TW202416216A - Path planning system and method of autonomous vehicles to compute the predicted path based on the point cloud data of either the preceding vehicle or the lane edge for reducing the costs of constructing high-precision graphics, and reducing the storage space - Google Patents

Abstract

Disclosed is a path planning system and method of an autonomous vehicle, which uses at least one sensor to detect the surrounding environment information of the vehicle, and converts the surrounding environment information into a bird's-eye view including the coordinate information of each coordinate point. The system identifies and marks the lane edges, lanes and other vehicles in the bird's-eye view based on the coordinate information, and then computes the center point of a lane as well as finds the preceding vehicle. Then, the speed of the preceding vehicle is computed based on the position of the preceding vehicle, and one of the predicted paths of the preceding vehicle is estimated. If the predicted path of the preceding vehicle is identical to the driving path of the present vehicle, the preceding vehicle will be used as a path reference point; otherwise, the lane edge will be used as a path reference line to compute the final path of the present vehicle. This invention can plan the paths through point cloud data, greatly reducing the costs of constructing high-precision graphics, and reducing the storage space occupied by the data.

Description

Self-driving vehicle route planning system and method

The present invention relates to a route planning system, and more particularly to a route planning system and method for a self-driving vehicle.

In recent years, self-driving car technology has gradually matured, and related open source self-driving software has been put into the market, lowering the threshold for self-driving car development. Currently, mainstream self-driving car technology mostly relies on high-precision maps recorded by GPS location or lane line detection to obtain the best path.

Among them, the method of obtaining the best path by lane line detection has its own shortcomings, that is, not all environments have lane lines, such as intersections and parking lots. In these places without lane lines, detection will fail, so the lane line detection method will be limited by the environment.

The method of using high-precision map data to calculate the best path requires first using a vehicle equipped with a stereo camera to collect complete road information and identify road features that are helpful for positioning. For example, buildings, traffic signs, street lights, and road markings such as lane lines, direction arrows, pedestrian crossings, etc. Then, the map data of the road information is combined with the positioning data of the GPS to generate an accurate route image. However, its biggest problem is that it cannot be used if the positioning fails. Especially when the vehicle is at an intersection and there is a lack of lane lines for detection, it will be impossible to plan the vehicle route at this time. In addition, obtaining map data requires a lot of manpower and funds for measurement, and the amount of data is also quite large, which leads to increased costs.

In view of this, the present invention proposes a route planning system and method for self-driving vehicles to solve the above-mentioned deficiencies and future needs of the prior art. The specific structure and implementation method are described in detail below:

The main purpose of the present invention is to provide a route planning system and method for a self-driving car, which does not rely on high-precision map data, but classifies the surrounding environment objects by echo intensity values, thereby reducing the manpower and cost of recording high-precision map data, and at the same time reducing the space occupied by data.

Another object of the present invention is to provide a route planning system and method for an autonomous vehicle, which does not rely on a navigation system and can still plan a route through physical detection using lidar when navigation fails.

Another object of the present invention is to provide a route planning system and method for a self-driving vehicle, which can identify the lane edge based on the surrounding environment and find the lane center point when there is no lane line on the road or intersection, and then plan the driving route, thereby greatly improving safety.

To achieve the above-mentioned purpose, the present invention provides a route planning system for a self-driving vehicle, a route planning system for a self-driving vehicle, which is arranged on a vehicle, and the route planning system for a self-driving vehicle comprises: at least one sensor for detecting the surrounding environment information of the vehicle; a bird's-eye view generation module, connected to the sensor, receiving the surrounding environment information and converting it into a bird's-eye view, the bird's-eye view including the coordinate information of each mark point; a category detection module, connected to the bird's-eye view generation module, judging and marking the lane edge, lane line and the preceding vehicle in the bird's-eye view according to the coordinate information; a lane center calculation module, connected to the category detection module, judging and marking the lane center information in the marked bird's-eye view according to the lane center information in the marked bird's-eye view; a lane center point is calculated based on the lane edge and lane line, a leading vehicle is found from other vehicles based on the lane center point and the position of the vehicle, and the speed of the leading vehicle is calculated based on the position of the leading vehicle; a leading vehicle prediction module is connected to the category detection module and the lane center calculation module, and estimates a predicted path of the leading vehicle through a vehicle kinematic model; and a path planning module is connected to the leading vehicle prediction module. If the predicted path of the leading vehicle is the same as the driving path of the vehicle, the leading vehicle is used as a path reference point. If the predicted path of the leading vehicle is different from the driving path of the vehicle or there is no leading vehicle, the lane edge is used as a path reference line to calculate a final path of the vehicle.

According to an embodiment of the present invention, the sensor is a lidar, and the sensor presents the surrounding environment information of the vehicle in the form of a point cloud image. The bird's-eye view generation module then uses a rotation axis formula to convert the point cloud image into a bird's-eye view image.

According to an embodiment of the present invention, the coordinate information includes the shape formed by the coordinate points, the density of the points, the height of the object formed by the coordinate points, or the echo intensity value of each coordinate point.

According to an embodiment of the present invention, the echo intensity value is preset to have a plurality of intervals, and the coordinate points of the echo intensity values in different intervals are displayed in different colors on the bird's-eye view.

According to an embodiment of the present invention, the category detection module filters the echo intensity value to filter out noise, and then determines the lane edge, lane line and the preceding vehicle in the bird's-eye view based on the coordinate information.

According to an embodiment of the present invention, the category detection module utilizes a Kalman filter to filter the coordinate information.

According to an embodiment of the present invention, the lane center calculation module finds a feasible driving range based on the lane edge and lane line in the bird's eye view, and then takes the center point of two adjacent lane lines as the lane center point, or takes the average value of the lane line and the lane edge as the lane center point.

According to an embodiment of the present invention, after the lane center calculation module obtains the position of the preceding vehicle marked in the bird's-eye view, it calculates the speed of the preceding vehicle based on the position of the preceding vehicle in at least two consecutive bird's-eye views.

According to an embodiment of the present invention, the preceding vehicle prediction module further establishes a driving behavior interest area through the marked lane lines, and then predicts the behavior of the preceding vehicle, including going straight or turning, based on the predicted path and the driving behavior interest area.

According to an embodiment of the present invention, when the predicted path of the preceding vehicle is the same as the driving path of the own vehicle, the path planning module uses the preceding vehicle as a path reference point and combines it with the position of the own vehicle and the center point of the lane line and the speed of the preceding vehicle to calculate the final path of the own vehicle.

According to an embodiment of the present invention, when the predicted path of the preceding vehicle is different from the driving path of the vehicle, the path planning module uses the lane edge as a path reference line and calculates an edge curvature based on the path reference line to calculate the final path of the vehicle.

The present invention further provides a method for planning a route for a self-driving vehicle, comprising the following steps: using at least one sensor to detect the surrounding environment information of the vehicle; converting the surrounding environment information into a bird's-eye view, the bird's-eye view including the coordinate information of each landmark; determining and marking the lane edge, lane line and other vehicles in the bird's-eye view according to the coordinate information; calculating a lane center point according to the marked lane edge and lane line in the bird's-eye view, and calculating the lane center point according to the lane center point. The method uses the point and the position of the vehicle to find a leading vehicle from other vehicles, and then calculates the speed of the leading vehicle according to the marked position of the leading vehicle; estimates a predicted path of the leading vehicle through a vehicle-to-vehicle kinematic model; and if the predicted path of the leading vehicle is the same as the driving path of the vehicle, uses the leading vehicle as a path reference point; if the predicted path of the leading vehicle is different from the driving path of the vehicle or there is no leading vehicle, uses the edge of the lane as a path reference line to calculate a final path of the vehicle.

According to an embodiment of the present invention, the step of calculating the speed of the preceding vehicle based on the position of the preceding vehicle further includes the following steps: calculating the speed of the preceding vehicle based on the position of the preceding vehicle in at least two bird's-eye views over a continuous period of time.

According to an embodiment of the present invention, the step of estimating a predicted path of a preceding vehicle through a vehicle kinematic model further includes the following steps: establishing a driving behavior interest area through marked lane lines, and then predicting the behavior of the preceding vehicle based on the predicted path and the driving behavior interest area, including going straight or turning.

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those familiar with the art without making progressive labor are within the scope of protection of the present invention.

It should be understood that when used in this specification and the appended patent applications, the terms "include" and "comprising" indicate the presence of described features, wholes, steps, operations, elements and/or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and/or combinations thereof.

It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the present invention. As used in this specification and the appended patent applications, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" used in this specification and the appended patent applications refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

The present invention provides a route planning system and method for a self-driving vehicle. Please refer to FIG. 1, which is a schematic diagram of the route planning system for a self-driving vehicle of the present invention. The route planning system 10 for a self-driving vehicle is disposed on a vehicle (not shown in the figure). The route planning system 10 for a self-driving vehicle includes at least one sensor 12, a bird's-eye view generation module 13, a category detection module 14, a lane center calculation module 15, a front vehicle prediction module 16, and a route planning module 17. The sensor 12 is connected to the bird's-eye view generation module 13, the bird's-eye view generation module 13 is connected to the category detection module 14, the category detection module 14 is connected to the lane center calculation module 15 and the front vehicle prediction module 16, the lane center calculation module 15 is connected to the front vehicle prediction module 16, and the front vehicle prediction module 16 is connected to the path planning module 17. The above modules are set in an on-board host 11, and the on-board host 11 includes at least one processor (not shown in the figure), and the modules can be implemented by one or more processors.

The sensor 12 is installed on the vehicle to detect the surrounding environment information of the vehicle. In one embodiment, the sensor 12 is a lidar, which captures the point cloud data of the surrounding environment and generates a point cloud map. The bird's-eye view generation module 13 uses a rotation formula to convert the point cloud map into a bird's-eye view, and the bird's-eye view includes the coordinate information of each point, including the shape composed of the coordinate points, the density of the points, the height of the object composed of the coordinate points, or the echo intensity value of each point. The detection category of physical quantities such as. Since the sensor 12 can filter specific information, the sensor 12 can be used to determine whether there is a preceding vehicle.

In one embodiment, if the sensor 12 is a lidar, the point cloud echo received by it will have different echo intensities due to different materials, colors, etc. of the objects, so the lane edge, lane line, or the front vehicle can be determined by the echo intensity value. Specifically, the echo intensity value can be preset to a plurality of intervals, and the coordinate points of different echo intensity value intervals are displayed in different colors on the bird's-eye view. For example, the echo intensity values a~b are special color coatings. If they meet the characteristics of low height and long strip shape, they are determined to be lane lines or lane edges; the echo intensity values c~d are metals. If they meet the characteristics of medium to high height and cube shape, they are determined to be vehicles; and the echo intensity values e~f are vegetation or concrete. If they meet the characteristics of medium to high height and irregular shape, they are determined to be bushes or sidewalks. This determination step is performed by the category detection module 14.

The category detection module 14 identifies the lane lines, lane edges and all vehicles based on the coordinate information, and marks them on the bird's-eye view, for example, by drawing the lane lines and lane edges on the bird's-eye view, and selecting all vehicles, including the vehicle itself and the preceding vehicle/other vehicles. If the sensor 12 is a lidar, the category detection module 14 first filters the coordinate information using a Kalman filter to filter out noise, and then identifies the lane lines, lane edges and all vehicles.

The lane center calculation module 15 is used to calculate a lane center point based on the marked lane edges and lane lines in the bird's-eye view. First, a feasible driving range is found from the lane edges and lane lines in the bird's-eye view. Then, the center points of two adjacent lane lines in the feasible driving range are taken as the lane center point, or the average value of the lane line and the lane edge is taken as the lane center point. Multiple lane center points can be connected to form a lane center line. Since it is known which of the marked vehicles is the vehicle, when the lane center point is known, it can be further known which of the other vehicles is the front vehicle. In addition, after the lane center calculation module 15 obtains the position of the front vehicle, the speed of the front vehicle can be calculated based on the position of the front vehicle in at least two bird's-eye views in a continuous period of time. Therefore, the lane center calculation module 15 outputs information such as the feasible driving range, the lane center point, the position of the preceding vehicle, and the speed of the preceding vehicle.

The front vehicle prediction module 16 uses a vehicle kinematics model to estimate a predicted path of the front vehicle based on the position of the front vehicle captured in the bird's-eye view and the assumption that the speed of the front vehicle is constant. The front vehicle prediction module 16 further establishes a driving behavior interest area through the marked lane lines, and then predicts the behavior of the front vehicle t seconds later based on the predicted path and the driving behavior interest area, including going straight or turning. Therefore, the output of the front vehicle prediction module 16 is the predicted behavior of the front vehicle.

The path planning module 17 determines whether the driving paths of the preceding vehicle and the vehicle are the same according to the predicted path and predicted behavior of the preceding vehicle. If the predicted path of the preceding vehicle is the same as the driving path of the vehicle, for example, when both vehicles are turning right, the path of the preceding vehicle is used as a reference point. By combining the positions of the vehicle, the preceding vehicle, and the center point of the lane, a path equation of the final path of the vehicle can be calculated. If the predicted path of the preceding vehicle is different from the driving path of the vehicle, the edge of the lane closest to the vehicle is used as a reference line to calculate the final path of the vehicle.

Please also refer to Figure 2, which is a flow chart of the route planning method of the self-driving car of the present invention. In step S10, at least one sensor 12 is used to detect the surrounding environment information of the vehicle. In step S12, the bird's-eye view generation module 13 converts the surrounding environment information into a bird's-eye view, and the bird's-eye view includes the coordinate information of each landmark. In step S14, the category detection module 14 determines and marks the lane edges, lane lines and other vehicles in the bird's-eye view based on the coordinate information. In step S16, the lane center calculation module 15 calculates a lane center point based on the marked lane edges and lane lines in the bird's-eye view. Then, the lane center calculation module 15 finds a front vehicle from other vehicles based on the lane center point and the position of the vehicle, and then calculates the speed of the front vehicle based on the marked position of the front vehicle. In this step, the lane center calculation module 15 first finds a feasible driving range from the lane edge and lane line in the bird's eye view, and then takes the center point of two adjacent lane lines in this feasible driving range as the lane center point, or takes the average value of the lane line and the lane edge as the lane center point. In step S18, the front vehicle prediction module 16 estimates a predicted path of the front vehicle through a vehicle kinematic model, and further predicts the behavior of the front vehicle, including going straight or turning. Next, as in step S20, the sensor 12 first determines whether there is a preceding vehicle. If there is a preceding vehicle, then in step S22, the path planning module 17 further determines whether the predicted path of the preceding vehicle is the same as the driving path of the vehicle. If they are the same, then as described in step S24, the preceding vehicle is used as a path reference point, and the positions of the vehicle and the center point of the lane are combined to calculate a final path of the vehicle. On the contrary, if the predicted path of the preceding vehicle is different from the driving path of the vehicle, or if step S20 determines that there is no preceding vehicle, then as described in step S26, the lane edge is used as a path reference line to calculate a final path of the vehicle.

In the above step S12, the bird's-eye view generation module 13 converts the point cloud image into a bird's-eye view using a rotation formula. The rotation formula is as follows (1): (1) Where (x', y', z') is the original coordinate of the point cloud, and (x, y, z) is the coordinate of the transformed bird's-eye view. (cos αi, cos βi, cos γi) are changed to (c _1i , c _2i , c _3i ), (i=1, 2, 3). α, β, γ are the angles of rotation of the original coordinate system. (h ₁ , h ₂ , h ₃ ) are the positions of the new origin in the original coordinate system.

In the above step S18, the front vehicle prediction module 16 estimates the predicted path of the front vehicle through the vehicle kinematic model, and further predicts the behavior of the front vehicle. For details, please refer to Figure 3, which is a coordinate diagram of the predicted path of the front vehicle. A is the front wheel position of the self-driving model; B is the rear wheel position of the self-driving model; C is the center of mass position of the self-driving model; O is the intersection of OA and OB, which is the instantaneous rolling center of the vehicle, and the line segments OA and OB are perpendicular to the directions of the two tires respectively. δr is the rear wheel deflection angle, δf is the front wheel deflection angle, Lr is the length from the rear wheel to the center of mass, and Lf is the length from the front wheel to the center of mass. Therefore, the predicted path of the front vehicle can be expressed by the following formula (2): (2) Where ψ is the heading angle; β is the slip angle, which refers to the angle between the vehicle's direction of travel and the direction of the wheel. v is the vehicle speed, and r is the wheel angular velocity.

In the above step S24, the cubic equation is Find the final path of the vehicle as follows (3): r(s) = [x(s), y(s), θ(s), k(s)]' (3) where x is the x-axis coordinate point, y is the y-axis coordinate point, θ is the heading angle of the vehicle, and k is the curvature of the curve at the intersection. In the absence of a preceding vehicle, the curvature of the lane can be obtained from the lane edge, and then substituted into the cubic equation using the following equations (4) to (8) to obtain the final path formula (3): (4) (5) (6) (7) (8)

Figures 4 to 6 are schematic diagrams of embodiments of the present invention applied at a T-junction. Taking the case where the sensor is a lidar, the point cloud image is first converted into a bird's-eye view as shown in Figure 4 using the axis rotation formula, and the color image is represented in grayscale. Then, the surrounding environmental objects are classified according to the echo intensity value to find the lane lines, lane edges and all vehicles, as shown in Figure 5, where the long dashed line is the lane line 20, the short dashed line is the lane edge 22, and the rectangular frame is the other vehicle 24. The black dot is the position of the vehicle 26. Find the lane center point 28 between two lane lines 20 or between a lane line 20 and a lane edge 22, as shown by the triangle mark in Figure 5. It should be noted that the lane center point 28 is the first center point after passing the intersection, and as the vehicle 26 moves, the lane center point 28 at each time t will also move, and multiple lane center points 28 can be connected to form a lane center line. In Figure 6, it is determined whether there is a vehicle in front based on the vehicle width range of the vehicle 26. If there is a vehicle in front, the driving behavior is predicted through vehicle kinematics; otherwise, the curvature of the nearest lane edge 22 is extracted for calculation to find the final path of the curve. For example, the light gray arc arrow in Figure 6 is the curve path of the vehicle 26.

Figures 7 to 9 are schematic diagrams of embodiments of the present invention applied at an intersection. Taking the case where the sensor is a lidar, the point cloud image is first converted into a bird's-eye view as shown in Figure 7 using the rotation axis formula, and the color image is represented in grayscale. Then, the surrounding environmental objects are classified according to the echo intensity value to find the lane lines, lane edges and all vehicles, as shown in Figure 8, where the short dashed line is the lane edge 22 and the rectangular frame is the other vehicle 26. The black dot is the position of the vehicle 26. Next, find the lane center point 28 between the two lane edges 22, as shown by the triangle mark in Figure 8. Since the vehicle 26 can go straight or turn right, the lane center points 28 of the straight path and the right turn path are found at the same time, generating the two triangle marks in Figure 8. Similar to Figure 6, the two triangle marks are also the first lane center points 28 of the two paths after passing the intersection. In Figure 9, the width of the vehicle 26 is used to determine whether there is a vehicle in front. If there is a vehicle in front, the driving behavior of the vehicle in front is predicted through vehicle kinematics; otherwise, the curvature of the nearest lane edge 22 is extracted for calculation to find the final path through the curve. For example, the light gray straight arrow and light gray arc arrow in Figure 9 are both the paths of the vehicle 26 passing the intersection.

Figures 10 to 12 are schematic diagrams of an embodiment of the present invention applied in an underground parking lot. Taking the case where the sensor is a lidar, the point cloud image is first converted into a bird's-eye view as shown in Figure 10 using the axis rotation formula, and the color image is represented in grayscale. Then, the surrounding environmental objects are classified according to the echo intensity value to find the lane lines, lane edges and all vehicles, as shown in Figure 11, where the short dashed line is the lane edge 22 and the rectangular frame is the other vehicle 24. The black dot is the position of the vehicle 26. Find the lane center point 28 between the two lane edges 22, as shown by the triangle mark in Figure 11. In FIG. 12 , the vehicle width of the vehicle 26 is used to determine whether there is a vehicle in front. If there is a vehicle in front, the driving behavior of the vehicle in front is predicted through vehicle kinematics. Otherwise, the curvature of the nearest lane edge 22 is extracted for calculation to find the final path of the vehicle 26 . The light gray straight arrow in FIG. 12 is the path of the vehicle 26 .

In summary, the present invention provides a self-driving vehicle path planning system and method, which converts the point cloud image obtained by the lidar into a bird's-eye view through a conversion formula, determines the object type of the surrounding environment, finds the lane line and lane edge, and then calculates the feasible driving range. At the same time, the lane center point is found as the end point by the lane line of other lanes (i.e., the lane where the vehicle is about to go straight or turn). If there is a front vehicle at the center of the lane and it is predicted that the front vehicle and the vehicle have the same path, the predicted path of the front vehicle is used as the path reference point of the vehicle; otherwise, the lane edge of the environment is referenced to calculate the final path of the vehicle. In this way, the vehicle does not need high-precision maps or GPS. The final path of the vehicle can be calculated by the echo intensity value of the lidar point cloud data, which greatly reduces the cost of recording high-precision maps and the storage space occupied by the data. In addition, the system of the present invention can still be used normally in basements without GPS.

However, the above is only the preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Therefore, all equivalent changes or modifications based on the features and spirit described in the scope of the present invention should be included in the scope of the patent application of the present invention.

10: Autonomous vehicle path planning system 11: Onboard host 12: Sensor 13: Bird's-eye view generation module 14: Category detection module 15: Lane center calculation module 16: Front vehicle prediction module 17: Path planning module 20: Lane line 22: Lane edge 24: Other vehicles 26: Self-driving vehicle 28: Lane center point

Figure 1 is a block diagram of the path planning system of the self-driving car of the present invention. Figure 2 is a flow chart of the path planning method of the self-driving car of the present invention. Figure 3 is a schematic diagram of the coordinates of the predicted path of the front vehicle. Figures 4 to 6 are schematic diagrams of an embodiment of the present invention applied at a T-junction. Figures 7 to 9 are schematic diagrams of an embodiment of the present invention applied at an intersection. Figures 10 to 12 are schematic diagrams of an embodiment of the present invention applied in an underground parking lot.

10: Self-driving car route planning system

11: Car host

12: Sensor

13: Bird's-eye view generation module

14: Category detection module

15: Lane center calculation module

16: Front vehicle prediction module

17: Path planning module

Claims (23)

A route planning system for a self-driving vehicle is provided on a vehicle, and the route planning system for the self-driving vehicle includes: At least one sensor for detecting the surrounding environment information of the vehicle; A bird's-eye view generation module, connected to the at least one sensor, receives the surrounding environment information and converts it into a bird's-eye view, and the bird's-eye view includes the coordinate information of each landmark; A category detection module, connected to the bird's-eye view generation module, determines and marks the lane edge, lane line and other vehicles in the bird's-eye view according to the coordinate information; A lane center calculation module, connected to the category detection module, finds a feasible driving range based on the lane edges and lane lines marked in the bird's-eye view, calculates a lane center point, finds a leading vehicle from other vehicles based on the lane center point and the position of the vehicle, and calculates the speed of the leading vehicle based on the position of the leading vehicle; A leading vehicle prediction module, connected to the category detection module and the lane center calculation module, estimates a predicted path of the leading vehicle through a vehicle kinematic model; and A path planning module is connected to the preceding vehicle prediction module. If the predicted path of the preceding vehicle is the same as the driving path of the vehicle, the preceding vehicle is used as a path reference point. If the predicted path of the preceding vehicle is different from the driving path of the vehicle or there is no preceding vehicle, the lane edge is used as a path reference line to calculate the final path of the vehicle. A route planning system for a self-driving vehicle as described in claim 1, wherein the at least one sensor is a lidar. A route planning system for a self-driving vehicle as described in claim 2, wherein the at least one sensor presents the surrounding environment information of the vehicle in the form of a point cloud image, and the bird's-eye view generation module then uses a rotation formula to convert the point cloud image into the bird's-eye view image. A self-driving vehicle route planning system as described in claim 1, wherein the coordinate information includes a shape formed by the coordinate points, a density of points, a height of an object formed by the coordinate points, or an echo intensity value of each coordinate point. A self-driving route planning system as described in claim 4, wherein the echo intensity value is preset to have multiple intervals, and the coordinate points of the echo intensity values in different intervals are displayed on the bird's-eye view in different colors. The route planning system for a self-driving vehicle as described in claim 4, wherein the category detection module filters the coordinate information to filter out noise, and then determines the lane edges, lane lines and other vehicles in the bird's-eye view based on the echo intensity values. A self-driving vehicle path planning system as described in claim 6, wherein the category detection module utilizes a Kalman filter to filter the coordinate information. The self-driving route planning system as described in claim 1, wherein the lane center calculation module finds a feasible driving range based on the lane edge and lane line in the bird's-eye view, and then takes the center points of two adjacent lane lines in the feasible driving range as the lane center point, or takes the average value of the lane line and the lane edge as the lane center point. A self-driving route planning system as described in claim 1, wherein after the lane center calculation module obtains the position of the leading vehicle, it calculates the speed of the leading vehicle based on the position of the leading vehicle in at least two bird's-eye views at continuous time. As described in claim 9, the path planning system for self-driving vehicles, wherein the preceding vehicle prediction module further establishes a driving behavior interest area through the marked lane line, and then predicts the behavior of the preceding vehicle based on the predicted path and the driving behavior interest area, including going straight or turning. In the path planning system for a self-driving vehicle as described in claim 1, when the predicted path of the leading vehicle is the same as the driving path of the vehicle, the path planning module uses the leading vehicle as the path reference point and combines it with the position of the vehicle and the center point of the lane line and the speed of the leading vehicle to calculate the final path of the vehicle. In the path planning system for a self-driving vehicle as described in claim 1, when the predicted path of the preceding vehicle is different from the driving path of the vehicle, the path planning module uses the lane edge as the path reference line and calculates an edge curvature using the path reference line to calculate the final path of the vehicle. A method for planning a path for a self-driving vehicle comprises the following steps: Using at least one sensor to detect the surrounding environment information of a vehicle; Converting the surrounding environment information into a bird's-eye view, the bird's-eye view including the coordinate information of each landmark; Identifying and marking the lane edges, lane lines and other vehicles in the bird's-eye view based on the coordinate information; Calculating a lane center point based on the marked lane edges and lane lines in the bird's-eye view, finding a leading vehicle from other vehicles based on the lane center point and the position of the vehicle, and then calculating the speed of the leading vehicle based on the position of the leading vehicle; Estimate a predicted path of the leading vehicle through a vehicle kinematic model; and If the predicted path of the preceding vehicle is the same as the driving path of the vehicle, the preceding vehicle is used as a path reference point. If the predicted path of the preceding vehicle is different from the driving path of the vehicle or there is no preceding vehicle, the lane edge is used as a path reference line to calculate the final path of the vehicle. A route planning method for a self-driving vehicle as described in claim 13, wherein the surrounding environment information of the vehicle is presented in a point cloud image, and a rotation formula is used to convert the point cloud image into the bird's-eye view. A method for self-driving vehicle route planning as described in claim 13, wherein the coordinate information includes a shape formed by the coordinate points, a density of points, a height of an object formed by the coordinate points, or an echo intensity value of each coordinate point. A route planning method for a self-driving vehicle as described in claim 15, wherein the echo intensity value is preset to have multiple intervals, and the coordinate points of the echo intensity values in different intervals are displayed on the bird's-eye view in different colors. A method for self-driving vehicle route planning as described in claim 16, wherein the echo intensity values are filtered to remove noise, and then the lane edges, lane lines and other vehicles in the bird's-eye view are identified based on the coordinate information. A method for autonomous vehicle path planning as described in claim 17, wherein the coordinate information is filtered using a Kalman filter. A method for self-driving vehicle route planning as described in claim 13, wherein the calculation of the lane center point comprises the following steps: Finding a feasible driving range based on the lane edge and lane line in the bird's-eye view; and In the feasible driving range, taking the center points of two adjacent lane lines as the lane center point, or taking the average value of the lane line and the lane edge as the lane center point. The route planning method for a self-driving vehicle as described in claim 13, wherein the step of calculating the speed of the preceding vehicle based on the position of the preceding vehicle further includes the following steps: Calculating the speed of the preceding vehicle based on the position of the preceding vehicle in at least two consecutive bird's-eye views. The path planning method for a self-driving vehicle as described in claim 13, wherein the step of estimating a predicted path of the preceding vehicle through the vehicle kinematic model further includes the following steps: Establishing a driving behavior interest region through the marked lane line, and then predicting the behavior of the preceding vehicle based on the predicted path and the driving behavior interest region, including going straight or turning. As described in claim 13, in the path planning method for a self-driving vehicle, when the predicted path of the preceding vehicle is the same as the driving path of the vehicle, the preceding vehicle is used as the path reference point, and is combined with the position of the vehicle and the center point of the lane line and the speed of the preceding vehicle to calculate the final path of the vehicle. As described in claim 13, in the path planning method for a self-driving vehicle, when the predicted path of the preceding vehicle is different from the driving path of the vehicle, the edge of the lane is used as the path reference line, and an edge curvature is calculated using the path reference line to calculate the final path of the vehicle.

Images