WO2020124624A1

WO2020124624A1 - Autonomous driving sensing method and system employing close coupling

Info

Publication number: WO2020124624A1
Application number: PCT/CN2018/123652
Authority: WO
Inventors: 王峰; 智凯旋; 揭云飞; 钟有东; 肖飞; 黄祖德
Original assignee: 东莞市普灵思智能电子有限公司
Priority date: 2018-12-20
Filing date: 2018-12-25
Publication date: 2020-06-25
Also published as: CN109725339A

Abstract

An autonomous driving sensing method employing close coupling comprises: acquiring measurement data of an inertial navigation module, image data of a stereo vision module, and raw satellite navigation measurement data of an autonomous driving vehicle (S1); and closely coupling the image data of the stereo vision module, the raw satellite navigation measurement data, and the measurement data of the inertial navigation module, and correcting a drift error of the inertial navigation module (S2). An autonomous driving sensing system employing the autonomous driving sensing method employing close coupling is also provided. The method closely couples the measurement data of the inertial navigation module, the image data of the stereo vision module, and the raw satellite navigation measurement data, and limits an increase in the drift error of the inertial navigation module, thereby improving positioning accuracy, eliminating the need for a high-cost laser scanning radar, and reducing costs of the autonomous driving vehicle.

Description

Tightly coupled automatic driving perception method and system

Technical field

The present invention relates to the technical field of computer applications, and in particular to a tightly coupled automatic driving perception method and system.

Background technique

In recent years, with the increasing awareness of automobile safety and the development of information technology, more and more attention has been paid to the field of autonomous driving. Many companies and scientific research institutions in the world have begun to invest in the development of autonomous driving related products. It is expected that autonomous driving vehicles will be in 2021. Will enter the market and bring huge changes to the automotive industry. Relevant research shows that the development of autonomous driving technology will bring disruptive development in various fields. For example, its development can enhance highway traffic safety, ease traffic congestion and reduce environmental pollution. At the same time, autonomous driving technology is also a measure of a country. An important symbol of scientific research strength and industrial level has broad application prospects in the field of national defense and national economy.

Automated driving means that the car senses the road environment through the onboard sensor system, and controls the vehicle's steering and speed according to the road, vehicle position and obstacle information obtained by the perception, and then automatically plans the driving route and controls the vehicle to reach the predetermined target Technology.

Nowadays, in terms of autonomous driving, major companies have their own technical directions. The existing technology has a combined system of a visual system and an inertial navigation module with a binocular direct method, but the error generated by the visual system and the inertial navigation module in the combined system cannot be Effective limitation, the error of the combined system will increase without limitation under the condition of no image gradient for a long time, resulting in the failure of the combined system perception.

The prior art also has a vision system with a monocular feature point method, an inertial navigation module, and a tightly coupled automatic driving perception system for satellite navigation, but the monocular camera cannot detect featureless obstacles, such as isolation barriers on high-speed roads, bicycles, or animals, etc. . The existing vision system also uses a binocular stereo vision system for coupling, but the feature point method is still used, which requires a large amount of calculation and requires high hardware performance.

To this end, we propose a stereo vision image processing module, inertial navigation module and satellite navigation module based on the binocular direct method of tightly coupled automatic driving perception method and system.

Summary of the invention

The main purpose of the present invention is to provide a tightly coupled automatic driving perception method and system, which has the advantages of maximizing the positioning accuracy of the automatic driving perception system, and improving the calculation efficiency and reliability.

To achieve the above object, the present invention provides a tightly coupled automatic driving perception method, which includes:

Step S1: Obtain the image data of the stereo vision module, the measurement data of the inertial navigation module and the original measurement data of the satellite navigation;

Step S2: Tightly couple the image data of the stereo vision module, the original measurement data of the satellite navigation and the measurement data of the inertial navigation module, and correct the drift error of the inertial navigation module.

Preferably, the stereo vision module is processed by a direct method of a binocular camera, and the image data includes static measurement data and dynamic measurement data of the binocular camera.

Preferably, the tight coupling consists of a weighted reprojection error of stereo vision, a satellite navigation error, and a time error from inertial navigation to form a cost function.

Preferably, the step S1 specifically includes:

Step S21: Use a binocular camera to obtain the image data of the stereo vision module;

Step S22: Obtain the measurement data of the inertial navigation module by using an inertial sensor;

Step S23: Obtain the satellite navigation original measurement data through the receiver;

Step S24: Perform tight coupling processing on the inertial navigation module measurement data, the image data, and the satellite navigation original measurement data.

Preferably, the step S22 specifically includes:

Step S221: Using an inertial sensor to measure the 3-axis acceleration and 3-axis angular velocity of the autonomous vehicle in a fixed coordinate system;

Step S222: Rotate the acceleration and the angular velocity to the navigation coordinate system, solve the inertial navigation machinery layout equations, and calculate the position and attitude angle of the autonomous vehicle.

Preferably, the step S23 specifically includes:

Step S231: Receive the signal of the navigation satellite with the receiver;

Step S232: Analyze the ephemeris information of each satellite, and calculate the satellite position and satellite velocity of each satellite according to the ephemeris information;

Step S233, and calculate the pseudo distance, Doppler frequency drift and carrier phase of the satellite.

Preferably, the step S24 specifically includes: correcting the drift error of the inertial navigation module through the satellite navigation raw measurement data combined with the image data of the stereo vision module.

A tightly coupled automatic driving perception system, the system includes: a stereo vision image processing module of a binocular direct method, a satellite navigation module, an inertial navigation module, and a system tightly coupled module. The inertial navigation module is used to acquire inertia using an inertial sensor The measurement data of the navigation module; the stereo vision image processing module, which uses a binocular camera to obtain the image data of the stereo vision module; the satellite navigation module, which is used to obtain the original measurement data of the satellite navigation through the receiver; the system tight coupling module, which is used to The inertial navigation module measurement data, the image data of the stereo vision module and the satellite navigation original measurement data are tightly coupled;

The stereo vision image processing module, the satellite navigation module and the inertial navigation module are all connected to the system tight coupling module.

Preferably, the stereo vision image processing module includes a binocular camera.

Preferably, the inertial navigation module includes an inertial sensor, and the inertial sensor is fixed on the autonomous vehicle.

Compared with the prior art, the present invention has the following beneficial effects: The present invention tightly couples the measurement data of the inertial navigation module, the image data of the stereo vision module and the original measurement data of the satellite navigation, and performs the error measurement of the inertial navigation module. The correction improves the positioning accuracy and no longer requires expensive laser scanning radar, thereby reducing the cost of self-driving cars.

BRIEF DESCRIPTION

FIG. 1 is a flowchart of a tightly coupled automatic driving perception method according to an embodiment of the present invention.

FIG. 2 is a flowchart of a system tight coupling module according to an embodiment of the present invention.

FIG. 3 is a schematic structural diagram of a tightly coupled automatic driving perception system according to an embodiment of the present invention.

detailed description

In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

The invention provides an automatic driving perception method based on tight coupling of a stereo vision module, an inertial navigation module and a satellite navigation module. Inertial navigation can provide information continuously, with high accuracy in a short time, but positioning errors will accumulate over time; satellite navigation has long-term stability, but it is susceptible to interference, and the frequency of data update is low; stereo vision calculates obstacles to cameras according to the parallax of different cameras Distance, but the vision system cannot effectively locate and detect the distance of obstacles in the environment where the image lacks gradient. Stereo vision, inertial navigation and satellite navigation constitute a combined navigation system, which can help each other to sense the status of the vehicle and the environment, complement each other in different environments, improve reliability and navigation accuracy, and can accurately extract the distance, which can replace the existing Laser scanning radar reduces costs.

FIG. 1 is a flowchart of a tightly coupled automatic driving perception method according to an embodiment of the present invention. As shown in FIG. 1, the tightly coupled automatic driving perception method specifically includes:

S1. Obtain the measurement data of the inertial navigation module of the self-driving vehicle, the image data of the stereo vision module and the original measurement data of the satellite navigation; S2. In the tight coupling process, the image data of the stereo vision module and the original measurement data of the satellite navigation and the inertial navigation The measurement data of the module is tightly coupled to correct the error of the measurement data of the inertial navigation module, so as to perceive the state of the vehicle and the environment. The following describes the process of the specific automatic driving perception method in detail:

(1) The image data of the stereo vision module is obtained by the stereo vision image processing module of the binocular direct method. The following describes the detailed process of acquiring the image data of the stereo vision module by using a binocular camera:

The direct method is based on the assumption that the grayscale is unchanged. The pixel grayscale of the same spatial point is fixed in each image. The direct method does not need to extract features, and at the same time in the absence of corners and edges or the light changes are not obvious The environment also has a good effect; and the direct method needs to process less data, which can achieve high calculation efficiency.

The specific process of using the binocular direct method to process the image captured by the camera stereo vision is as follows:

1. Use a binocular camera to obtain grayscale images of two or more images of the measured object from different positions, and record the images obtained by the binocular camera at time t and t+1 as I _i and I _j .

2. Calibrate the camera through matlab or opencv to obtain the internal parameters of the camera.

3. Perform distortion processing on the obtained image.

4. Input the above image data into the tightly coupled module of the system, and calculate the photometric energy according to the calculated image. Specifically, the spatial point Pi in the image Ii appears in another image Ij, and a spatial point Pi appearing in the images Ii and Ij is selected, according to the assumption that the gray value measured at the three-dimensional point in the same space under various viewing angles is unchanged In principle, the projection p'of the point p in the image Ii on the image Ij is calculated by the following formula:

Among them, Π _K and

Is the projection and back projection function of the camera image frame point, d _p is the inverse depth of p point, and T _ji is the conversion relationship between image frames:

Among them, R _ji is a 3*3 rotation matrix, and t is a translation vector.

Its photometric error energy function is:

among them,

Is the Huber norm, to prevent the error energy function from increasing too fast with the photometric error; ω _p is the weight value, in order to reduce the weight value corresponding to the pixels with large gradients in the image, so that the final energy function can reflect most pixels Photometric error, not the error of pixels with large individual gradients; I _i [p] and I _j [p'] are the gray values of P _i at the corresponding points of the image.

The camera motion is obtained by minimizing the photometric energy, and when the photometric energy is the minimum value, the image data of the stereo vision module is solved. The objective function is:

The above formula (1-3) is the photometric error energy function of the monocular camera. When the camera is a binocular camera, the stereo vision module uses the direct method of the binocular camera to process. The image data of the stereo vision module includes the binocular camera is static Static measurement data at time and dynamic measurement data at dynamic time. The binocular direct method balances the relative weight of each image frame of the camera and static stereo vision in motion by introducing a coupling factor λ. The error energy function is:

Among them, obs ^t (p) represents the observation point in all image frames,

It is the error energy function in static stereo vision. Then, according to formula (1-4) and formula (1-5), the objective function of the new binocular camera can be obtained. R _ji and t appearing in the conversion between the above two image frames are the pose of the camera, and the pose of the camera is obtained by using the gradient descent method or Gauss-Newton method to solve the objective function. Furthermore, the camera pose is used to correct the error of the measurement data of the inertial navigation module of the self-driving vehicle in the inertial navigation. The camera pose obtained by the binocular direct method does not need to extract features, and the ability to respond to road and environmental changes is significantly improved.

(2) The measurement data of the inertial navigation module is obtained through the inertial navigation module. The measurement data of the inertial navigation module includes the speed and displacement angular rate of the autonomous driving vehicle. The following describes the detailed process of acquiring the measurement data of the inertial navigation module:

First, the inertial sensors are used to measure the 3-axis acceleration and 3-axis angular velocity of the autonomous vehicle in a fixed coordinate system. Preferably, the inertial sensor is installed on the vehicle chassis, the inertial sensor is an accelerometer and a gyroscope, wherein the accelerometer is used to measure the acceleration of the vehicle, and the gyroscope is used to measure the angular velocity of the vehicle. However, there are measurement errors such as zero drift in the measurement sensor. These measurement errors cause the positioning error to increase in time squared and the attitude angle error to increase in proportion to time. If not limited, the navigation system quickly loses its ability, then the error is modeled Compensation can reduce deterministic errors and random drift errors.

Further, the acceleration and angular velocity are rotated into the navigation coordinate system, the inertial navigation machinery arrangement equation is solved and the position and attitude angle of the autonomous vehicle are calculated. Specifically, the navigation system selected for updating the pose value and error compensation is the n system, which is usually the northeast sky.

Under the northeast sky coordinate system, the vehicle position update formula is as follows:

In the above formula,

Is the projection of the carrier velocity in the n system; λ, L, and h represent the longitude, latitude, and height of the carrier; a represents the basic geodetic parameter in the WGS-84 coordinate system-the long semi-axis length of the ellipsoid, and e is the ellipsoid's Eccentricity. Finally, the differential equations about λ, L, and h are obtained, and the values of λ, L, and h can be obtained according to the solution, so that the position of the self-driving vehicle can be calculated, R _N is the curvature of the unitary surface, and R _M is the radius of the meridian circle curvature.

Under the northeast sky coordinate system, the vehicle speed update formula is as follows:

In the above formula,

Is the quaternion direction cosine matrix

The transposition of v ⁿ is the projection of the velocity of the carrier in the n system;

The displacement angular rate calculated by the relative velocity of the carrier;

It represents the projection of the earth's rotation angular rate under n; g ⁿ is the projection of the local gravity acceleration on n; f ^b is the measured output value of the accelerometer. The symbol "×" represents vector cross product. Finally get about v ⁿ ,

The differential equation of, according to the solution, we can get v ⁿ ,

The value of, so that the speed and displacement angular rate of the autonomous vehicle can be calculated.

Furthermore, combining inertial navigation kinematics with a simple dynamic deviation model yields the following system of equations:

among them,

The element of is each uncorrelated zero-mean Gaussian white noise process.

Is measured by an accelerometer, and g _W is the earth's gravitational acceleration vector. Compared with the gyro bias modeled as a random walk, we use a time constant τ>0 to model the accelerometer bias as a bounded random walk. The matrix Ω is estimated along with the gyroscope measurement

Angular rate

composition:

Finally, we obtain the prediction error e _s of the inertial navigation part of the combined navigation, e _s is the time error term of the inertial navigation:

The three items on the right are the 1, 2, and 3 components of the quaternion.

(3) The satellite navigation raw measurement data is obtained through the satellite navigation module. The satellite navigation raw measurement data includes satellite position, satellite speed, pseudo-range, Doppler frequency drift and carrier phase. The process is described:

The Global Navigation Satellite System (GNSS) has high navigation accuracy. The GNSS located on the vehicle transmits signals to the satellites in orbit in the air, and the receiver receives the signals of the navigation satellites; the ephemeris information of each satellite is resolved based on the received satellite signals , Calculate the satellite position and satellite speed of each of the satellites according to the ephemeris information. At the same time, the pseudo-distance, Doppler frequency drift and carrier phase of the satellite can also be calculated based on ephemeris information.

Specifically, the satellite navigation receiver uses a single-point positioning method to measure the pseudo distance, which is the relative distance between a satellite and the user. In satellite navigation, the pseudorange ρ ⁽ⁿ⁾ (t) is calculated using the time difference between the time t _u (t) and the transmission time t _s ⁽ⁿ⁾ (t-τ) when the satellite signal n is received. The speed c of the radio wave is multiplied by the following expression:

Among them, the symbol τ represents the actual time interval from the transmission of the GNSS signal to the reception by the user. However, since the clocks of the GNSS satellite and the user receiver are usually not synchronized with the GNSS time t, the satellite time is used to advance the GNSS time.

Indicates that the receiver time advances the GNSS time by δt _u (t), that is:

t _u (t)=t+δt _u (t) (3-3)

Moreover, the ionosphere, troposphere and other structures will cause a certain degree of delay in the propagation of electromagnetic waves, so τ needs to subtract the ionospheric delay I ⁽ⁿ⁾ (t) and the tropospheric delay T ⁽ⁿ⁾ (t) to be The propagation time of the geometric distance r ⁽ⁿ⁾ of the satellite signal from the satellite position to the receiver position, namely:

τ=r ⁽ⁿ⁾ /c+I ⁽ⁿ⁾ (t)+T ⁽ⁿ⁾ (t) (3-4)

Substitute (3-2), (3-3), (3-4) into (3-1) to get the final formula for calculating the pseudorange ρ ⁽ⁿ⁾ (t), namely:

d _trop = cT ⁽ⁿ⁾ (t)

d _iono = cI ⁽ⁿ⁾ (t)

among them,

The satellite clock, d _iono ionospheric delay and d _trop tropospheric delay are known quantities, ε ⁽ⁿ⁾ represents the unknown pseudorange measurement noise, r ⁽ⁿ⁾ is the receiver in physical space (x,y, z) The geometric distance from the nth satellite (x ⁽ⁿ⁾ , y ⁽ⁿ⁾ , z ⁽ⁿ⁾ ), the coordinates of each position (x ⁽ⁿ⁾ , y ⁽ⁿ⁾ , z ⁽ⁿ⁾ ) can be from The ephemeris broadcast by each satellite can be calculated.

When the pseudorange ρ ⁽ⁿ⁾ (t) is calculated, the observation equation of the carrier phase in satellite navigation can be obtained as follows:

φλ=ρ(t _s ,t _r )+c(dt _r -dt _s )+d _trop -d _iono +d _rel +d _SA +d _multi +Nλ+ε (3-6)

among them,

Is the carrier phase observation value, λ is the carrier wavelength, N is the full-period ambiguity, t _s is the time when the satellite transmits the signal, t _r is the time when the receiver receives the signal, dt _s and dt _r are the clock difference between the satellite and the receiver, c is the speed of light, d _iono ionospheric delay, d _trop delay of the troposphere, d _SA is the SA influence, d _multi multi-path effect, ε is the carrier measurement _{_{noise, ρ (t s, t r}} ) is t _s time satellite and The geometric distance between the receiver antennas at time t _r , which contains station coordinates, satellite orbits, and earth rotation parameters.

Since the Doppler frequency shift observation is an instantaneous observation of the carrier phase rate, ignoring changes in the ionosphere and troposphere delay versus time,

Differentiate the carrier phase observation equation:

among them,

Then, the Doppler frequency shift measurement equation is:

Where λ is the wavelength corresponding to carrier L1 (f1=1575.42MHz),

Is the Doppler frequency shift of user u relative to satellite i, v ⁽ⁱ⁾ is the moving speed of satellite i,

Is the moving speed of user u, a _u ⁽ⁱ⁾ is the unit vector of user u pointing to satellite i, c is the speed of light in vacuum, δf _u is the clock drift of user u, and δf ⁽ⁱ⁾ is the clock drift of satellite i ,

It is the Doppler frequency measurement noise of user u relative to satellite i.

(4) Tightly couple the data input of three parts: stereo vision image processing module, inertial navigation module and satellite navigation module. The data includes inertial navigation module measurement data, stereo vision module image data and satellite navigation original measurement data. The original measurement data is combined with the image data of the stereo vision module to correct the drift error of the inertial navigation module, so as to assist the inertial navigation module to limit the drift error. FIG. 2 is a specific flowchart of the system tight coupling module. In this figure, the inertial sensor is used to obtain the 3-axis acceleration and 3-axis angular velocity of the vehicle in a fixed coordinate system and input into the inertial navigation module; the binocular camera collects pictures for direct method input; the GPS receiver is used to obtain satellites Raw measurement data. Combine the reprojection error of the direct method of the binocular camera, the satellite navigation error obtained from the satellite's original measurement data and the time error of inertial navigation, and perform an overall optimization estimate to correct the drift error of the inertial navigation module, and finally output the optimal bit posture.

When tight coupling is performed, the tight coupling consists of a weighted reprojection error of stereo vision, satellite navigation error, and time error from inertial navigation to form a cost function to express, the expression is as follows:

Where e _r is the weighted reprojection error of stereo vision, e _g is the satellite navigation error, e _s is the time error term of inertial navigation, i represents the camera label, k represents the camera frame label, and j represents the landmark label. The landmark labels visible in the k-th frame and the i-th camera are written as the set J(i, k). In addition,

The information matrix representing the corresponding subscript measurement, and

Represents the inertial navigation error information when corresponding to the k-th frame picture,

Represents the error information matrix corresponding to the satellite when it corresponds to the sth satellite at time t.

Furthermore, _er is the weighted reprojection error of stereo vision. The manifestation of the reprojection error of stereo vision is:

Among them, h _i represents the projection model of the camera, and z ^{i, j, k} represents the image coordinates of the feature.

Represents the attitude of the optimization system,

External parameters representing inertial navigation and camera,

Represents feature coordinates.

Furthermore, e _g is the satellite navigation error. The error of each navigation satellite s at each time t includes three parts of errors. Its manifestation is:

Wherein, e _p represents a pseudorange error, e _d denotes the Doppler error, e _c represents the carrier phase error.

Furthermore, the form of the corresponding error information matrix W _g becomes the following form:

Through linear or non-linear optimization methods, the value of the cost function J(x) is minimized, thereby completing the tight coupling between the stereo vision image processing module, the inertial navigation module, and the satellite navigation module, and combining the original measurement data of the satellite navigation The image data of the stereo vision module corrects the drift error of the inertial navigation module. When the number of satellites is less than the set number, the receiver cannot be positioned. The original measurement data of satellite navigation combined with the image data of the stereo vision module corrects the system error of the inertial navigation module, thereby improving the accuracy of navigation and greatly enhancing navigation. The robustness of the system. The tightly coupled autonomous driving perception system can help provide high-precision measurements and maps to the environment, eliminating the need for expensive laser scanning radar and reducing the cost of autonomous vehicles.

Based on the above tightly coupled automatic driving perception method, the present invention also provides a tightly coupled automatic driving perception system 100. FIG. 3 is a schematic structural diagram of the tightly coupled automatic driving perception system 100 according to an embodiment of the present invention, as shown in FIG. It is shown that the tightly coupled automatic driving perception system 100 includes a stereo vision image processing module 10, a satellite navigation module 20, an inertial navigation module 30, and a system tight coupling module 40 of the binocular direct method.

Specifically, the inertial navigation module 30 is used to acquire inertial navigation module measurement data by using an inertial sensor; the details are as described above. The stereo vision image processing module 10 adopts a binocular direct method to obtain the image data of the stereo vision module; as described above. The satellite navigation module 20 is used to obtain the satellite navigation raw measurement data of the navigation satellite through the receiver; as described above. The system tight coupling module 40 is used to perform tight coupling processing on the measurement data of the inertial navigation module, the image data of the stereo vision module, and the original measurement data of the satellite navigation; as described above. The connection relationship between each module is as follows: the stereo vision image processing module 10, the satellite navigation module 20, and the inertial navigation module 30 are all connected to the system tight coupling module 40.

Among them, the stereo vision image processing module 10 includes a binocular camera, and the binocular camera is installed on the self-driving vehicle; as described above. Furthermore, the inertial navigation module 30 includes an inertial sensor, which is fixed to the autonomous vehicle; specifically as described above.

The basic principles and main features of the present invention and the advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the description only describe the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have Various changes and improvements that fall within the scope of the claimed invention. The claimed protection scope of the present invention is defined by the appended claims and their equivalents.

Claims

A tightly coupled automatic driving perception method, characterized in that the method includes:

Step S1: Obtain the image data of the stereo vision module, the measurement data of the inertial navigation module and the original measurement data of the satellite navigation;

Step S2: Tightly couple the image data of the stereo vision module, the original measurement data of the satellite navigation and the measurement data of the inertial navigation module, and correct the drift error of the inertial navigation module.
The tightly coupled automatic driving perception method according to claim 1, wherein the stereo vision module uses a direct method of binocular camera to process, and the image data includes static measurement data and dynamic measurement data of the binocular camera.
The tightly coupled automatic driving perception method according to claim 1, wherein the tightly coupled weighted reprojection error of stereo vision, satellite navigation error, and time error from inertial navigation constitute a cost function.
The tightly coupled automatic driving perception method according to claim 1, wherein the step S1 specifically comprises:

Step S21: Use a binocular camera to obtain the image data of the stereo vision module;

Step S22: Obtain the measurement data of the inertial navigation module by using an inertial sensor;

Step S23: Obtain the satellite navigation original measurement data through the receiver;

Step S24: Perform tight coupling processing on the inertial navigation module measurement data, the image data, and the satellite navigation original measurement data.
The tightly coupled automatic driving perception method according to claim 4, wherein the step S22 specifically includes:

Step S221: Using an inertial sensor to measure the 3-axis acceleration and 3-axis angular velocity of the autonomous vehicle in a fixed coordinate system;

Step S222: Rotate the acceleration and the angular velocity to the navigation coordinate system, solve the inertial navigation machinery layout equations, and calculate the position and attitude angle of the autonomous vehicle.
The tightly coupled automatic driving perception method according to claim 4, wherein the step S23 specifically includes:

Step S231: Receive the signal of the navigation satellite with the receiver;

Step S232: Analyze the ephemeris information of each satellite, and calculate the satellite position and satellite velocity of each satellite according to the ephemeris information;

Step S233, and calculate the pseudo distance, Doppler frequency drift and carrier phase of the satellite.
The tightly coupled automatic driving perception method according to claim 4, wherein step S24 specifically comprises: combining the satellite navigation original measurement data with the image data of the stereo vision module to the inertial navigation module Drift errors are corrected.
A tightly coupled automatic driving perception system, characterized in that the system includes: a stereo vision image processing module of a binocular direct method, a satellite navigation module, an inertial navigation module, and a system tightly coupled module. The inertial navigation module is used for The inertial sensor obtains the measurement data of the inertial navigation module; the stereo vision image processing module uses a binocular camera to obtain the image data of the stereo vision module; the satellite navigation module is used to obtain the satellite navigation original measurement data through the receiver; the system is tightly coupled module, used Performing tight coupling processing on the measurement data of the inertial navigation module, the image data of the stereo vision module, and the original measurement data of the satellite navigation;

The stereo vision image processing module, the satellite navigation module, and the inertial navigation module are all connected to the system tight coupling module.
The tightly coupled automatic driving perception system according to claim 8, wherein the stereoscopic image processing module includes a binocular camera.
The tightly coupled automatic driving perception system according to claim 8, wherein the inertial navigation module includes an inertial sensor, and the inertial sensor is fixed to the autonomous vehicle.