Parking lot map processing method, device, equipment and medium

Abstract

The present application provides a method, device, equipment and medium for processing a parking lot map. In the method, multiple vehicles are driving in a parking lot with a ramp, and the vehicles send data obtained by sensors, laser radars, vehicle controllers, etc. to a server. The server generates a driving route based on the mapping data received from multiple vehicles, and then determines the ramp route in the driving route. The ramp route is divided into a ramp section entering or exiting the ramp, a turning section, and a smooth section, and the data of all vehicles in each section are calculated, and then fitting is performed. Based on the fitted data, ramps and walls are generated on the map. In this solution, the server generates ramps and walls on the map based on the mapping data of multiple vehicles, thereby generating a map corresponding to the ramps between parking lots.

Description

Technical Field

[0001] The present application relates to the field of autonomous valet parking, and in particular to a method, device, equipment and medium for processing a parking lot map. Background Art

[0002] With the development of science and technology and the improvement of people's living standards, people have put forward higher requirements for food, clothing, housing and transportation. In terms of travel, people also have higher requirements for car control, comfort, fuel consumption, etc. Therefore, cars have evolved from being completely controlled by people to being able to be unmanned and autonomous valet parking. For autonomous valet parking, a map of the parking lot is necessary data.

[0003] In the prior art, when a parking lot map is to be constructed, the driver is required to drive along a designated route and park in a designated parking space. The vehicle is equipped with sensors, and after the vehicle drives through each floor of the parking lot, the sensor data is sent to the server. The server can obtain a map of each floor of the parking lot based on the sensor data.

[0004] In summary, the existing parking lot map processing method can only obtain the map of each floor, and there is currently no solution that can generate the map corresponding to the ramps between parking lots. Summary of the invention

[0005] The embodiments of the present application provide a parking lot map processing method, device, equipment and medium, which are used to solve the problem that the existing parking lot map processing method can only obtain a map of each floor, and there is currently no solution that can generate a map corresponding to the ramps between parking lots.

[0006] In a first aspect, an embodiment of the present application provides a method for processing a parking lot map, which is applied to a server, and the method includes:

[0007] Receive mapping data sent by multiple vehicles, the mapping data including wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, the IMU data including acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data including ramp entrances, the laser radar point cloud data or ultrasonic data including the distance between the wall and the vehicle, and the z-axis direction is a direction perpendicular to the road surface where the vehicle is located;

[0008] According to the mapping data, ramps and walls are generated in a preset map.

[0009] In a specific implementation, generating ramps and walls in a preset map according to the mapping data includes:

[0010] Generate driving routes corresponding to all vehicles according to the wheel speed pulse data and the IMU data;

[0011] For each driving route corresponding to the vehicle, determining the starting position and the ending position of the ramp in the driving route according to the IMU data and the visual perception data corresponding to the vehicle, and obtaining at least one ramp route;

[0012] For each ramp route, the ramp route is divided into an entry or exit ramp section, a turning section and a smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle;

[0013] According to the IMU data, laser radar point cloud data or ultrasonic data and steering wheel angle corresponding to the vehicle, the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are obtained;

[0014] Fitting the slope and width corresponding to the slope section entering or exiting the slope, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the slope route corresponding to all vehicles to obtain the fitted slope, width and curvature;

[0015] The ramp and the wall are generated on the map according to the fitted slope, width and curvature.

[0016] In a specific implementation, the step of dividing the ramp route into a ramp section, a turning section, and a smooth section according to the wheel speed pulse data, IMU data, and steering wheel angle corresponding to the vehicle includes:

[0017] Selecting a section corresponding to an upward pitch angular velocity greater than a preset first angular velocity or a downward pitch angular velocity less than a preset second angular velocity in the IMU data from the ramp route, and determining it as a pitch section;

[0018] Determine the road section in the pitch section whose road section length is greater than a preset length as the road section for entering or exiting the ramp;

[0019] Determine the section of the slope route where the steering wheel angle is greater than a preset angle as a turning section;

[0020] The sections of the ramp route except the ramp entry or exit section and the turning section are determined as smooth sections.

[0021] In a specific implementation, the slope and width corresponding to the ramp section for entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are obtained according to the IMU data, the laser radar point cloud data or the ultrasonic data and the steering wheel angle corresponding to the vehicle, including:

[0022] Integrate the upward pitch angular velocity or downward pitch angular velocity in the IMU data corresponding to the entering or exiting ramp section to obtain the slope corresponding to the entering or exiting ramp section;

[0023] Calculating a plurality of first widths according to the laser radar point cloud data or ultrasonic data corresponding to the entering or exiting ramp road section;

[0024] Fitting the multiple first widths to obtain a width corresponding to the entry or exit ramp section;

[0025] Calculate the slope of the turning section according to the acceleration in the z-axis direction in the IMU data corresponding to the turning section;

[0026] Calculating the curvature corresponding to the turning section according to the turning section and the laser radar point cloud data or ultrasonic data corresponding to the turning section;

[0027] Calculating a plurality of second widths according to the laser radar point cloud data or ultrasonic data corresponding to the turning section;

[0028] Fitting the multiple second widths to obtain a width corresponding to the turning section;

[0029] Calculating multiple slopes according to the acceleration in the z-axis direction in the IMU data corresponding to the smooth road section;

[0030] Fitting the multiple slopes to obtain the slope corresponding to the smooth road section;

[0031] Calculating a plurality of third widths according to the laser radar point cloud data or ultrasonic data corresponding to the smooth road section;

[0032] The multiple third widths are fitted to obtain the width corresponding to the smooth road section.

[0033] In a second aspect, an embodiment of the present application provides a method for processing a parking lot map, which is applied to a vehicle, and the method includes:

[0034] Acquire mapping data, the mapping data including wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, the IMU data including acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data including the ramp entrance, the laser radar point cloud data or ultrasonic data including the distance between the wall and the vehicle, and the z-axis direction is a direction perpendicular to the road surface where the vehicle is located;

[0035] The mapping data is sent to a server.

[0036] In a specific implementation, the obtaining of mapping data includes:

[0037] Acquiring the wheel speed pulse data through a wheel speed pulse sensor;

[0038] Acquire the IMU data through an IMU sensor;

[0039] Acquiring the visual perception data through a vehicle controller;

[0040] Acquiring the steering wheel angle through an angle sensor;

[0041] Acquire the laser radar point cloud data according to the laser radar;

[0042] The ultrasonic data is acquired by an ultrasonic sensor.

[0043] In a third aspect, an embodiment of the present application provides a parking lot map processing device, including:

[0044] A receiving module, used to receive mapping data sent by multiple vehicles, wherein the mapping data includes wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, wherein the IMU data includes acceleration, pitch angle velocity and pitch angle velocity in the z-axis direction, the visual perception data includes a ramp entrance, and the laser radar point cloud data or ultrasonic data includes a distance between a wall and a vehicle, wherein the z-axis direction is a direction perpendicular to the road surface where the vehicle is located;

[0045] A processing module is used to generate ramps and walls in a preset map according to the mapping data.

[0046] In a specific implementation, the processing module is specifically used to:

[0047] Generate driving routes corresponding to all vehicles according to the wheel speed pulse data and the IMU data;

[0048] For each driving route corresponding to the vehicle, determining the starting position and the ending position of the ramp in the driving route according to the IMU data and the visual perception data corresponding to the vehicle, and obtaining at least one ramp route;

[0049] For each ramp route, the ramp route is divided into an entry or exit ramp section, a turning section and a smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle;

[0050] According to the IMU data, laser radar point cloud data or ultrasonic data and steering wheel angle corresponding to the vehicle, the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are obtained;

[0051] Fitting the slope and width corresponding to the slope section entering or exiting the slope, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the slope route corresponding to all vehicles to obtain the fitted slope, width and curvature;

[0052] The ramp and the wall are generated on the map according to the fitted slope, width and curvature.

[0053] In a specific implementation, the processing module is further used to:

[0054] Selecting a section corresponding to an upward pitch angular velocity greater than a preset first angular velocity or a downward pitch angular velocity less than a preset second angular velocity in the IMU data from the ramp route, and determining it as a pitch section;

[0055] Determine the road section in the pitch section whose road section length is greater than a preset length as the road section for entering or exiting the ramp;

[0056] Determine the section of the slope route where the steering wheel angle is greater than a preset angle as a turning section;

[0057] The sections of the ramp route except the ramp entry or exit section and the turning section are determined as smooth sections.

[0058] In a specific implementation, the processing module is further used to:

[0059] Integrate the upward pitch angular velocity or downward pitch angular velocity in the IMU data corresponding to the entering or exiting ramp section to obtain the slope corresponding to the entering or exiting ramp section;

[0060] Calculating a plurality of first widths according to the laser radar point cloud data or ultrasonic data corresponding to the entering or exiting ramp road section;

[0061] Fitting the multiple first widths to obtain a width corresponding to the entry or exit ramp section;

[0062] Calculate the slope of the turning section according to the acceleration in the z-axis direction in the IMU data corresponding to the turning section;

[0063] Calculating the curvature corresponding to the turning section according to the turning section and the laser radar point cloud data or ultrasonic data corresponding to the turning section;

[0064] Calculating a plurality of second widths according to the laser radar point cloud data or ultrasonic data corresponding to the turning section;

[0065] Fitting the multiple second widths to obtain a width corresponding to the turning section;

[0066] Calculating multiple slopes according to the acceleration in the z-axis direction in the IMU data corresponding to the smooth road section;

[0067] Fitting the multiple slopes to obtain the slope corresponding to the smooth road section;

[0068] Calculating a plurality of third widths according to the laser radar point cloud data or ultrasonic data corresponding to the smooth road section;

[0069] The multiple third widths are fitted to obtain the width corresponding to the smooth road section.

[0070] In a fourth aspect, an embodiment of the present application provides a parking lot map processing device, including:

[0071] An acquisition module is used to acquire mapping data, wherein the mapping data includes wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, wherein the IMU data includes acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data includes a ramp entrance, and the laser radar point cloud data or ultrasonic data includes a distance between a wall and a vehicle, wherein the z-axis direction is a direction perpendicular to the road surface where the processing device of the parking lot map is located;

[0072] The sending module is used to send the mapping data to the server.

[0073] In a specific implementation, the acquisition module is specifically used to:

[0074] Acquiring the wheel speed pulse data through a wheel speed pulse sensor;

[0075] Acquire the IMU data through an IMU sensor;

[0076] Acquiring the visual perception data through a vehicle controller;

[0077] Acquiring the steering wheel angle through an angle sensor;

[0078] Acquire the laser radar point cloud data according to the laser radar;

[0079] The ultrasonic data is acquired by an ultrasonic sensor.

[0080] In a fifth aspect, an embodiment of the present application provides a server, including:

[0081] Processor, memory, communication interface;

[0082] The memory is used to store executable instructions of the processor;

[0083] Wherein, the processor is configured to execute the parking lot map processing method described in any one of the first aspects by executing the executable instructions.

[0084] In a sixth aspect, an embodiment of the present application provides a vehicle, including:

[0085] Processor, memory, communication interface, wheel speed pulse sensor, inertial measurement unit IMU sensor, camera, vehicle controller, angle sensor, lidar, and / or ultrasonic sensor;

[0086] The wheel speed pulse sensor is used to obtain wheel speed pulse data;

[0087] The IMU sensor is used to obtain IMU data;

[0088] The camera is used to obtain video data or image data;

[0089] The vehicle controller is used to obtain visual perception data;

[0090] The angle sensor is used to obtain the steering wheel angle;

[0091] The laser radar is used to obtain laser radar point cloud data;

[0092] The ultrasonic sensor is used for the ultrasonic data.

[0093] The memory is used to store executable instructions of the processor;

[0094] Wherein, the processor is configured to execute the parking lot map processing method described in any one of the second aspects by executing the executable instructions.

[0095] In a seventh aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the parking lot map processing method described in any one of the first aspect to the second aspect is implemented.

[0096] In an eighth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the parking lot map processing method described in any one of the first to second aspects.

[0097] The parking lot map processing method, device, equipment and medium provided in the embodiments of the present application are that multiple vehicles are driving in a parking lot with a ramp, and the vehicles send data obtained by sensors, laser radars, vehicle controllers, etc. to a server. The server generates a driving route based on the mapping data received from multiple vehicles, and then determines the ramp route in the driving route. The ramp route is divided into a ramp section entering or exiting the ramp, a turning section, and a smooth section, and the data of all vehicles in each section is calculated, and then fitting is performed. Based on the fitted data, ramps and walls are generated on the map. In this solution, the server generates ramps and walls on the map based on the mapping data of multiple vehicles, thereby generating a map corresponding to the ramps between parking lots. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0099] Figure 1 A schematic diagram of a ramp with a gentle slope provided in an embodiment of the present application;

[0100] Figure 2 A flowchart of a first embodiment of a method for processing a parking lot map provided in this application;

[0101] Figure 3 A flowchart of a second embodiment of a method for processing a parking lot map provided in this application;

[0102] Figure 4 A flowchart of a third embodiment of a method for processing a parking lot map provided in this application;

[0103] Figure 5a A flowchart of a fourth embodiment of a method for processing a parking lot map provided in this application;

[0104] Figure 5bA schematic diagram of calculating the slope of a turning section provided in an embodiment of the present application;

[0105] Figure 6 A schematic diagram of the structure of a first embodiment of a parking lot map processing device provided by the present application;

[0106] Figure 7 A schematic diagram of the structure of a second embodiment of a parking lot map processing device provided by the present application;

[0107] Figure 8 A schematic diagram of the structure of a server provided for this application;

[0108] Fig. 9 A schematic structural diagram of a vehicle provided for this application. DETAILED DESCRIPTION

[0109] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments made by ordinary technicians in this field under the enlightenment of the embodiments belong to the scope of protection of the present application.

[0110] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0111] With the rapid development of science and technology and the improvement of people's living standards, people have higher and higher requirements for cars, higher and higher safety, and higher and higher intelligence. Therefore, related technologies of unmanned driving and autonomous valet parking have emerged one after another. For autonomous valet parking, a map of the parking lot is necessary data.

[0112] Usually, the construction of parking lot maps is to install sensors on the vehicle, and the driver drives the vehicle in the parking lot and parks it. The driving area is each floor of the parking lot. After the vehicle is parked, the data can be uploaded to the server. The server can obtain the map of each floor of the parking lot based on the sensor data. At present, there is no solution that can generate inter-floor ramps on the map.

[0113] In view of the problems existing in the prior art, the inventors found in the process of studying the processing method of the parking lot map that in the process of establishing a parking lot, it is necessary to build it according to relevant design specifications. The entrances and exits can use straight ramps, curved ramps, and straight and curved combination ramps. For example, the minimum clear width of the ramp can be as shown in Table 1:

[0114] Table 1

[0115]

[0116] Exemplarily, the maximum longitudinal slope of the ramp may be as shown in Table 2:

[0117] Table 2

[0118]

[0119] In addition, a gentle slope should be set in the ramp, for example, Figure 1 A schematic diagram of a ramp with a gentle slope provided in an embodiment of the present application, such as Figure 1 As shown, the left side is a straight gentle slope, and the right side is a curved gentle slope, from the starting point 1 to the end point 2 of the ramp, representing the entire ramp. When the longitudinal slope of the ramp is greater than 10%, a gentle slope section should be set at both the upper and lower ends of the ramp. The horizontal length of the straight gentle slope section should not be less than 3.6m, and the gentle slope gradient should be 1 / 2 of the ramp gradient; the horizontal length of the curved gentle slope section should not be less than 2.4m, and the radius of curvature should not be less than 20m. The center of the gentle slope section is the original starting point or end point of the ramp; the slope and length of the gentle slope for large vehicles should be determined according to the vehicle type.

[0120] Therefore, according to relevant specifications, ramps can be divided into sections for entering or exiting the ramp, turning sections, and flat sections.

[0121] When it is necessary to construct a map of the ramp in the parking lot, multiple vehicles can be used to drive in the parking lot with a ramp, and when driving on the ramp, the vehicle is equipped with a wheel speed pulse sensor, an inertial measurement unit (IMU) sensor, a camera, a vehicle controller, an angle sensor, a laser radar, and / or an ultrasonic sensor. After the vehicle drives in the parking lot, the data obtained by the above-mentioned device is sent to the server. The server generates a driving route based on the received mapping data, determines the ramp route from it, and divides the lane route into a ramp section, a turning section, and a smooth section. Ramps and walls are generated according to the data corresponding to each section. Based on the above-mentioned inventive concept, a processing scheme for the parking lot map in this application is designed.

[0122] Exemplarily, an application scenario of the parking lot map processing method provided in an embodiment of the present application is described below. The application scenario may include: multiple vehicles, a parking lot, ramps and walls in the parking lot, and a server.

[0123] Exemplarily, in this application scenario, the vehicle is equipped with wheel speed pulse sensors, IMU sensors, cameras, vehicle controllers, angle sensors, laser radars and ultrasonic sensors. When the vehicle is driving and parking in the parking lot, the data corresponding to the sensors can be obtained through the above sensors. The video obtained by the camera is processed by the vehicle controller to obtain visual perception data. The laser radar point cloud data can be obtained through the laser radar. The IMU data includes the acceleration, the pitch angle velocity and the pitch angle velocity in the z-axis direction. The visual perception data includes the ramp entrance. The laser radar point cloud data or ultrasonic data includes the distance between the wall and the vehicle. Then the vehicle sends the mapping data to the server. The mapping data includes wheel speed pulse data, IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data. The z-axis direction is the direction perpendicular to the road surface where the vehicle is located.

[0124] It should be noted that the IMU data includes three-dimensional acceleration, namely the x-axis, y-axis and z-axis. The three axes are perpendicular to each other. When the vehicle is driving, the plane formed by the x-axis and y-axis is parallel to the road surface where the vehicle is located, and the z-axis direction is perpendicular to the road surface where the vehicle is located.

[0125] After receiving the mapping data sent by multiple vehicles, the server generates the driving routes corresponding to all vehicles based on the wheel speed pulse data and IMU data. For each vehicle's driving route, the ramp route in the driving route is determined based on the IMU data and visual perception data. The ramp route is then divided into the entry or exit ramp section, the turning section and the smooth section based on the wheel speed pulse data, IMU data and steering wheel angle. Then, the slope and width corresponding to the entry or exit ramp section and the smooth section, as well as the slope, width and curvature corresponding to the turning section are obtained based on the IMU data, the laser radar point cloud data or the ultrasonic data and the steering wheel angle. The slope and width corresponding to the entry or exit ramp section and the smooth section, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the ramp routes corresponding to all vehicles are fitted, and the ramps and walls are generated on the map based on the fitted data, so that the ramps and walls corresponding to the ramp routes are generated on the map.

[0126] It should be noted that the above scenario is only an illustration of an application scenario provided by an embodiment of the present application. The embodiment of the present application does not limit the actual form of the various devices included in the scenario, but limits the interaction method between the devices. In the specific application of the solution, it can be set according to actual needs.

[0127] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0128] Figure 2 A flowchart of a first embodiment of a method for processing a parking lot map provided in this application is shown in FIG. Figure 2 As shown, the parking lot map processing method specifically includes the following steps:

[0129] S201: Acquire mapping data.

[0130] S202: Sending the mapping data to the server.

[0131] In order to realize automatic parking of vehicles in parking lots, it is necessary to build a map of parking lots, which includes ramp parts and map parts of each floor.

[0132] In the above steps, the ramp part of the map needs to be constructed based on data, so the vehicle needs to obtain data. Sensors, vehicle controllers, lidars, cameras, etc. are installed on the vehicle. When the vehicle is driving in a parking lot with a ramp and needs to pass through the ramp during driving, the vehicle can obtain mapping data based on sensors, lidars and vehicle controllers. The mapping data includes wheel speed pulse data, IMU data, visual perception data, steering wheel angle, lidar point cloud data or ultrasonic data. IMU data includes acceleration, pitch angle velocity and pitch angle velocity in the z-axis direction. Visual perception data includes the ramp entrance. Lidar point cloud data or ultrasonic data includes the distance between the wall and the vehicle. The z-axis direction is perpendicular to the road surface where the vehicle is located. The vehicle then sends the mapping data to the server so that the server can subsequently construct a map of the ramp part of the parking lot based on the mapping data.

[0133] S203: receiving mapping data sent by multiple vehicles.

[0134] S204: Generate ramps and walls in a preset map according to the mapping data.

[0135] In the above steps, after multiple vehicles send mapping data to the server, the server can receive the mapping data sent by multiple vehicles. The mapping data includes wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, lidar point cloud data or ultrasonic data. The IMU data includes acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction. The visual perception data includes the ramp entrance. The lidar point cloud data or ultrasonic data includes the distance between the wall and the vehicle. The z-axis direction is the direction perpendicular to the road surface where the vehicle is located.

[0136] The driving route of each vehicle is obtained based on the wheel speed pulse data and IMU data in the mapping data. The ramp route is determined from the driving route of each vehicle based on the IMU data and visual perception data corresponding to each vehicle in the mapping data. The ramp route is divided based on the wheel speed pulse data, IMU data and steering wheel angle corresponding to each vehicle in the mapping data. Then, the data corresponding to the divided road section is determined based on the IMU data, laser radar point cloud data or ultrasonic data and steering wheel angle corresponding to each vehicle in the mapping data. Then, ramps and walls can be generated on the map based on the data.

[0137] It should be noted that the preset map is set by the staff before the implementation of this solution, and is used to generate ramps and walls on the preset map. The preset map can be a blank map or a map with each floor in the parking lot. The embodiment of this application does not limit the preset map, and it can be set according to actual conditions.

[0138] In the method for processing a parking lot map provided in this embodiment, the vehicle obtains mapping data through sensors, laser radars, and vehicle controllers, and then sends the mapping data to a server. The server generates ramps and walls on the map based on the mapping data. Compared with the prior art that can only obtain a map of each layer, this solution can generate ramps and walls between layers on the map, thereby generating a map corresponding to the ramps between layers of the parking lot.

[0139] The following is a description of the process by which a vehicle acquires mapping data provided in an embodiment of the present application.

[0140] Map building needs to be based on the mapping data obtained by the vehicle, and wheel speed pulse sensors, IMU sensors, cameras, vehicle controllers, angle sensors, lidars, and / or ultrasonic sensors need to be installed on the vehicle.

[0141] The vehicle obtains wheel speed pulse data through the wheel speed pulse sensor; obtains IMU data through the IMU sensor; obtains visual perception data through the vehicle controller; obtains steering wheel angle through the angle sensor; obtains lidar point cloud data based on the lidar; and obtains ultrasonic data through the ultrasonic sensor.

[0142] Specifically, the wheel speed pulse data includes the rotation speed of the four wheels of the vehicle, the IMU data includes the acceleration and angular velocity of the vehicle in three dimensions, and the lidar point cloud data or ultrasonic data includes the distance between the wall and the vehicle. The vehicle is equipped with a camera, and the acquired video or image is processed by the vehicle controller to obtain visual perception data, which includes the ramp entrance.

[0143] It should be noted that the vehicle controller may generate visual perception data based on the acquired video or image by inputting the acquired image into an image recognition neural network model, or by first extracting frames from the acquired video and then inputting the frames into the image recognition neural network model. The embodiment of the present application does not limit the manner in which the vehicle controller generates visual perception data based on the acquired video or image, and the method may be selected according to actual conditions.

[0144] The parking lot map processing method provided in this embodiment obtains corresponding data through sensors, obtains lidar point cloud data based on lidar, obtains static identification data based on a vehicle controller, and constructs a map corresponding to the ramp in the parking lot based on these data, thereby effectively improving the accuracy of the constructed map.

[0145] Figure 3 The flowchart of the second embodiment of the method for processing a parking lot map provided in this application is as follows: Figure 3 As shown, based on the above embodiment, step S104 in embodiment 1 can be implemented by the following steps:

[0146] S301: Generate driving routes corresponding to all vehicles based on wheel speed pulse data and IMU data.

[0147] In this step, after receiving the mapping data sent by multiple vehicles, the server generates the corresponding driving routes for all vehicles based on the pulse data and IMU data contained therein.

[0148] Specifically, since the wheel speed pulse data includes the rotation speed of the vehicle's four wheels, and the IMU data includes the vehicle's acceleration in three dimensions: front and back, left and right, and up and down, as well as the angular velocity in three dimensions, the corresponding driving routes of all vehicles can be generated based on the pulse data and IMU data, combined with the vehicle's initial position.

[0149] S302: For each driving route corresponding to the vehicle, determine the starting position and the ending position of the ramp in the driving route according to the IMU data and the visual perception data corresponding to the vehicle, and obtain at least one ramp route.

[0150] In this step, after the server generates the driving routes corresponding to all vehicles, for each driving route corresponding to the vehicle, the starting position and ending position of the ramp in the driving route are determined according to the IMU data and visual perception data corresponding to the vehicle. Since the visual perception data includes the ramp entrance, the position corresponding to the ramp entrance in the visual perception data is found in the driving route, and combined with the change of the upward angular velocity or the downward angular velocity from 0 in the IMU data, the starting position of the ramp can be determined. Starting from the starting position, if the upward angular velocity or the downward angular velocity changes from 0 again, this position can be determined as the ending position of the ramp. In this way, at least one ramp route can be obtained.

[0151] It should be noted that the pitch angle velocity or the pitch angle velocity changes from 0, and the magnitude of the change must exceed the preset magnitude. The preset magnitude is set by the staff before the implementation of this solution, and is used to determine the starting position and the ending position of the ramp in the driving route. The embodiment of this application does not limit the preset magnitude, and it can be set according to actual conditions.

[0152] Exemplarily, the parking lot has two floors. Driving from the first floor to the second floor requires a first uphill drive, a horizontal drive, and a second uphill drive. Thus, there are two slope routes, namely, the route corresponding to the first uphill drive and the route corresponding to the second uphill drive.

[0153] It should be noted that the above example is only an illustration of a slope route. The embodiment of the present application does not limit the number of parking floors, inter-floor structure, etc. of the parking lot, which can be determined according to actual conditions.

[0154] S303: For each ramp route, the ramp route is divided into an entry or exit ramp section, a turning section and a smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle.

[0155] In this step, after the server obtains the ramp route, since in reality the ramp will include sections entering or exiting the ramp, turning sections, and sections where the vehicle body is relatively stable, it is necessary to determine the section entering or exiting the ramp in the off-ramp route based on the wheel speed pulse data and IMU data corresponding to the vehicle; determine the turning section in the off-ramp route based on the steering wheel angle; and the remaining sections in the ramp route are stable sections.

[0156] S304: According to the IMU data, lidar point cloud data or ultrasonic data and steering wheel angle corresponding to the vehicle, the slope and width corresponding to the ramp section, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are obtained.

[0157] In this step, after the server divides the ramp route into an entry or exit ramp section, a turning section and a flat section, in order to generate ramps and walls, it is necessary to calculate the slope, width in each section, and the curvature of the turning section. The slope and width corresponding to the entry or exit ramp section and the flat section can be calculated based on IMU data, lidar point cloud data or ultrasonic data, and the slope, width and curvature corresponding to the turning section can be calculated based on IMU data, lidar point cloud data or ultrasonic data and the steering wheel angle.

[0158] S305: Fitting the slope and width corresponding to the ramp section entering or exiting the ramp, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the ramp route corresponding to all vehicles to obtain the fitted slope, width and curvature.

[0159] In this step, after the server obtains the slope and width corresponding to the entering or exiting ramp section, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the ramp route corresponding to each vehicle, a fitting operation is required due to the large amount of data to obtain the fitted slope and width corresponding to the entering or exiting ramp section, the fitted slope, width and curvature corresponding to the turning section, and the fitted slope and width corresponding to the smooth section.

[0160] Specifically, for each smooth road section, there is only one slope and one width calculated based on the data of one vehicle, so the number of vehicles is the same as the number of slopes and widths corresponding to each smooth road section; for each smooth road section, all corresponding slopes and widths are fitted.

[0161] Exemplarily, the least squares fitting method can be used for fitting a smooth section. It can also be fitted by combining the RANSAC algorithm with the least squares fitting method. Taking the slope as an example, a part of the slope is taken out from all the slopes corresponding to a smooth section for least squares fitting to obtain the fitted slope. The remaining slope is subtracted from the fitted slope, and all the differences are added to obtain the error. Repeating this step can obtain multiple errors, from which the minimum error is selected, and the fitted slope corresponding to the minimum error is used as the fitted slope of the smooth section. The embodiment of the present application does not limit the method for fitting a smooth section, and can be selected according to actual conditions.

[0162] For each entry or exit ramp section, the slope calculated based on the data of a vehicle is the slope corresponding to each position in this section, and there is only one width. The fitting of the width is similar to that of the flat section, and will not be repeated here.

[0163] For example, the fitting method for the slope of the entry or exit ramp section can be: for the slope calculated according to the data of each vehicle, select the slopes corresponding to multiple fixed positions. In this way, the entry or exit ramp section will correspond to multiple slopes at each fixed position, and then perform the least squares fitting to obtain the fitted slope corresponding to the fixed position. Then perform the least squares fitting or polynomial fitting on the fitted slopes corresponding to all fixed positions to obtain the fitted slope corresponding to each position in the entry or exit ramp section.

[0164] For example, the fitting method for the slope of the road section entering or exiting the ramp can also be: for the slope calculated according to the data of each vehicle, select the slopes corresponding to multiple fixed positions. In this way, the road section entering or exiting the ramp will correspond to multiple slopes at each fixed position, and then the fitting method similar to the RANSAC algorithm and the least squares fitting method used in the smooth road section can be used to obtain the fitted slope corresponding to the fixed position. Then, the fitted slopes corresponding to all fixed positions are fitted by least squares fitting or polynomial fitting, and the fitted slope corresponding to each position in the road section entering or exiting the ramp can be obtained.

[0165] It should be noted that the embodiment of the present application does not limit the fitting method of the slope when entering or exiting a slope section, and can be selected according to actual conditions.

[0166] For each turning section, the slope calculated based on the data of one vehicle is the slope corresponding to each position in this section, the curvature is the curvature corresponding to each position in this section, and there is only one width. The fitting of the width is similar to the fitting method of the width in a smooth section, which will not be repeated here. The fitting of the slope and curvature is similar to the fitting method of the slope in a ramp section entering or exiting, which will not be repeated here.

[0167] S306: Generate ramps and walls on the map according to the fitted slope, width and curvature.

[0168] In this step, after the server obtains the fitted slope, width and curvature, for a smooth section, the server generates the ramp and wall corresponding to the smooth section on the map according to the fitted width, the fitted slope and the length corresponding to the smooth section; for an entry or exit ramp section, the server generates the ramp and wall corresponding to the entry or exit ramp section on the map according to the fitted width and the fitted slope corresponding to each position; for a turning section, the server generates the ramp and wall corresponding to the turning section on the map according to the fitted width, the fitted slope corresponding to each position and the fitted curvature corresponding to each position; in this way, the complete slope and wall can be generated on the map.

[0169] The parking lot map processing method provided in this embodiment generates the width, slope and curvature of the ramp section, turning section and flat section for entering or exiting the vehicle according to the mapping data corresponding to each vehicle. Then, fitting is performed, and ramps and walls are generated on the map according to the fitted width, slope and curvature, so as to realize the generation of the map corresponding to the ramp between parking lots.

[0170] Figure 4 The flowchart of the third embodiment of the method for processing a parking lot map provided in this application is as follows: Figure 4 As shown, based on the above embodiment, step S303 in embodiment 2 can be implemented by the following steps:

[0171] S401: Select a section corresponding to an upward pitch angular velocity greater than a preset first angular velocity or a downward pitch angular velocity less than a preset second angular velocity in the IMU data from the slope route, and determine it as a pitch section.

[0172] In this step, after the server obtains the ramp route, it needs to divide the ramp route, and select the road section corresponding to the upward angular velocity greater than the preset first angular velocity or the downward pitch angular velocity less than the preset second angular velocity in the IMU data from the ramp route, and determine it as the pitching section. When the upward angular velocity or the downward pitch angular velocity value in the IMU data is not 0, it means that the vehicle body is pitching up or down, and the corresponding road surface has a slope.

[0173] It should be noted that the preset first angular velocity and the preset second angular velocity are set by the staff before the implementation of this solution, and are used to determine the pitch section. The preset first angular velocity can be 5 degrees per second, or 3 degrees per second. The preset second angular velocity can be -5 degrees per second, or -4 degrees per second. The embodiment of the present application does not limit the preset first angular velocity and the preset second angular velocity, and can be set according to actual conditions.

[0174] S402: Determine a section of the pitch section whose length is greater than a preset length as a section for entering or exiting a slope.

[0175] In this step, after the server determines the pitch section, since the sections that meet the pitch section conditions include not only the actual entry or exit ramp sections, but also the sections corresponding to the speed bumps in the ramp, in order to determine the entry or exit ramp sections, the sections in the pitch section whose length is greater than the preset length are determined as the entry or exit ramp sections.

[0176] It should be noted that the preset length is set by the staff before the implementation of this solution, and is used to determine the entry or exit ramp section. The preset length can be 5 meters or 2 meters. The embodiment of this application does not limit the preset length and can be set according to actual conditions.

[0177] S403: Determine a section of the slope route where the steering wheel angle is greater than a preset angle as a turning section.

[0178] In this step, after obtaining the slope route, the server determines the section in the slope route where the steering wheel angle is greater than a preset angle as a turning section.

[0179] Optionally, after determining the section in the off-slope route where the steering wheel angle is greater than a preset angle, the section where the length is greater than a preset length may also be determined as a turning section.

[0180] It should be noted that the preset angle and preset length are set by the staff before the implementation of this solution to determine the turning section. The preset angle can be 90 degrees or 180 degrees. The preset length can be 5 meters or 2 meters. The embodiment of the present application does not limit the preset angle and preset length, and can be set according to actual conditions.

[0181] It should be noted that the execution order of steps S401 and S402 for determining the section of entering or exiting a slope and step S403 for determining a turning section may be to execute steps S401 and S402 first and then execute step S403; or to execute step S403 first and then execute step S401 and S402; or the steps for determining the section of entering or exiting a slope and the steps for determining a turning section may be executed simultaneously. The embodiment of the present application does not limit the execution order of the steps for determining the section of entering or exiting a slope and the steps for determining a turning section, and the order may be selected according to actual conditions.

[0182] S404: Determine the sections of the slope route except the sections for entering or exiting the slope and the turning sections as smooth sections.

[0183] In this step, after determining the entry or exit ramp section and the turning section, the server determines the sections of the ramp route except the entry or exit ramp section and the turning section as smooth sections.

[0184] The parking lot map processing method provided in this embodiment divides the ramp route into the ramp section, the turning section and the smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle. When the ramp and wall are generated on the map, they are generated according to different sections, which effectively improves the accuracy of the generated ramp and wall.

[0185] Figure 5a A flowchart of a fourth embodiment of a parking lot map processing method provided in this application is shown in FIG. Figure 5a As shown, based on the above embodiment, step S304 in embodiment 2 can be implemented by the following steps:

[0186] S501: Integrate the upward pitch angular velocity or downward pitch angular velocity in the IMU data corresponding to the ramp section being entered or driven out, and obtain the slope corresponding to the ramp section being entered or driven out.

[0187] After the server divides the ramp route into an entry or exit ramp section, a turning section and a flat section, it is necessary to calculate the slope and width corresponding to the entry or exit ramp section.

[0188] In this step, since the pitch angular velocity or the pitch angular velocity in the IMU data will change from 0 when the vehicle enters or exits a slope section, the curve formed by the pitch angular velocity or the pitch angular velocity can be integrated to obtain the slope corresponding to each moment when the vehicle enters or exits the slope section. Combined with the wheel speed pulse data and the IMU data, the position corresponding to each moment can be obtained, so that the slope corresponding to each position when entering or exiting the slope section can be obtained.

[0189] S502: Calculate a plurality of first widths according to the laser radar point cloud data or ultrasonic data corresponding to the ramp section being entered or driven out.

[0190] In this step, after dividing the ramp route, the server calculates multiple first widths for the sections entering or exiting the ramp according to the laser radar point cloud data or ultrasonic data corresponding to the sections entering or exiting the ramp.

[0191] Specifically, since the laser radar point cloud data or ultrasonic data includes the distance between the wall and the vehicle, the width of the ramp can be obtained. When entering or exiting a ramp section, there are multiple laser radar point cloud data or ultrasonic data, so multiple first widths can be obtained.

[0192] Optionally, the visual perception data also includes vehicles. According to the time when the vehicle in the visual perception data enters or exits a slope section, the lidar point cloud data or ultrasonic data within that time period may be removed, and the remaining lidar point cloud data or ultrasonic data may be used to calculate multiple first widths.

[0193] S503: Fitting the multiple first widths to obtain a width corresponding to the road section entering or exiting the ramp.

[0194] In this step, after obtaining the multiple first widths, the server performs fitting on the multiple first widths to obtain the width corresponding to the road section entering or exiting the ramp.

[0195] Exemplarily, the method for fitting multiple first widths may be to perform least squares fitting, or to perform fitting by combining the RANSAC algorithm with least squares fitting, taking out some first widths from all first widths for least squares fitting, obtaining the fitted first width, using the remaining first width and the fitted first width as the difference, and adding all the differences to obtain the error; repeating this step, multiple errors may be obtained, from which the minimum error is selected, and the fitted first width corresponding to the minimum error is used as the width corresponding to the road section entering or exiting the ramp. The embodiment of the present application does not limit the method for fitting multiple first widths, and may be selected according to actual conditions.

[0196] It should be noted that the execution order of step S501 of the server calculating the slope corresponding to the entry or exit ramp road section and step S502 and step 503 of calculating the width corresponding to the entry or exit ramp road section can be to first execute the step of calculating the slope corresponding to the entry or exit ramp road section, and then execute the step of calculating the width corresponding to the entry or exit ramp road section; it can also be to first execute the step of calculating the width corresponding to the entry or exit ramp road section, and then execute the step of calculating the slope corresponding to the entry or exit ramp road section; it can also be that the step of calculating the width corresponding to the entry or exit ramp road section and the step of calculating the slope corresponding to the entry or exit ramp road section are executed simultaneously. The embodiment of the present application does not limit the execution order of the step of calculating the width corresponding to the entry or exit ramp road section and the step of calculating the slope corresponding to the entry or exit ramp road section, and can be selected according to actual conditions.

[0197] S504: Calculate the slope corresponding to the turning section according to the acceleration in the z-axis direction in the IMU data corresponding to the turning section.

[0198] After the server divides the ramp route into an entry or exit ramp section, a turning section and a flat section, it is necessary to calculate the slope, width and curvature corresponding to the turning section.

[0199] In this step, since the acceleration in the z-axis direction in the IMU data is not always 0 when the vehicle is traveling on a slope, the slope corresponding to each position in the turning section can be calculated based on the acceleration in the z-axis direction and the gravity acceleration corresponding to each position in the turning section.

[0200] For example, Figure 5b A schematic diagram of calculating the slope of a turning section provided in an embodiment of the present application; Figure 5b As shown, the slope of the road section is equal to the angle between the gravitational acceleration and the z-axis. The component of the gravitational acceleration on the z-axis can be obtained according to the IMU data, that is, the acceleration in the z-axis direction in the IMU data. Combined with the value of the gravitational acceleration, the angle between the gravitational acceleration and the z-axis can be obtained, and then the slope can be obtained.

[0201] S505: Calculate the curvature corresponding to the turning section according to the turning section and the laser radar point cloud data or ultrasonic data corresponding to the turning section.

[0202] In this step, after the server divides the slope route, for the turning section, the turning section is the driving route of the vehicle on this section. Since the laser radar point cloud data or ultrasonic data includes the distance between the left wall and the vehicle and the distance between the right wall and the vehicle, the position data of the walls on both sides can be obtained according to the turning section and the laser radar point cloud data or ultrasonic data corresponding to the turning section. There are multiple position data of each side wall. For the position data of each side wall, the wall data is fitted to obtain a fitting curve, and then according to the function corresponding to the fitting curve, the curvature corresponding to each position of the side wall can be obtained. Since each position in the turning section has a corresponding relationship with each position of the two side walls, the wall corresponding to each position of the two side walls constitutes the curvature corresponding to each position in the turning section.

[0203] S506: Calculate a plurality of second widths according to the laser radar point cloud data or ultrasonic data corresponding to the turning section.

[0204] S507: Fit the multiple second widths to obtain a width corresponding to the turning section.

[0205] In the above steps, after the server divides the slope route, it is necessary to calculate the corresponding width for the turning section.

[0206] It should be noted that steps S506 to S507 are similar to steps S501 to S502 and will not be described in detail here.

[0207] It should be noted that the execution order of step S504 in which the server calculates the slope corresponding to the turning section, step S505 in which the server calculates the curvature corresponding to the turning section, step S506 in which the server calculates the width corresponding to the turning section, and step S507 may be to first execute the step of calculating the slope, then execute the step of calculating the curvature, and finally execute the step of calculating the width; or to first execute the step of calculating the width, then execute the step of calculating the slope, and finally execute the step of calculating the curvature; or to execute the step of calculating the width, the step of calculating the slope, and the step of calculating the curvature simultaneously. The embodiment of the present application does not limit the execution order of the step of calculating the slope corresponding to the turning section, the step of calculating the curvature corresponding to the turning section, and the step of calculating the width corresponding to the turning section by the server, and the order may be selected according to the actual situation.

[0208] S508: Calculate multiple slopes according to the acceleration in the z-axis direction in the IMU data corresponding to the smooth road section.

[0209] After the server divides the ramp route into the ramp section, the turning section and the flat section, it is necessary to calculate the slope and width corresponding to the flat section.

[0210] In this step, since the acceleration in the z-axis direction in the IMU data is not always 0 when the vehicle is driving on a slope, the slope corresponding to each position in the smooth section can be calculated based on the acceleration in the z-axis direction and the value of gravity acceleration corresponding to each position in the smooth section. Multiple slopes can be randomly selected.

[0211] Optionally, the visual perception data also includes speed bumps. According to the time when the speed bumps in the visual perception data are in the smooth road section, and the time corresponding to the acceleration or deceleration obtained according to the three-dimensional acceleration in the IMU data, the IMU data within the above two time periods are removed, and the acceleration in the z-axis direction in the remaining MU data is used to calculate multiple slopes.

[0212] S509: Fitting multiple slopes to obtain the slope corresponding to the smooth road section.

[0213] In this step, after obtaining multiple slopes, the server fits the multiple slopes to obtain the slope corresponding to the smooth road section.

[0214] Exemplarily, the method for fitting multiple slopes can be to perform least squares fitting, or to fit by combining the RANSAC algorithm with least squares fitting, taking out some slopes from all slopes for least squares fitting, obtaining the fitted slope, using the remaining slope and the fitted slope as the difference, and adding all the differences to obtain the error; repeating this step, multiple errors can be obtained, the minimum error is selected, and the fitted slope corresponding to the minimum error is used as the slope corresponding to the smooth road section. The embodiment of the present application does not limit the method for fitting multiple slopes, and can be selected according to actual conditions.

[0215] S510: Calculate a plurality of third widths according to the laser radar point cloud data or ultrasonic data corresponding to the smooth road section.

[0216] S511: Fit multiple third widths to obtain a width corresponding to a smooth road section.

[0217] In the above steps, after the server divides the slope route, it is necessary to calculate the corresponding width for the smooth section.

[0218] It should be noted that steps S510 to S511 are similar to steps S501 to S502 and will not be described in detail here.

[0219] It should be noted that the execution order of steps S508 and 509 for the server to calculate the slope corresponding to the smooth section and steps S510 and 511 for calculating the width corresponding to the smooth section can be to first execute the step of calculating the slope corresponding to the smooth section, and then execute the step of calculating the width corresponding to the smooth section; it can also be to first execute the step of calculating the width corresponding to the smooth section, and then execute the step of calculating the slope corresponding to the smooth section; it can also be that the step of calculating the width corresponding to the smooth section and the step of calculating the slope corresponding to the smooth section are executed simultaneously. The embodiment of the present application does not limit the execution order of the step of calculating the width corresponding to the smooth section and the step of calculating the slope corresponding to the smooth section, and can be selected according to actual conditions.

[0220] It should be noted that the execution order of steps S501 to S503 for the server to calculate the data of entering or exiting a slope section, steps S504 to S507 for calculating the data of a turning section, and steps S508 to S511 for calculating the data of a flat section may be to first execute the step of calculating the data of entering or exiting a slope section, then execute the step of calculating the data of a turning section, and finally execute the step of calculating the data of a flat section.

[0221] Alternatively, the step of calculating the data of the flat road section may be performed first, followed by the step of calculating the data of the road section entering or exiting a slope, and finally the step of calculating the data of the turning road section.

[0222] Alternatively, the steps of calculating the data of entering or exiting a ramp section, calculating the data of a turning section, and calculating the data of a smooth section may be executed simultaneously. The embodiment of the present application does not limit the execution order of the steps of calculating the data of entering or exiting a ramp section, calculating the data of a turning section, and calculating the data of a smooth section by the server, and the execution order may be selected according to actual conditions.

[0223] The parking lot map processing method provided in this embodiment obtains the curvature corresponding to the entering or exiting ramp section, turning section, smooth section and turning section based on the IMU data, lidar point cloud data or ultrasonic data corresponding to the vehicle and the steering wheel angle, and generates ramps and walls based on these data, effectively improving the accuracy of generating ramps and walls.

[0224] The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0225] Figure 6 This is a schematic diagram of the structure of the first embodiment of the parking lot map processing device provided by this application; Figure 6 As shown, the parking lot map processing device 60 includes:

[0226] A receiving module 61 is used to receive mapping data sent by multiple vehicles, wherein the mapping data includes wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, wherein the IMU data includes acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data includes a ramp entrance, and the laser radar point cloud data or ultrasonic data includes a distance between a wall and a vehicle, wherein the z-axis direction is a direction perpendicular to the road surface where the vehicle is located;

[0227] The processing module 62 is used to generate ramps and walls in a preset map according to the mapping data.

[0228] Furthermore, the processing module 62 is specifically configured to:

[0229] Generate driving routes corresponding to all vehicles according to the wheel speed pulse data and the IMU data;

[0230] For each driving route corresponding to the vehicle, determining the starting position and the ending position of the ramp in the driving route according to the IMU data and the visual perception data corresponding to the vehicle, and obtaining at least one ramp route;

[0231] For each ramp route, the ramp route is divided into an entry or exit ramp section, a turning section and a smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle;

[0232] According to the IMU data, laser radar point cloud data or ultrasonic data and steering wheel angle corresponding to the vehicle, the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are obtained;

[0233] Fitting the slope and width corresponding to the slope section entering or exiting the slope, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the slope route corresponding to all vehicles to obtain the fitted slope, width and curvature;

[0234] The ramp and the wall are generated on the map according to the fitted slope, width and curvature.

[0235] Furthermore, the processing module 62 is further configured to:

[0236] Selecting a section corresponding to an upward pitch angular velocity greater than a preset first angular velocity or a downward pitch angular velocity less than a preset second angular velocity in the IMU data from the ramp route, and determining it as a pitch section;

[0237] Determine the road section in the pitch section whose road section length is greater than a preset length as the road section for entering or exiting the ramp;

[0238] Determine the section of the slope route where the steering wheel angle is greater than a preset angle as a turning section;

[0239] The sections of the ramp route except the ramp entry or exit section and the turning section are determined as smooth sections.

[0240] Furthermore, the processing module 62 is further configured to:

[0241] Integrate the upward pitch angular velocity or downward pitch angular velocity in the IMU data corresponding to the entering or exiting ramp section to obtain the slope corresponding to the entering or exiting ramp section;

[0242] Calculating a plurality of first widths according to the laser radar point cloud data or ultrasonic data corresponding to the entering or exiting ramp road section;

[0243] Fitting the multiple first widths to obtain a width corresponding to the entry or exit ramp section;

[0244] Calculate the slope of the turning section according to the acceleration in the z-axis direction in the IMU data corresponding to the turning section;

[0245] Calculating the curvature corresponding to the turning section according to the turning section and the laser radar point cloud data or ultrasonic data corresponding to the turning section;

[0246] Calculating a plurality of second widths according to the laser radar point cloud data or ultrasonic data corresponding to the turning section;

[0247] Fitting the multiple second widths to obtain a width corresponding to the turning section;

[0248] Calculating multiple slopes according to the acceleration in the z-axis direction in the IMU data corresponding to the smooth road section;

[0249] Fitting the multiple slopes to obtain the slope corresponding to the smooth road section;

[0250] Calculating a plurality of third widths according to the laser radar point cloud data or ultrasonic data corresponding to the smooth road section;

[0251] The multiple third widths are fitted to obtain the width corresponding to the smooth road section.

[0252] The parking lot map processing device provided in this embodiment is used to execute the technical solution of the server in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0253] Figure 7 This is a schematic diagram of the structure of the second embodiment of the parking lot map processing device provided by this application; Figure 7 As shown, the parking lot map processing device 70 includes:

[0254] An acquisition module 71 is used to acquire mapping data, wherein the mapping data includes wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, wherein the IMU data includes acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data includes a ramp entrance, the laser radar point cloud data or ultrasonic data includes a distance between a wall and a vehicle, and the z-axis direction is a direction perpendicular to the road surface where the processing device of the parking lot map is located;

[0255] The sending module 72 is used to send the mapping data to the server.

[0256] Furthermore, the acquisition module is specifically used to:

[0257] Acquiring the wheel speed pulse data through a wheel speed pulse sensor;

[0258] Acquire the IMU data through an IMU sensor;

[0259] Acquiring the visual perception data through a vehicle controller;

[0260] Acquiring the steering wheel angle through an angle sensor;

[0261] Acquire the laser radar point cloud data according to the laser radar;

[0262] The ultrasonic data is acquired by an ultrasonic sensor.

[0263] The parking lot map processing device provided in this embodiment is used to execute the technical solution of the vehicle in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0264] Figure 8 A schematic diagram of the structure of a server provided in this application. Figure 8 As shown, the server 80 includes:

[0265] Processor 81, memory 82, and communication interface 83;

[0266] The memory 82 is used to store executable instructions of the processor 81;

[0267] The processor 81 is configured to execute the technical solution of the server in any of the aforementioned method embodiments by executing the executable instructions.

[0268] Optionally, the memory 82 can be independent or integrated with the processor 81.

[0269] Optionally, when the memory 82 is a device independent of the processor 81, the server 80 may further include:

[0270] A bus is used to connect the above devices.

[0271] The server is used to execute the technical solution of the server in any of the aforementioned method embodiments, and its implementation principle and technical effect are similar and will not be repeated here.

[0272] Fig. 9 A schematic diagram of the structure of a vehicle provided in this application. Fig. 9 As shown, the vehicle 900 includes:

[0273] Processor 901, memory 902, and communication interface 903, wheel speed pulse sensor 904, IMU sensor 905, camera 906, vehicle controller 907, angle sensor 908, laser radar 909, and / or, ultrasonic sensor 910;

[0274] The wheel speed pulse sensor 904 is used to obtain wheel speed pulse data;

[0275] The IMU sensor 905 is used to obtain IMU data;

[0276] The camera 906 is used to obtain video data or image data;

[0277] The vehicle controller 907 is used to obtain visual perception data according to the video data or the image data;

[0278] The angle sensor 908 is used to obtain the steering wheel angle;

[0279] The laser radar 909 is used to obtain laser radar point cloud data;

[0280] The ultrasonic sensor 910 is used for the ultrasonic data;

[0281] The memory 902 is used to store executable instructions of the processor 901;

[0282] Among them, the processor 901 is configured to execute the technical solution of the vehicle in any of the aforementioned method embodiments by executing the executable instructions.

[0283] Optionally, the memory 902 may be independent or integrated with the processor 901 .

[0284] Optionally, when the memory 902 is a device independent of the processor 901, the vehicle 900 may further include:

[0285] A bus is used to connect the above devices.

[0286] The vehicle is used to execute the technical solution of the vehicle in any of the aforementioned method embodiments, and its implementation principle and technical effects are similar and will not be repeated here.

[0287] An embodiment of the present application also provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the technical solution provided by any of the aforementioned method embodiments is implemented.

[0288] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the technical solution provided by any of the aforementioned method embodiments when executed by a processor.

[0289] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0290] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for processing a parking lot map, characterized in that: Applied to a server, the method comprises: Receive mapping data sent by multiple vehicles, the mapping data including wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, the IMU data including acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data including ramp entrances, the laser radar point cloud data or ultrasonic data including the distance between the wall and the vehicle, and the z-axis direction is a direction perpendicular to the road surface where the vehicle is located; Generate driving routes corresponding to all vehicles according to the wheel speed pulse data and the IMU data; For each driving route corresponding to the vehicle, determining the starting position and the ending position of the ramp in the driving route according to the IMU data and the visual perception data corresponding to the vehicle, and obtaining at least one ramp route; For each ramp route, the ramp route is divided into an entry or exit ramp section, a turning section and a smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle; According to the IMU data, laser radar point cloud data or ultrasonic data and steering wheel angle corresponding to the vehicle, the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are obtained; Fitting the slope and width corresponding to the slope section entering or exiting the slope, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the slope route corresponding to all vehicles to obtain the fitted slope, width and curvature; The ramp and the wall are generated on a preset map according to the fitted slope, width and curvature.

2. The method according to claim 1, characterized in that: The method of dividing the ramp route into a ramp section, a turning section and a smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle includes: Selecting a section corresponding to an upward pitch angular velocity greater than a preset first angular velocity or a downward pitch angular velocity less than a preset second angular velocity in the IMU data from the ramp route, and determining it as a pitch section; Determine the road section in the pitch section whose road section length is greater than a preset length as the road section for entering or exiting the ramp; Determine the section of the slope route where the steering wheel angle is greater than a preset angle as a turning section; The sections of the ramp route except the ramp entry or exit section and the turning section are determined as smooth sections.

3. The method according to claim 1, characterized in that The method of obtaining the slope and width corresponding to the ramp section for entering or exiting the ramp, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section according to the IMU data, the laser radar point cloud data or the ultrasonic data and the steering wheel angle corresponding to the vehicle includes: Integrate the upward pitch angular velocity or downward pitch angular velocity in the IMU data corresponding to the entering or exiting ramp section to obtain the slope corresponding to the entering or exiting ramp section; Calculating a plurality of first widths according to the laser radar point cloud data or ultrasonic data corresponding to the entering or exiting ramp road section; Fitting the multiple first widths to obtain a width corresponding to the entry or exit ramp section; Calculate the slope of the turning section according to the acceleration in the z-axis direction in the IMU data corresponding to the turning section; Calculating the curvature corresponding to the turning section according to the turning section and the laser radar point cloud data or ultrasonic data corresponding to the turning section; Calculating a plurality of second widths according to the laser radar point cloud data or ultrasonic data corresponding to the turning section; Fitting the multiple second widths to obtain a width corresponding to the turning section; calculating multiple slopes according to the acceleration in the z-axis direction in the IMU data corresponding to the smooth section; Fitting the multiple slopes to obtain the slope corresponding to the smooth road section; Calculating a plurality of third widths according to the laser radar point cloud data or ultrasonic data corresponding to the smooth road section; The multiple third widths are fitted to obtain the width corresponding to the smooth road section.

4. A method for processing a parking lot map, characterized in that: Applied to a vehicle, the method comprises: Acquire mapping data, the mapping data including wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, the IMU data including acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data including the ramp entrance, the laser radar point cloud data or ultrasonic data including the distance between the wall and the vehicle, and the z-axis direction is the direction perpendicular to the road surface where the vehicle is located; Sending the mapping data to a server; Wherein, the wheel speed pulse data and the IMU data are used to generate driving routes corresponding to all vehicles; For each driving route corresponding to the vehicle, the IMU data and visual perception data corresponding to the vehicle are used to determine the starting position and the ending position of the ramp in the driving route to obtain at least one ramp route; For each ramp route, the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle are used to divide the ramp route into a ramp entry or exit section, a turning section and a smooth section; The IMU data, laser radar point cloud data or ultrasonic data and steering wheel angle corresponding to the vehicle are used to obtain the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section; The slope and width corresponding to the ramp section entering or exiting the ramp route corresponding to all vehicles, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are used for fitting to obtain the fitted slope, width and curvature; The fitted slope, width and curvature are used to generate the ramp and the wall on a preset map.

5. The method according to claim 4, characterized in that The obtaining of mapping data includes: Acquiring the wheel speed pulse data through a wheel speed pulse sensor; Acquire the IMU data through an IMU sensor; Acquiring the visual perception data through a vehicle controller; Acquiring the steering wheel angle through an angle sensor; Acquire the laser radar point cloud data according to the laser radar; The ultrasonic data is acquired by an ultrasonic sensor.

6. A parking lot map processing device, characterized in that: include: A receiving module, used to receive mapping data sent by multiple vehicles, wherein the mapping data includes wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, wherein the IMU data includes acceleration, pitch angle velocity and pitch angle velocity in the z-axis direction, the visual perception data includes a ramp entrance, and the laser radar point cloud data or ultrasonic data includes a distance between a wall and a vehicle, wherein the z-axis direction is a direction perpendicular to the road surface where the vehicle is located; A processing module, configured to generate driving routes corresponding to all vehicles according to the wheel speed pulse data and the IMU data; for the driving route corresponding to each vehicle, determine the starting position and the ending position of the ramp in the driving route according to the IMU data and the visual perception data corresponding to the vehicle, and obtain at least one ramp route; For each ramp route, the ramp route is divided into an entry or exit ramp section, a turning section and a smooth section according to the wheel speed pulse data, IMU data and steering wheel angle corresponding to the vehicle; According to the IMU data, laser radar point cloud data or ultrasonic data and steering wheel angle corresponding to the vehicle, the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are obtained; The slope and width corresponding to the ramp section entering or exiting the ramp route corresponding to all vehicles, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section are fitted to obtain the fitted slope, width and curvature; based on the fitted slope, width and curvature, the ramp and the wall are generated on the preset map.

7. The device according to claim 6, characterized in that The processing module is further specifically used for: Selecting a section corresponding to an upward pitch angular velocity greater than a preset first angular velocity or a downward pitch angular velocity less than a preset second angular velocity in the IMU data from the ramp route, and determining it as a pitch section; Determine the road section in the pitch section whose road section length is greater than a preset length as the road section for entering or exiting the ramp; Determine the section of the slope route where the steering wheel angle is greater than a preset angle as a turning section; The sections of the ramp route except the ramp entry or exit section and the turning section are determined as smooth sections.

8. The device according to claim 6, characterized in that The processing module is further specifically used for: Integrate the upward pitch angular velocity or downward pitch angular velocity in the IMU data corresponding to the entering or exiting ramp section to obtain the slope corresponding to the entering or exiting ramp section; Calculating a plurality of first widths according to the laser radar point cloud data or ultrasonic data corresponding to the entering or exiting ramp road section; Fitting the multiple first widths to obtain a width corresponding to the entry or exit ramp section; Calculate the slope of the turning section according to the acceleration in the z-axis direction in the IMU data corresponding to the turning section; Calculating the curvature corresponding to the turning section according to the turning section and the laser radar point cloud data or ultrasonic data corresponding to the turning section; Calculating a plurality of second widths according to the laser radar point cloud data or ultrasonic data corresponding to the turning section; Fitting the multiple second widths to obtain a width corresponding to the turning section; Calculating multiple slopes according to the acceleration in the z-axis direction in the IMU data corresponding to the smooth road section; Fitting the multiple slopes to obtain the slope corresponding to the smooth road section; Calculating a plurality of third widths according to the laser radar point cloud data or ultrasonic data corresponding to the smooth road section; The multiple third widths are fitted to obtain the width corresponding to the smooth road section.

9. A parking lot map processing device, characterized in that: include: An acquisition module is used to acquire mapping data, wherein the mapping data includes wheel speed pulse data, inertial measurement unit IMU data, visual perception data, steering wheel angle, laser radar point cloud data or ultrasonic data, wherein the IMU data includes acceleration, pitch angular velocity and pitch angular velocity in the z-axis direction, the visual perception data includes a ramp entrance, and the laser radar point cloud data or ultrasonic data includes a distance between a wall and a vehicle, wherein the z-axis direction is a direction perpendicular to the road surface where the processing device of the parking lot map is located; wherein the wheel speed pulse data and the IMU data are used to generate driving routes corresponding to all vehicles; for the driving route corresponding to each vehicle, the IMU data and visual perception data corresponding to the vehicle are used to determine the starting position and the ending position of the ramp in the driving route to obtain at least one ramp route; for each ramp route, the wheel speed pulse data, the IMU data and the steering wheel angle corresponding to the vehicle are used to divide the ramp route into a ramp section entering or exiting, a turning section and a smooth section; the IMU data, the laser radar point cloud data or the ultrasonic data and the steering wheel angle corresponding to the vehicle are used to obtain the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section; the slope and width corresponding to the ramp section entering or exiting, the slope, width and curvature corresponding to the turning section, and the slope and width corresponding to the smooth section in the ramp routes corresponding to all vehicles are used for fitting to obtain the fitted slope, width and curvature; the fitted slope, width and curvature are used to generate the ramp and the wall on a preset map; The sending module is used to send the mapping data to the server.

10. The device according to claim 9, characterized in that The acquisition module is specifically used for: Acquiring the wheel speed pulse data through a wheel speed pulse sensor; Acquire the IMU data through an IMU sensor; Acquiring the visual perception data through a vehicle controller; Acquiring the steering wheel angle through an angle sensor; Acquire the laser radar point cloud data according to the laser radar; The ultrasonic data is acquired by an ultrasonic sensor.

11. A server, characterized in that: include: Processor, memory, communication interface; The memory is used to store executable instructions of the processor; The processor is configured to execute the parking lot map processing method according to any one of claims 1 to 3 by executing the executable instructions.

12. A vehicle, characterized in that: include: Processor, memory, communication interface, wheel speed pulse sensor, inertial measurement unit IMU sensor, camera, vehicle controller, angle sensor, lidar, and / or ultrasonic sensor; The wheel speed pulse sensor is used to obtain wheel speed pulse data; The IMU sensor is used to obtain IMU data; The camera is used to obtain video data or image data; The vehicle controller is used to obtain visual perception data based on the video data or the image data; The angle sensor is used to obtain the steering wheel angle; The laser radar is used to obtain laser radar point cloud data; The ultrasonic sensor is used for the ultrasonic data; The memory is used to store executable instructions of the processor; Wherein, the processor is configured to execute the parking lot map processing method described in claim 4 or 5 by executing the executable instructions.

13. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the parking lot map processing method according to any one of claims 1 to 5 is implemented.

14. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the parking lot map processing method according to any one of claims 1 to 5 when being executed by a processor.

Images