Parking mapping method and system based on combination of laser and IMU (Inertial Measurement Unit) and vehicle

Abstract

The invention provides a parking mapping method and system based on laser and IMU combination and a vehicle, and the method comprises the steps: obtaining the observation data of a parking space posture in real time based on laser radar observation data; on the basis of IMU odometer data, obtaining prediction data of the attitude of the parking space in real time; constructing a pose optimization objective function by minimizing the difference value between the observation data of the self-parking space pose and the prediction data of the self-parking space pose; on the basis of observation data of the self-parking space attitude and prediction data of the self-parking space attitude, performing optimization solution on the attitude optimization objective function to obtain optimal attitude data; optimizing laser radar observation data according to the obtained optimal pose data to obtain a local sub-graph; and constructing a global map based on the obtained local sub-graphs.

Description

Technical Field

[0001] The present invention belongs to the technical field related to intelligent driving assistance, and in particular relates to a parking mapping method, system and vehicle based on the combination of laser and IMU. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Parking mapping usually refers to the process of building a parking environment map through various sensors (such as cameras, ultrasonic sensors, etc.) in parking scenarios such as parking lots. This map provides key environmental information to the vehicle's automatic parking system, helping the vehicle to better plan parking routes and perform parking space detection and other operations.

[0004] The inventors found that traditional parking mapping methods usually use vision + IMU (Inertial Measurement Unit) odometer for track calculation, and ultrasound for spatial parking space search, corner point update and obstacle avoidance. This method has poor visual capture ability in areas with low light intensity such as underground garages, and can only rely on IMU odometer for parking mapping; and using single data for parking mapping is easily affected by the accuracy of data acquisition equipment and its built-in algorithm, resulting in poor accuracy of parking mapping and greater parking risks. Summary of the invention

[0005] The present invention provides a parking mapping method, system and vehicle based on the combination of laser and IMU, so as to solve the problem that the traditional solution has poor visual capture ability in areas with low light intensity such as underground garages, and can only rely on IMU odometer for parking mapping; and the use of single data for parking mapping is easily affected by the accuracy of data acquisition equipment and its built-in algorithm, resulting in poor accuracy of parking mapping and greater parking risks.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a parking mapping method based on a combination of laser and IMU, which is applied to a vehicle equipped with a laser radar, and the method comprises:

[0008] Based on the LiDAR observation data, the observation data of the vehicle's position and posture is obtained in real time;

[0009] Based on IMU odometer data, the prediction data of the vehicle's position and posture is obtained in real time;

[0010] The pose optimization objective function is constructed by minimizing the difference between the observed pose data and the predicted pose data of the ego-vehicle.

[0011] Based on the observation data of the ego-vehicle posture and the predicted data of the ego-vehicle posture, the optimal posture data is obtained by optimizing and solving the posture optimization objective function;

[0012] The laser radar observation data is optimized with the obtained optimal posture data to obtain a local sub-image;

[0013] The global map is constructed based on the obtained local sub-map.

[0014] Furthermore, the observation data of the vehicle's posture is obtained in real time based on the laser radar observation data. Specifically, the laser radar generates a number of point cloud data frames arranged in time sequence by continuously scanning the surrounding environment; each frame of point cloud data reflects the three-dimensional spatial information around the vehicle at the corresponding moment; and the observation data of the vehicle's posture is determined by inter-frame matching between adjacent point cloud data frames.

[0015] Furthermore, the method of acquiring predicted data of the vehicle's posture in real time based on the IMU odometer data is specifically as follows: acquiring the vehicle's acceleration data in real time based on the IMU odometer; and determining the predicted data of the vehicle's posture through integration processing based on the acquired acceleration data.

[0016] Furthermore, the posture optimization objective function is specifically expressed as follows:

[0017] minF(x)=min∑e i (x) T Ω i e i (x)

[0018] Among them, e i (x) represents the difference between the LiDAR observation and the IMU prediction, Ω i Indicates e i (x) is the variance corresponding to the normal distribution it follows.

[0019] Furthermore, the optimization solution of the posture optimization objective function is specifically: performing a first-order Taylor approximation transformation on the posture optimization objective function, and optimizing and solving it based on the least squares method to obtain the optimal posture data.

[0020] Furthermore, the laser radar observation data is optimized by using the obtained optimal posture data, specifically: based on the obtained optimal posture data, the laser radar observation data is translated and transformed to achieve coordinate conversion of the laser radar observation data.

[0021] Furthermore, the constructing of the global map based on the obtained local sub-graphs is specifically: based on a number of local sub-graphs obtained at different moments in the parking process, the global map is obtained by splicing the obtained local sub-graphs.

[0022] Furthermore, in the process of constructing the local sub-graph, loop detection is performed according to whether the features in the current lidar observation data are consistent with one or several frames of historical point cloud data, and the local sub-graph is optimized based on the loop detection results.

[0023] In a second aspect, the present invention provides a parking mapping system based on a combination of laser and IMU, comprising:

[0024] A posture observation data acquisition unit, which is used to acquire the observation data of the posture of the vehicle in real time based on the laser radar observation data;

[0025] A posture prediction data acquisition unit, which is used to obtain the prediction data of the vehicle posture in real time based on the integration of IMU odometer data;

[0026] An objective function construction unit, which is used to construct a posture optimization objective function by minimizing the difference between the observed data of the ego-vehicle posture and the predicted data of the ego-vehicle posture;

[0027] A posture optimization unit, which is used to obtain optimal posture data by optimizing and solving the posture optimization objective function based on the observation data of the self-vehicle posture and the prediction data of the self-vehicle posture;

[0028] A local sub-graph construction unit, which is used to optimize the laser radar observation data with the obtained optimal posture data to obtain a local sub-graph;

[0029] The global map construction unit constructs a global map based on the obtained local sub-map.

[0030] In a third aspect, the present invention provides a vehicle, which adopts the above-mentioned parking mapping method based on the combination of laser and IMU.

[0031] One or more of the above technical solutions have the following beneficial effects:

[0032] The present invention provides a parking mapping method, system and vehicle based on the combination of laser and IMU. The solution adopts a combination of laser radar and IMU odometer to achieve parking mapping, which can effectively address the problem of poor accuracy of traditional solutions that can only rely on single data (i.e., IMU) for parking mapping in dark environments (such as underground garages).

[0033] The scheme of the present invention optimizes and solves the ego-vehicle posture by minimizing the difference between the observation data of the ego-vehicle posture and the predicted data of the ego-vehicle posture, and updates and optimizes the laser radar observation data based on the optimized ego-vehicle posture, thereby obtaining an optimized local sub-graph; at the same time, the scheme performs secondary optimization on the local sub-graph by means of loop closure detection, further ensuring the accuracy of the local sub-graph, thereby improving the effectiveness of the parking mapping result.

[0034] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0036] Figure 1 This is an overall flow chart of a parking mapping method based on the combination of laser and IMU according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0038] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0039] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0040] Terminology explanation:

[0041] Local submap: A local submap is a map representation of the local environment of the vehicle. It is extracted and constructed from the environmental data around the vehicle, such as point cloud data scanned by a lidar or image data taken by a camera. The local submap can be in various forms such as a grid map and a feature map, and is used to describe obstacles, road boundaries, lane lines, and other information within a certain range around the vehicle.

[0042] In one or more embodiments, Figure 1 As shown, the present application provides a parking mapping method based on the combination of laser and IMU, which is applied to a vehicle equipped with a laser radar. The method includes the following processing steps:

[0043] Step 1: Based on the LiDAR observation data, obtain the observation data of the vehicle's posture in real time; based on the integration of the IMU odometer data, obtain the prediction data of the vehicle's posture in real time;

[0044] In the specific implementation, the vehicle posture data obtained from the laser radar observation data is:

[0045]

[0046] Assume that the noise data of the lidar (not quantifiable) is:

[0047]

[0048] The vehicle posture data obtained by integrating the IMU is:

[0049]

[0050] The noise data of IMU (not quantifiable) is:

[0051]

[0052] The observation equation of the laser radar is:

[0053]

[0054] Among them, R is the rotation matrix and T is the translation matrix. is the pose matrix in the laser coordinate system. is the pose matrix transformed to the vehicle coordinates. The data observed by the LiDAR is finally mapped to the vehicle coordinates after translation and rotation. Due to the different dimensions of the vectors, Make a homogeneous transformation into right Make a homogeneous transformation into

[0055] Step 2: Construct a posture optimization objective function to minimize the difference between the observed data of the ego-vehicle posture and the predicted data of the ego-vehicle posture;

[0056] In the specific implementation, it is assumed that the difference between the laser radar observation value and the IMU prediction value is e i ,

[0057] e i =X i -Z i

[0058] Among them, X i is the row vectorization matrix of Zl

[0059]

[0060] Z i is the row vectorization matrix of Zi

[0061]

[0062] Among them, e i The mean is 0 and the variance is Ω i Normal distribution. That is, e i ~N(0,Ω i ).

[0063] The error e is obtained by Bayesian probability estimation i The joint probability distribution is:

[0064]

[0065] To make the error as small as possible, the Gaussian distribution should be as large as possible. Since the joint probability distribution function is unchanged, it is transformed into an optimization problem, so we take the logarithm of both sides of the equation to get:

[0066]

[0067] because It is independent of the variable x. Then the problem of finding the maximum value of lnG(ei(x)) is transformed into minimizing problem.

[0068] Finally, the objective function is expressed as: minF(x)=min∑e i (x) T Ω i e i (x).

[0069] Step 3: Based on the observation data of the ego-vehicle posture and the predicted data of the ego-vehicle posture, the optimal posture data is obtained by optimizing and solving the posture optimization objective function;

[0070] Combined with the above objective function, we can find that F(x) is a convex function. We use the gradient descent method to solve the minimum point corresponding to F(x). Since F(x) is nonlinear, we cannot directly use the least squares method to solve it. So we perform a first-order Taylor approximation transformation on the original formula:

[0071] e i (x+Δx)=e i (x)+J i (x)Δx

[0072] Among them, J i (x) is the partial derivative of the mapping function F(x) with respect to the state vector x, that is:

[0073]

[0074] F(x + Δx) = ∑e i (x + Δx) T Ω i e i (x + Δx)

[0075] = ∑(e i (x) + J i Δx) T Ω i e i (x) + J i Δx

[0076] = ∑(e i T Ω i e i + e i T Ω i J i Δx + e i T Δx T J i T Ω i e i + Δx T J i T Ω i J i Δx)

[0077] = ∑(e i T Ω i e i + 2e i T Ω i J i Δx + Δx T J i T Ω i J i Δx)

[0078] = ∑c i + ∑(2b i Δx + Δx T H i Δx)

[0079] = ∑c i + ∑2b i Δx + Δx T ∑H i Δx

[0080] Combining the above equations, it can be seen that F(x + Δx) is a quadratic function of Δx.

[0081] Then take the partial derivative of F(x+Δx), when When , we obtain:

[0082] Δx=-H- 1 b

[0083] Then the corresponding Δx when the derivative is 0 is the minimum iteration value of the gradient descent. According to this value, the gradient descent can eventually converge to obtain the optimal posture data.

[0084] Step 4: Optimize the lidar observation data with the obtained optimal pose data to obtain a local sub-image;

[0085] In the specific real time, the laser radar observation data is optimized by the obtained optimal posture data, specifically: based on the obtained optimal posture data, the laser radar observation data is translated and transformed to realize the coordinate transformation of the laser radar observation data.

[0086] Specifically, the laser radar observation data is usually constructed with its own position as the origin of the coordinate system, and the coordinate axis direction is set as usual, for example: the x-axis points to the front of the laser radar, the y-axis points to the left, and the z-axis points upward. The point cloud data collected by the laser radar is initially based on this coordinate system to represent the position relationship of each point relative to the laser radar.

[0087] Given the position coordinate information in the optimal pose data, assuming that the position of the vehicle in the target reference coordinate system (taking the world coordinate system as an example) is (x0, y0, z0), for any point cloud data point P(x l ,y l ,z l ), we must first perform a translation transformation to convert it from the laser radar coordinate system to the target reference coordinate system. w ,y w , z w ) point coordinates are calculated according to the following formula:

[0088]

[0089] Through the above addition operation, the laser radar point cloud data can be converted into the target reference coordinate system in terms of position.

[0090] In more implementations, data screening and noise processing may also be performed based on the point cloud data after the coordinate system conversion. Specifically:

[0091] Data screening: After completing the coordinate transformation, the optimized LiDAR observation data can be screened according to actual application requirements. For example, in some data application scenarios that only focus on a specific area (such as a certain range in front of the vehicle for obstacle avoidance), point cloud data points that are too far away or in directions that do not need to be paid attention to can be eliminated, reducing the amount of data while improving subsequent processing efficiency and focusing on key information. Data screening operations can be performed by setting conditions such as distance thresholds and angle ranges.

[0092] Noise processing: Although the laser radar itself has high accuracy, the collected data may still contain noise points due to environmental factors (such as strong light reflection, smoke, etc.) or the device itself. Filtering technology can be used to process the noise of the optimized point cloud data. Common filtering methods include statistical filtering (removing noise points that obviously deviate from the statistical distribution of surrounding points) and radius filtering (removing isolated points with too few points within a certain radius, etc.), which further improves the data quality and makes the optimized laser radar observation data purer and more reliable, which is more conducive to subsequent analysis and application.

[0093] In more implementations, during the construction of the local subgraph, loop detection is performed based on whether features in the current lidar observation data are consistent with one or several frames of historical point cloud data, and the local subgraph is optimized based on the loop detection result.

[0094] Specifically, the optimization of the local subgraph based on the loop detection result specifically includes:

[0095] (1) Error correction based on loop closure:

[0096] Once the loop is determined, the loop information can be used to correct the error of the local sub-map. Since there are accumulated errors in the process of constructing the local sub-map and the previous map stitching, the exact position and posture of the vehicle at the loop point can be recalculated through the features matched at the loop. For example, according to the coordinate difference between the matching features, the position and angle of the local sub-map in the global coordinate system are adjusted, and the previously accumulated errors are redistributed and corrected, so that the local sub-map more accurately reflects the actual environment.

[0097] At the same time, the point cloud data in the local sub-image can be optimized to remove unreasonable points caused by errors or refit and correct some fuzzy features to further improve the quality of the local sub-image.

[0098] (2) Local sub-graph fusion and update:

[0099] For multiple local sub-images related to loop closure, the fusion between them is optimized according to the accurate position relationship determined by loop closure detection. If there is inaccurate splicing of these local sub-images before, the loop closure information is used to re-splice and fuse them to ensure that the transition between local sub-images is natural and accurately reflects the continuity of the environment.

[0100] In addition, combined with the current lidar observation data, the parts of the local sub-map that may change are updated, such as the detection of new obstacles, changes in parking space occupancy, etc., so that the local sub-map always reflects the latest status of the actual environment.

[0101] Step 5: Construct a global map based on the obtained local sub-map.

[0102] In a specific implementation, the construction of the global map based on the obtained local sub-maps is specifically: based on a number of local sub-maps obtained at different moments in the parking process, the global map is obtained by splicing the obtained local sub-maps.

[0103] In one or more embodiments, corresponding to the above method, this embodiment provides a parking mapping system based on the combination of laser and IMU, including:

[0104] A posture observation data acquisition unit, which is used to acquire the observation data of the posture of the vehicle in real time based on the laser radar observation data;

[0105] A posture prediction data acquisition unit, which is used to obtain the prediction data of the vehicle posture in real time based on the integration of IMU odometer data;

[0106] An objective function construction unit, which is used to construct a posture optimization objective function by minimizing the difference between the observed data of the ego-vehicle posture and the predicted data of the ego-vehicle posture;

[0107] A posture optimization unit, which is used to obtain optimal posture data by optimizing and solving the posture optimization objective function based on the observation data of the self-vehicle posture and the prediction data of the self-vehicle posture;

[0108] A local sub-graph construction unit, which is used to optimize the laser radar observation data with the obtained optimal posture data to obtain a local sub-graph;

[0109] The global map construction unit constructs a global map based on the obtained local sub-map.

[0110] It can be understood that the system described in this embodiment corresponds to the above-mentioned method embodiment, and its technical details have been described in detail in the method embodiment, so they will not be repeated here.

[0111] In more embodiments, this embodiment provides a vehicle, which adopts the above-mentioned parking mapping method based on the combination of laser and IMU.

[0112] In a specific implementation, the vehicle may also include RF (Radio Frequency) circuits, memories including one or more computer-readable storage media, input units, display units, sensors, audio circuits, WiFi (Wireless Fidelity) modules, processors including one or more processing cores, and power supplies. Those skilled in the art will appreciate that the above components do not limit the vehicle and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently. Among them:

[0113] RF circuits can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is handed over to one or more processors for processing; in addition, uplink data is sent to the base station. Usually, the RF circuit includes but is not limited to an antenna, at least one amplifier, a tuner, one or more oscillators, a user identity module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. In addition, the RF circuit can also communicate with the network and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0114] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the vehicle (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory may also include a memory controller to provide the processor and the input unit with access to the memory.

[0115] The input unit can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Specifically, the input unit may include a touch-sensitive surface and other input devices. The touch-sensitive surface, also known as a touch display or touchpad, can collect the user's touch operations on or near it (such as the user's operation on or near the touch-sensitive surface using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface may include a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor, and can receive and execute the command sent by the processor. In addition, the touch-sensitive surface can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch-sensitive surface, the input unit may also include other input devices. Specifically, other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0116] The display unit can be used to display information input by the user or information provided to the user and various graphical user interfaces of the vehicle, which can be composed of graphics, text, icons, videos and any combination thereof. The display unit may include a display panel. Optionally, the display panel may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. Further, the touch-sensitive surface may cover the display panel. When the touch-sensitive surface detects a touch operation on or near it, it is transmitted to the processor to determine the type of touch event, and then the processor provides corresponding visual output on the display panel according to the type of touch event. The touch-sensitive surface and the display panel are implemented as two independent components to implement input and output functions, but in some embodiments, the touch-sensitive surface can be integrated with the display panel to implement input and output functions.

[0117] The vehicle may also include at least one sensor, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel according to the brightness of the ambient light, and the proximity sensor may turn off the display panel and / or backlight when the vehicle moves to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the vehicle, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0118] The audio circuit, speaker, and microphone can provide an audio interface between the user and the vehicle. The audio circuit can convert the received audio data into an electrical signal and transmit it to the speaker, which converts it into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit and converted into audio data. The audio data is then processed by the output processor and sent to another vehicle through the RF circuit, or the audio data is output to a memory for further processing. The audio circuit may also include an earphone jack to provide communication between an external headset and the vehicle.

[0119] WiFi is a short-range wireless transmission technology. The vehicle can help users send and receive emails, browse web pages, and access streaming media through the WiFi module, which provides users with wireless broadband Internet access. Although the WiFi module is shown, it is understandable that it is not a necessary component of the vehicle and can be omitted as needed without changing the essence of the invention.

[0120] The processor is the control center of the vehicle, using various interfaces and lines to connect various parts of the entire mobile phone, and by running or executing software programs and / or modules stored in the memory, and calling data stored in the memory, it executes various functions of the vehicle and processes data, thereby monitoring the mobile phone as a whole. Optionally, the processor may include one or more processing cores; preferably, the processor may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor.

[0121] The vehicle also includes a power source (such as a battery) for supplying power to various components. Preferably, the power source can be logically connected to the processor through a power management system, so that the power management system can manage charging, discharging, and power consumption. The power source can also include one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0122] Although not shown, the vehicle may also include a camera, a Bluetooth module, etc., which will not be described in detail here. Specifically in this embodiment, the display unit of the vehicle is a touch screen display, and the vehicle also includes a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors. The one or more programs include a method for executing the method shown in the above embodiment.

[0123] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A parking mapping method based on the combination of laser and IMU, which is applied to vehicles equipped with laser radar, characterized in that: The method comprises: Based on the LiDAR observation data, the observation data of the vehicle's position and posture is obtained in real time; Based on IMU odometer data, the prediction data of the vehicle's position and posture is obtained in real time; The pose optimization objective function is constructed by minimizing the difference between the observed pose data and the predicted pose data of the ego-vehicle. Based on the observation data of the ego-vehicle posture and the prediction data of the ego-vehicle posture, the optimal posture data is obtained by optimizing and solving the posture optimization objective function; The laser radar observation data is optimized with the obtained optimal posture data to obtain a local sub-image; The global map is constructed based on the obtained local sub-map.

2. A parking mapping method based on the combination of laser and IMU as claimed in claim 1, characterized in that: The method of obtaining the observation data of the vehicle's posture in real time based on the laser radar observation data is specifically as follows: the laser radar generates a number of point cloud data frames arranged in time sequence by continuously scanning the surrounding environment; each frame of point cloud data reflects the three-dimensional spatial information around the vehicle at the corresponding moment; and the observation data of the vehicle's posture is determined by inter-frame matching between adjacent point cloud data frames.

3. The parking mapping method based on the combination of laser and IMU as claimed in claim 1, characterized in that: The method of obtaining the predicted data of the vehicle's posture in real time based on the IMU odometer data is specifically as follows: obtaining the acceleration data of the vehicle in real time based on the IMU odometer; and determining the predicted data of the vehicle's posture through integration processing based on the obtained acceleration data.

4. The parking mapping method based on the combination of laser and IMU as claimed in claim 1, characterized in that: The pose optimization objective function is specifically expressed as follows: minF(x)=min∑e i (x) T Ω i e i (x) Among them, e i (x) represents the difference between the LiDAR observation and the IMU prediction, Ω i Indicates e i (x) is the variance corresponding to the normal distribution it follows.

5. The parking mapping method based on the combination of laser and IMU as claimed in claim 1, characterized in that: The optimization solution of the posture optimization objective function is specifically: performing a first-order Taylor approximation transformation on the posture optimization objective function, and optimizing and solving it based on the least squares method to obtain the optimal posture data.

6. The parking mapping method based on the combination of laser and IMU as claimed in claim 1, characterized in that: The laser radar observation data is optimized by using the obtained optimal posture data, specifically: based on the obtained optimal posture data, the laser radar observation data is translated and transformed to achieve the coordinate transformation of the laser radar observation data.

7. The parking mapping method based on the combination of laser and IMU as claimed in claim 1, characterized in that: The constructing of the global map based on the obtained local sub-graphs is specifically: based on a plurality of local sub-graphs obtained at different moments in the parking process, the global map is obtained by splicing the obtained local sub-graphs.

8. The parking mapping method based on the combination of laser and IMU as claimed in claim 1, characterized in that: During the construction of the local sub-graph, loop detection is performed based on whether the features in the current lidar observation data are consistent with one or several frames of historical point cloud data, and the local sub-graph is optimized based on the loop detection results.

9. A parking mapping system based on the combination of laser and IMU, characterized in that: include: A posture observation data acquisition unit, which is used to acquire the observation data of the posture of the vehicle in real time based on the laser radar observation data; A posture prediction data acquisition unit, which is used to obtain the prediction data of the vehicle posture in real time based on the integration of IMU odometer data; An objective function construction unit, which is used to construct a posture optimization objective function by minimizing the difference between the observed data of the ego-vehicle posture and the predicted data of the ego-vehicle posture; A posture optimization unit, which is used to obtain optimal posture data by optimizing and solving the posture optimization objective function based on the observation data of the self-vehicle posture and the prediction data of the self-vehicle posture; A local sub-graph construction unit, which is used to optimize the laser radar observation data with the obtained optimal posture data to obtain a local sub-graph; The global map construction unit constructs a global map based on the obtained local sub-map.

10. A vehicle, characterized in that: A parking mapping method based on the combination of laser and IMU as described in any one of claims 1 to 8 is adopted.

Images