned vehicle enters the preset area to the current moment.

[0177] The positioning module 85 is used to locate the current position of the unmanned vehicle according to the initial position and the total distance difference.

[0178] Please refer again Fig. 9 , is a structural diagram of one of the unmanned vehicle positioning devices provided in an embodiment of the present invention. Based on the functional modules shown in the unmanned vehicle positioning device 800, the unmanned vehicle positioning device 900 also includes a third acquisition module 91, a judgment module 92 and a navigation module 93.

[0179] The third acquisition module 91 is used to acquire the geographic location of the unmanned vehicle.

[0180] The judgment module 92 is used to judge whether the geographical location is within the area range of the preset area. If the geographical location is within the area range of the preset area, the step of obtaining the initial position of the unmanned vehicle when entering the preset area is entered.

[0181] The navigation module 93 is used to continue navigating the unmanned vehicle according to the real-time geographical location received by the positioning device of the unmanned vehicle if the geographical location is not within the area range of the preset area.

[0182] An unmanned vehicle positioning device provided by an embodiment of the present invention obtains the initial position of the unmanned vehicle when entering a preset area through a first acquisition module, and controls the unmanned vehicle to enter an autonomous positioning mode. The second acquisition module obtains the first point cloud and the second point cloud of the unmanned vehicle at any two adjacent moments in the preset area according to the autonomous positioning mode. The calculation module calculates the distance difference of the unmanned vehicle at any two adjacent moments according to the first point cloud and the second point cloud. The accumulation module accumulates the distance difference corresponding to each two adjacent moments within the target duration to obtain the total distance difference. The target duration is the duration from the entry moment to the current moment when the unmanned vehicle enters the preset area. The positioning module locates the current position of the unmanned vehicle according to the initial position and the total distance difference. Therefore, the embodiment of the present invention improves the positioning accuracy of the unmanned vehicle.

[0183] A schematic diagram of the structure of an unmanned vehicle provided by an embodiment of the present invention is shown in FIG. Fig.10 , which shows that it is possible to execute Figures 2 to 7 The hardware structure of the unmanned vehicle of the unmanned vehicle positioning method in the unmanned vehicle 10 can be Figure 1 The unmanned vehicle 10 is shown.

[0184] The unmanned vehicle 10 includes: at least one processor 101; and a memory 102 in communication with the at least one processor 101. Fig.10 The memory 102 stores instructions that can be executed by the at least one processor 101, and the instructions are executed by the at least one processor 101 so that the at least one processor 101 can perform the above Figures 2 to 7 The unmanned vehicle positioning method.

[0185] The processor 101 and the memory 102 may be connected via a bus or other means. Fig.10 The example of connecting through bus is taken in the following.

[0186] The memory 102 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the unmanned vehicle positioning method in the embodiment of the present invention, for example, Figure 8 and attached Fig. 9 The processor 101 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 102, that is, the unmanned vehicle positioning method described in the above method embodiment is implemented.

[0187] The memory 102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created according to the use of the unmanned vehicle positioning device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 102 may optionally include a memory remotely arranged relative to the processor 101, and these remote memories may be connected to the device for controlling the driving of the unmanned vehicle via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0188] The one or more modules are stored in the memory 102, and when executed by the one or more processors 101, the unmanned vehicle positioning method in any of the above method embodiments is executed, for example, the above described Figures 2 to 7 Steps to achieve Figures 8 to 9 The functions of each module and unit in it.

[0189] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0190] The embodiment of the present invention further provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, for example, to execute the above-described Figures 2 to 7 Steps to achieve Figures 8 to 9 The functions of each module in.

[0191] The embodiment of the present invention further provides a computer program product, including a computer program stored on a non-volatile computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the unmanned vehicle executes the unmanned vehicle positioning method in any of the above method embodiments, for example, executing the above described Figures 2 to 7 Steps to achieve Figures 8 to 9 The functions of each module in.

[0192] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0193] Through the description of the above implementation methods, ordinary technicians in this field can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Ordinary technicians in this field can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0194] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may also be combined, the steps may be implemented in any order, and there are many other changes in different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they may still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for positioning an unmanned vehicle, characterized in that: include: When the unmanned vehicle is in an open-air area, obtaining environmental data of the open-air area, the environmental data including rain degree data or snow degree data; Using the camera of the unmanned vehicle to shoot the surrounding environment to obtain an environmental image; Extracting characteristic connected regions of all raindrops or snowflakes in the environmental image; Calculate the area of ​​the characteristic connected region of each raindrop or snowflake; Calculating the average area of ​​the raindrops or snowflakes in the environment image according to the area of ​​the characteristic connected area of ​​each raindrop or snowflake; According to a preset confidence score table, traverse the target confidence level including the average area value of the region, the preset confidence score table includes a plurality of confidence levels, each of which corresponds to a type of confidence degree; Selecting the confidence level of the target confidence level as the confidence level of autonomous positioning; If the confidence level is greater than a preset confidence threshold, determining that the positioning mode is an autonomous positioning mode; Acquire an initial position of the unmanned vehicle when entering a preset area, at which the unmanned vehicle enters an autonomous positioning mode, wherein the preset area includes an open-air area and / or a closed area; According to the autonomous positioning mode, respectively obtaining a first point cloud and a second point cloud of the unmanned vehicle at any two adjacent moments in the preset area; Calculating the distance difference between the unmanned vehicle and any two adjacent moments according to the first point cloud and the second point cloud; Accumulate the distance difference corresponding to each two adjacent moments within the target duration to obtain a total distance difference, wherein the target duration is the duration from the entry moment when the unmanned vehicle enters the preset area to the current moment; The current position of the unmanned vehicle is located according to the initial position and the total distance difference.

2. The method according to claim 1, characterized in that Also includes: If the confidence level is less than or equal to the preset confidence threshold, the positioning mode is determined to be the navigation positioning mode.

3. The method according to claim 2, characterized in that Also includes: When the unmanned vehicle is in a closed area, the positioning mode is determined to be an autonomous positioning mode.

4. The method according to claim 1, characterized in that The first point cloud is obtained at a known position, and the second point cloud is obtained at an unknown position, and the calculating the distance difference of the unmanned vehicle at any two adjacent moments according to the first point cloud and the second point cloud comprises: Constructing a map of the unmanned vehicle at the unknown location based on the first point cloud and the second point cloud in combination with a SLAM algorithm; Calculate the unknown position based on the known position and the map; A distance difference is calculated according to the known position and the unknown position.

5. The method according to claim 4, characterized in that The distance difference includes a first distance difference in the X-axis direction and a second distance difference in the Y-axis direction in the world coordinate system of the unmanned vehicle.

Images