Method, apparatus and storage medium for planning a path of a vehicle

Abstract

The application discloses a method, device and storage medium for planning a path of a vehicle. The method comprises the following steps: acquiring first lateral position information of the vehicle at a current time and second lateral position information of the vehicle at a future time; determining a parameter of a planned path of the vehicle based on the first lateral position information and the second lateral position information, wherein the planned path is used to represent a path with the minimum risk of collision between the vehicle and surrounding obstacles of the vehicle during parking of the vehicle from the current time to the future time; and generating the planned path based on the parameter of the planned path and longitudinal position information of the vehicle at the future time. The application solves the technical problem of high risk of parking on the side of the lane.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a method, apparatus, and storage medium for planning a vehicle's path. Background Technology

[0002] Currently, when autonomous vehicles attempt to pull over to the side of the road, the least risky action of the autonomous driving assistance system is to pull over within the lane. However, there are still high-risk technical issues during the process of pulling over to the side of the road.

[0003] There is currently no effective solution to the high-risk technical problems that arise when vehicles are parked on the side of the road. Summary of the Invention

[0004] This invention provides a method, apparatus, and storage medium for planning vehicle routes, to at least address the technical problem of high risk during vehicle parking.

[0005] According to one aspect of the present invention, a method for planning a vehicle path is provided. The method includes: acquiring first lateral position information of the vehicle at a current time and second lateral position information at a future time; determining parameters of the planned path of the vehicle based on the first and second lateral position information, wherein the planned path represents the path with the lowest risk of collision with surrounding obstacles during the vehicle's parking process from the current time to a future time; and generating the planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at the future time.

[0006] Optionally, before acquiring the vehicle's first lateral position information at the current moment and the second lateral position information at a future moment, the method further includes: acquiring the vehicle's first driving speed at the current moment; in response to the first driving speed being greater than the second driving speed at a future moment when the vehicle travels along the planned path, reducing the first driving speed to the second driving speed; in response to the vehicle being within the coverage area of ​​a high-precision map, determining the vehicle's safe parking area based on the distance information between the vehicle's current position and the safe parking area, and the remaining length information of the safe parking area, and driving into the safe parking area, wherein the safe parking area includes at least one of the following: an emergency parking lane, an emergency lane, and the remaining length information is the length of the safe parking area excluding the vehicle when the vehicle enters the safe parking area.

[0007] Optionally, before obtaining the vehicle's first driving speed at the current moment, the method further includes: requesting the vehicle's planned path in response to the vehicle's driving object being in an abnormal state and / or the vehicle being in a fault state.

[0008] Optionally, obtaining the vehicle's first lateral position information at the current moment and the second lateral position information at a future moment includes: detecting the vehicle's first distance relative to the boundary line of the safe parking area in the coordinate system at the current moment, wherein the first lateral position information includes the first distance; and determining, based on the first distance, the vehicle's second distance relative to the boundary line of the safe parking area in the coordinate system at a future moment, wherein the second lateral position information includes the second distance.

[0009] Optionally, the parameters of the planned path of the vehicle are determined based on the first lateral position information and the second lateral position information, including: performing linear processing or derivative processing on the planned path of the vehicle using the first lateral position information and the second lateral position information to obtain the parameters of the planned path.

[0010] Optionally, after generating the planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at future times, the method further includes: integrating the derivative of the planned path of the vehicle within a longitudinal position information threshold and a range of longitudinal position information to obtain a comfort index of the planned path, wherein the longitudinal position information threshold is the longitudinal position information of the vehicle at the current time, and the comfort index is used to characterize the speed at which the vehicle enters the safe parking area; integrating the square of the minimum risk parking path of the vehicle within a range of longitudinal position information threshold and longitudinal position information to obtain a lane-changing result of the planned path, wherein the lane-changing result is used to characterize the distance between the first lateral position information at the current time and the second lateral position information at a future time according to the planned path; and performing linear processing on the comfort index, comfort index coefficient, lane-changing result, and lane-changing result coefficient to obtain an evaluation result of the planned path.

[0011] Optionally, after generating the planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at future times, the method further includes: controlling the vehicle to park according to the planned path of the vehicle, and obtaining the first distance of the vehicle relative to the boundary line of the safe parking area in the coordinate system at the current time, and the second distance of the vehicle's lateral distance to the boundary line of the safe parking area at the current time.

[0012] If the difference between the first distance and the second distance is less than the lateral distance threshold and the derivative of the first distance is less than the lateral angle threshold of the vehicle, it is determined that the vehicle has stopped parking according to the planned path.

[0013] According to another aspect of the present invention, an autonomous driving decision-making device for a vehicle is also provided, comprising: a first acquisition unit, configured to acquire first lateral position information of the vehicle at the current time and second lateral position information at a future time; a determination unit, configured to determine parameters of a planned path of the vehicle based on the first lateral position information and the second lateral position information, wherein the planned path represents the path with the lowest risk of collision with surrounding obstacles during the vehicle's parking process from the current time to a future time; and a generation unit, configured to generate a planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at a future time.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the vehicle path planning method of the present invention.

[0015] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program executes the vehicle path planning method of the present invention during runtime.

[0016] In this embodiment of the invention, a first lateral position information of the vehicle at the current moment and a second lateral position information at a future moment are obtained. Based on the first and second lateral position information, parameters of the vehicle's planned path are determined, wherein the planned path represents the path with the lowest risk of collision with surrounding obstacles during the vehicle's parking process from the current moment to the future moment. Based on the parameters of the planned path and the vehicle's longitudinal position information at the future moment, the planned path is generated. In other words, this embodiment of the invention obtains the first and second lateral position information of the vehicle at the current moment and the second lateral position information at the future moment, obtains the parameters of the vehicle's planned path based on the first and second lateral position information, and generates the planned path based on the parameters of the planned path and the vehicle's longitudinal position information at the future moment. This achieves the goal of making the vehicle more reliable and safer during parallel parking, solves the technical problem of high risk during parallel parking, and achieves the technical effect of reducing the risk of parallel parking. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 This is a flowchart of a vehicle path planning method according to an embodiment of the present invention;

[0019] Figure 2This is a flowchart of a minimum risk strategy working method according to an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of a path planning method according to an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of a vehicle route planning device according to an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] Example 1

[0025] According to an embodiment of the present invention, a method for planning a vehicle path is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] Figure 1 This is a flowchart of a vehicle path planning method according to an embodiment of the present invention, such as... Figure 1 As shown, the method may include the following steps:

[0027] Step S101: Obtain the vehicle's first lateral position information at the current moment and the second lateral position information at a future moment.

[0028] In the technical solution provided by step S101 of the present invention, the vehicle's path planning module calculates the vehicle's first lateral position at the current moment and the second lateral position at the future moment in the coordinate system based on the lane line information and road edge information sent by the vehicle's environmental perception module, as well as the emergency stopping lane edge information and emergency lane edge information sent by the high-precision map positioning module. The coordinate system includes a curvilinear coordinate system, which is a Frenet coordinate system. The first lateral position information includes the relative lateral distance, relative lateral velocity, and relative lateral acceleration between the vehicle and the path reference in the emergency stopping lane or emergency lane at the current moment. The second lateral position information includes the lateral distance, lateral velocity, and lateral acceleration of the vehicle at the stopping point.

[0029] Step S102: Based on the first lateral position information and the second lateral position information, determine the parameters of the vehicle's planned path, wherein the planned path is used to represent the path with the lowest risk of collision with surrounding obstacles during the vehicle's parking process from the current time to a future time.

[0030] In the technical solution provided by step S102 of the present invention, the planned path can be represented by a polynomial, wherein the polynomial can be a fifth-degree polynomial. The relative lateral distance, relative lateral velocity and relative lateral acceleration in the first lateral position are substituted into the fifth-degree polynomial, and the lateral distance, lateral velocity and lateral acceleration in the second lateral position are substituted into the fifth-degree polynomial. The coefficients of the fifth-degree polynomial are obtained by solving the system of equations simultaneously. The coefficients of the fifth-degree polynomial are the parameters of the path planning.

[0031] Step S103: Generate a planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at future times.

[0032] In the technical solution provided by step S103 of the present invention, the parameters of the planned path can be the coefficients of a fifth-order polynomial, and the longitudinal distance in the longitudinal position information of the vehicle at a future time is the independent variable of the fifth-order polynomial. Based on the coefficients and independent variables of the fifth-order polynomial, the planned path of the vehicle from the current time to the future time is generated.

[0033] In the embodiments of this invention, steps S101 to S103 above involve obtaining the vehicle's first lateral position information at the current moment and its second lateral position information at a future moment; determining the parameters of the vehicle's planned path based on the first and second lateral position information, wherein the planned path represents the path with the lowest risk of collision with surrounding obstacles during the vehicle's parking process from the current moment to the future moment; and generating the planned path based on the parameters of the planned path and the vehicle's longitudinal position information at the future moment. In other words, the embodiments of this invention obtain the vehicle's first lateral position information at the current moment and its second lateral position information at a future moment, obtain the parameters of the vehicle's planned path based on the first and second lateral position information, and generate the planned path based on the parameters of the planned path and the vehicle's longitudinal position information at the future moment. This achieves the goal of making the vehicle's parking process more reliable and safer, solving the technical problem of high risk during parking and achieving the technical effect of reducing the risk of parking.

[0034] The method described in this embodiment will be further described below.

[0035] As an optional embodiment, step 101, before acquiring the vehicle's first lateral position information at the current moment and the second lateral position information at a future moment, further includes: acquiring the vehicle's first driving speed at the current moment; in response to the first driving speed being greater than the second driving speed of the vehicle traveling along the planned path at a future moment, reducing the first driving speed to the second driving speed; in response to the vehicle being within the coverage area of ​​a high-precision map, determining the vehicle's safe parking area based on the distance information between the vehicle's current position and the safe parking area, and the remaining length information of the safe parking area, and driving into the safe parking area, wherein the safe parking area includes at least one of the following: an emergency parking lane, an emergency lane, and the remaining length information is the length of the safe parking area excluding the vehicle when driving into the safe parking area.

[0036] In this embodiment, when the vehicle's path planning decision module receives a trigger command from the vehicle's minimum risk path planning strategy module, the vehicle's speed sensor acquires the vehicle's first driving speed at the current moment. If the vehicle's first driving speed is greater than the second driving speed for future travel along the planned path, a deceleration command is sent to the vehicle's path planning decision module, causing the vehicle to decelerate from the first driving speed to the second driving speed. When the vehicle is traveling within the coverage area of ​​the high-precision map positioning system, the vehicle's path planning decision module selects an emergency lane or emergency stopping lane for parking based on the distance information between the vehicle and the current emergency stopping lane or emergency lane, as well as the remaining length information. When the vehicle is close to the emergency stopping lane... The vehicle will travel at the second speed and then pull over to the side of the road when it reaches the emergency stopping lane area. If the vehicle's driving area is not covered by the high-precision map positioning system, the vehicle's path planning and decision-making module will select the side of the road to pull over based on the roadside information provided by the vehicle's perception module. If the vehicle's perception module cannot provide effective roadside information, the vehicle's path planning and decision-making module will select one side of the lane to pull over based on the lane line information provided by the vehicle's perception module. If the vehicle's perception module determines that there are no dynamic obstacles on the side of the vehicle's current parking direction that pose a collision risk, and there are no static obstacles in front that would obstruct the parking action, the vehicle's path planning and decision-making module will initiate the parking action; otherwise, the vehicle will remain in the current lane at a low speed.

[0037] For example, when the vehicle's path planning decision module receives a trigger command from the vehicle's minimum risk path planning strategy module, the vehicle's speed sensor obtains the vehicle's first driving speed at the current moment, which is 60 kilometers per hour. The vehicle's path planning decision module determines the second driving speed for the vehicle to travel along the planned path in the future as 20 kilometers per hour. When the vehicle is traveling in the area covered by the high-precision map positioning system, the vehicle's visual camera obtains that the longitudinal distance between the vehicle and the emergency stopping lane is 10 meters. When the remaining length of the emergency stopping lane is 60 meters, the emergency stopping lane parking action is triggered, and the vehicle's first driving speed is adjusted to decelerate to the second driving speed to park on the side of the road.

[0038] As an optional embodiment, before obtaining the vehicle's first driving speed at the current moment, the method further includes: requesting the vehicle's planned path in response to the vehicle's driving object being in an abnormal state and / or the vehicle being in a fault state.

[0039] In this embodiment, the driver's status information is abnormal or the vehicle is in a faulty state. The driver's status information may include at least one of the following: driver's gaze direction, eye movement information, and hand grip on the steering wheel. If the driver's gaze direction is sufficient for normal driving task monitoring, the driver's eye movement maintains a normal blinking frequency, and the driver grips the steering wheel with reasonable force, then the driver's status is judged to be normal. If any of these items is abnormal, then the driver's status is judged to be abnormal. The vehicle being in a faulty state includes: tire pressure warning, sensor malfunction, etc., which are only examples and are not specific limitations.

[0040] As an optional implementation, step S101, obtaining the vehicle's first lateral position information at the current moment and the second lateral position information at a future moment, includes: detecting the vehicle's first distance relative to the boundary line of the safe parking area in the coordinate system at the current moment, wherein the first lateral position information includes the first distance; and determining, based on the first distance, the vehicle's second distance relative to the boundary line of the safe parking area in the coordinate system at a future moment, wherein the second lateral position information includes the second distance.

[0041] In this embodiment, the vehicle's camera senses a first distance relative to the boundary line of the safe parking area in the coordinate system at the current moment. The vehicle's path planning and decision-making module determines a second distance relative to the boundary line of the safe parking area in the coordinate system at a future moment, corresponding to the first distance, based on the relationship between the first distance and a preset distance between the vehicle and the boundary line of the safe parking area. The preset distance between the vehicle and the boundary line of the safe parking area can be at least one of the following: the distance between the target location and the boundary line of the safe parking area, the distance between the second boundary line and the boundary line of the safe parking area, the second boundary line being to the left of the target location, the distance between the first boundary line and the boundary line of the safe parking area, or the second boundary line being to the left of the first boundary line.

[0042] As an optional implementation, step S102, which determines the parameters of the vehicle's planned path based on the first lateral position information and the second lateral position information, includes: performing linear processing or derivative processing on the vehicle's planned path using the first lateral position information and the second lateral position information to obtain the parameters of the planned path.

[0043] In this embodiment, when the longitudinal position information of the vehicle in the planned path at a future time is at the starting position, the planned path is linearly processed or differentiated using the first lateral position information to obtain three identities; when the longitudinal position information of the vehicle in the planned path at a future time is not at the starting position, the planned path is linearly processed or differentiated using the second lateral position information to obtain three identities. The six identities are processed to obtain the parameters of the planned path, wherein the planned path of the vehicle is represented by a fifth-degree polynomial.

[0044] For example, when the longitudinal position of the vehicle in the planned path is at the starting position at a future time, the relative lateral distance is equal to parameter one of the fifth-degree polynomial equation for the planned path. The first derivative of the fifth-degree polynomial equation for the planned path is equal to parameter two of the planned path, where parameter two is equal to the relative lateral velocity. The second derivative of the fifth-degree polynomial equation for the planned path is equal to parameter three of the planned path, where parameter three is equal to the relative lateral acceleration. When the longitudinal position of the vehicle in the planned path is not at the starting position at a future time, the lateral distance is equal to the fifth-degree polynomial equation. The first derivative of the fifth-degree polynomial equation is equal to the lateral velocity, and the second derivative of the fifth-degree polynomial equation is equal to the lateral acceleration. Substituting parameters one, two, and three into the fifth-degree polynomial equation and solving them simultaneously yields parameters four, five, and six.

[0045] As an optional implementation, in step S103, after generating the planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at future times, the method further includes: integrating the derivative of the planned path of the vehicle within the longitudinal position information threshold and the longitudinal position information range to obtain a comfort index of the planned path, wherein the longitudinal position information threshold is the longitudinal position information of the vehicle at the current time, and the comfort index is used to characterize the speed at which the vehicle enters the safe parking area; integrating the square of the minimum risk parking path of the vehicle within the longitudinal position information threshold and the longitudinal position information range to obtain a lane-changing result of the planned path, wherein the lane-changing result is used to characterize the distance between the first lateral position information at the current time and the second lateral position information at a future time according to the planned path; and performing linear processing on the comfort index, comfort index coefficient, lane-changing result, and lane-changing result coefficient to obtain an evaluation result of the planned path.

[0046] In this embodiment, the derivative of the planned path of the vehicle is integrated within the longitudinal position information threshold and the longitudinal position information range to obtain the comfort index of the planned path. The longitudinal position information threshold is the longitudinal position information of the vehicle at the current moment, defined as 0. The comfort index is the speed at which the driver turns the steering wheel when the vehicle enters the safe parking area, i.e., the vehicle speed. In response to the square of the vehicle's minimum risk parking path within the longitudinal position information threshold and the longitudinal position information range, the square of the vehicle's minimum risk parking path is integrated to obtain the lane-changing result of the planned path. The lane-changing result represents the distance between the vehicle's first lateral position information at the current moment and its second lateral position information at a future moment according to the planned path. The product of the comfort index and the comfort index coefficient is the first product, and the product of the lane-changing result and the lane-changing result coefficient is the second product. The first and second products are summed to obtain the evaluation result of the planned path.

[0047] As an optional implementation, in step S103, after generating the planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at future times, the method further includes: controlling the vehicle to park according to the planned path, and obtaining a first distance of the vehicle relative to the boundary line of the safe parking area in the coordinate system at the current time, and a second distance of the vehicle's lateral distance to the boundary line of the safe parking area at the current time; in response to the difference between the first distance and the second distance being less than a lateral distance threshold and the derivative of the first distance being less than a lateral angle threshold of the vehicle, determining that the parking of the vehicle according to the planned path has ended.

[0048] In this embodiment, when the vehicle stops parking, the determination is based on the vehicle's current lateral relative position information. If the difference between the distance of the vehicle at the current moment relative to the boundary line of the safe parking area in the coordinate system and the shortest distance between the vehicle's current lateral distance and the boundary line of the safe parking area is less than the lateral distance threshold and the absolute value of the derivative of the first lateral distance is less than the vehicle's lateral angle threshold, then the vehicle stops parking and is in a state of minimum risk.

[0049] In this embodiment of the invention, in response to the vehicle being in an abnormal state or the vehicle being in a faulty state, a planned path for the vehicle is requested, and the vehicle's first driving speed at the current moment is obtained. In response to the first driving speed being greater than a second driving speed for the vehicle to travel along the planned path in a future time period, the first driving speed is reduced to the second driving speed. In response to the vehicle being within the coverage area of ​​a high-precision map, based on the distance information between the vehicle's current position and the safe parking area, and the remaining length information of the safe parking area, the vehicle's safe parking area is determined and the vehicle enters the safe parking area. Parameters for the vehicle's path planning into the parking area are obtained. Based on the parameters of the planned path and the vehicle's longitudinal position information in a future time period, a planned path is generated, and the planned path is evaluated. This solves the technical problem of high risk during the process of parking a vehicle on the side of the road, and achieves the technical effect of reducing the risk of parking a vehicle on the side of the road.

[0050] Example 2

[0051] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0052] With the development of intelligent driving technology, advanced driver assistance systems (ADAS) are increasingly being applied to vehicles, reducing the driving intensity for drivers. However, most mass-produced autonomous driving systems are at Level 2 or lower, requiring drivers to monitor the environment throughout the process and take over driving when necessary. If the driver does not respond to the takeover request, the ADAS will automatically execute the least-risk action. Currently, the least-risk action of most autonomous driving assistance systems adopts the solution of stopping within the lane. This solution has a high safety risk in scenarios such as highways. How to utilize limited upstream module information to achieve safe and reliable least-risk actions is of great significance for autonomous driving assistance systems.

[0053] Therefore, in order to overcome the above problems, a quadratic programming method for parking on the side of the road based on path planning has been proposed in a related technology. This method obtains constraint information based on lane and road edge based on the environmental perception module, and then establishes and solves a quadratic programming problem to obtain the parking path. This planning method based on numerical optimization has high requirements for system computing power and high accuracy in identifying road edge boundaries. It does not consider the impact of possible identification errors on the path planning results during the parking process, and there is a high risk of collision with the road boundary during the parking process.

[0054] In another related technology, a vehicle control method, device, and vehicle based on driver status are proposed. This method acquires driver vital sign information using sensing devices and performs deceleration and parking maneuvers when an abnormality is detected. While this invention considers using the rightmost lane information and roadside facilities such as guardrails as parking references in the selection of road boundary references, it does not consider the use of emergency stopping lanes on highways and does not utilize high-precision map positioning information for reasonable parking location selection, posing certain risks when applied to highways.

[0055] In another related technology, an autonomous vehicle control method is proposed. This method determines whether the main control module's operating state is abnormal based on vehicle state information detected by a fault detection module. When an abnormality is determined, an auxiliary control module is used to obtain the fault scenario and the fault problem encountered by the autonomous vehicle. The driving state of the autonomous vehicle is then controlled according to the control strategy determined by the auxiliary control module based on the fault scenario and the fault problem. This scheme divides the minimum risk strategy into three strategies based on different fault scenarios: pulling over to the side of the road within the safe speed limit, taking emergency braking, and emergency stopping within the safe speed limit. This scheme only considers emergency strategies when the vehicle and the autonomous driving system itself malfunction, without taking into account the driver's state information requirements for the minimum risk strategy. Therefore, this method is not suitable for Level 3 and above autonomous driving assistance systems.

[0056] However, this invention proposes a minimum risk strategy implementation method that utilizes limited upstream module information to achieve safe and reliable minimum risk actions for parking at the side of the road.

[0057] Figure 2 This is a flowchart of a minimum risk strategy working method according to an embodiment of the present invention, such as... Figure 2 As shown, the method may include the following steps:

[0058] Step S201, trigger the minimum risk action.

[0059] When the driver activates the autonomous driving assistance system, the vehicle's status monitoring module continuously monitors driver status information and vehicle fault information. Driver status information includes: driver's gaze direction, eye movements, and hand position on the steering wheel. If the driver's gaze direction is sufficient for normal driving task monitoring, the driver's eye movements maintain a normal blinking frequency, and the driver's hand position on the steering wheel is within a reasonable range, then the driver's status is considered normal. If any of these aspects are abnormal, the driver's status is considered abnormal. The autonomous driving system monitors whether the current scenario is within the system's designed operating range and simultaneously monitors vehicle fault information. If the vehicle's current driving scenario is outside the system's designed operating range or if abnormal information is reported in the vehicle fault information report, such as tire pressure warning or sensor malfunction, then the system's functional availability is considered abnormal; otherwise, the system's functional availability is considered normal. If any of the above driver status or functional availability information is abnormal, the minimum risk strategy is triggered; otherwise, the system maintains normal autonomous driving status.

[0060] Step S202: Select the appropriate action with the lowest risk.

[0061] When the vehicle's minimum risk strategy decision-making module receives a request to trigger the minimum risk strategy action, the high-precision map positioning module and the environmental perception module provide current driving environment information. This driving environment information includes: target information such as the position, size, speed, yaw angle, and acceleration of vehicles and pedestrians around the vehicle; high-precision map positioning information such as the nearest distance to the vehicle from the emergency lane / emergency stopping lane ahead, as well as the length and width of the emergency lane or emergency stopping lane, and corresponding road boundary information expressed using polynomials or discrete point sequences; lane line and curb information such as lane line information on the left and right sides of the vehicle, and curb information on the left and right sides, which can be represented by polynomial equations / discrete point sequences; and vehicle status information such as vehicle speed, acceleration or deceleration, hazard warning light status, and vehicle width.

[0062] When the vehicle's decision module receives the minimum risk strategy trigger command, it first checks the vehicle's current speed. If the vehicle's current speed is greater than the minimum risk strategy action speed, it sends a deceleration command to bring the vehicle's current speed down to the minimum risk strategy action speed. The vehicle's decision module then selects the appropriate minimum risk action based on the current environmental information.

[0063] Optionally, the decision-making process is as follows: (1) If the vehicle is currently traveling within the coverage area of ​​the high-precision map positioning system, the vehicle decision module determines that if the distance between the vehicle and the current emergency stopping lane is less than 10 meters and the length of the emergency stopping lane is greater than 50 meters, the vehicle stops in the emergency stopping lane. When parking is permitted on the rear side of the emergency stopping lane, the vehicle begins to stop. (2) If the vehicle is currently traveling within the coverage area of ​​the high-precision map positioning system, the vehicle decision module determines that if the distance between the vehicle and the current emergency stopping lane is less than 200 meters and the length of the emergency stopping lane is greater than 50 meters, the vehicle maintains a low speed. (3) If the vehicle is currently traveling within the coverage area of ​​the high-precision map positioning system, the vehicle decision module determines that if the distance between the vehicle and the emergency lane is less than 10 meters and the length of the emergency stopping lane is greater than 50 meters, the vehicle stops in the emergency lane. When parking is permitted on the rear side of the emergency lane, the vehicle begins to stop. (4) If the vehicle is currently traveling within the coverage area of ​​the high-precision map positioning system, the vehicle decision module determines that if the distance between the vehicle and the emergency lane is less than 200 meters and the length of the emergency stopping lane is greater than 50 meters, the vehicle maintains a low speed. (5) When the current vehicle driving area is not covered by the high-precision map positioning system, the decision module selects the side parking action based on the roadside information provided by the perception module. If the perception module cannot provide effective roadside information, the decision module selects one side of the lane for side parking based on the lane line information provided by the perception module. If it is determined that there is no dynamic obstacle on the side of the vehicle's current parking direction that poses a collision risk, and there is no static obstacle in front that obstructs the parking action, the parking action is triggered. Otherwise, the vehicle remains in the current lane at a low speed.

[0064] Step S203: Generate the minimum risk driving trajectory.

[0065] The vehicle's minimum risk trajectory planning module selects path planning reference information based on the instructions from the decision module. The available path reference information includes: lane line information and roadside information sent by the environmental perception module, as well as emergency stopping lane edge information and emergency lane edge information sent by the high-precision map positioning module.

[0066] Since the side of the vehicle is usually a protruding curb or road divider that cannot be crossed during the parking maneuver, a polynomial parking path planning method with an offset endpoint is proposed to avoid the danger of the vehicle colliding with the road edge facilities due to factors such as control overshoot and perception recognition errors during the parking process.

[0067] First, based on the acquired path reference information, the vehicle's coordinates on the current reference path are calculated, and the lateral position information is obtained. Among them, d0, These are the relative lateral distance, relative lateral velocity, and relative lateral acceleration between the current vehicle and the path reference, respectively. Longitudinal position information. Among them, s0, These are the relative longitudinal distance, relative longitudinal velocity, and relative longitudinal acceleration between the current vehicle and the path reference, respectively.

[0068] Since the planning task only considers the parking path, to reduce the computational load of the minimum risk path planning process, it is assumed that the vehicle maintains a constant speed during the parking maneuver using the minimum risk strategy. The path planning task will then be simplified to lateral south-latitude path planning based on reference road information. During the sampling of the target state coordinates, the vehicle's current relative lateral position and the curvature information of the reference road are considered to offset the target sampling points. Figure 3 This is a schematic diagram of a path planning method according to an embodiment of the present invention, such as... Figure 3 As shown, the route planning may include:

[0069] When vehicle C is at the target position, the lateral distance between the target position and the reference road boundary is d. target d target =d safe +W / 2, where d safe The safe distance between the target location and the road boundary can be taken as 0.2m, and W is the width of the vehicle.

[0070] When vehicle B is between the second boundary and the target position, it can be assumed that the lateral distance between vehicle B and the second boundary and the road reference boundary is d. endbound d endbound =d target +d offset , where d offset This represents the lateral distance of the second boundary relative to the target position.

[0071] When vehicle A is between the first boundary and the second boundary, the lateral distance between vehicle A and the first boundary and the road reference boundary can be considered as d. startbound d startbound =d endbound +d gap , where d gap This represents the lateral distance between the first boundary and the second boundary.

[0072] When vehicle A is to the left of the first boundary, that is, when the current position of vehicle A is relative to the lateral distance d0 > d startbound At that time, set the horizontal position of the endpoint d1 = d endbound When vehicle B is between the first and second boundaries, that is, when vehicle B's current position is relative to the lateral distance d... startbound <d0<d endbound At that time, the endpoint lateral position d1 = d is set according to the current lateral position of the vehicle. target +d offset·(d0-d endbound ) / d gap When vehicle C is between the second boundary and the target position, that is, when the current position of vehicle C is relative to the lateral distance d0 < d endbound At that time, set the horizontal position of the endpoint d1 = d target .

[0073] Based on the above rules, the lateral position information of the endpoint of the docking action can be obtained. The lateral velocity at the endpoint Endpoint lateral acceleration All are set to 0.

[0074] The longitudinal position information of the endpoint is obtained using a sampling method. The initial longitudinal position of the endpoint is set as a series of sampling points, with the sampling range starting from s. start to min(s) end s valid ), where s start s is the set starting sampling longitudinal distance. end s is the set longitudinal distance for terminating sampling. valid The effective distance information of the reference road sent from upstream sensing and high-precision map positioning is used to perform longitudinal sampling at fixed longitudinal intervals Δs within the range from the start to the end, resulting in multiple sets of longitudinal endpoint position information. The longitudinal velocity at the endpoint End point longitudinal acceleration Set to 0.

[0075] Based on the above sampling endpoint information, the SL path from the current vehicle's starting position to the sampling endpoint position is calculated using a fifth-order polynomial, resulting in the following feasible path equation:

[0076] D(s) = P0 + P1s + P2s 2 +P3s 3 +P4s 4 +P5s 5

[0077] Where P0, P1, P2, P3, P4, and P5 are the coefficients of the polynomial equation for the planned path.

[0078] To select the optimal path for the vehicle to pull over, this invention establishes a path evaluation method to evaluate candidate paths:

[0079] Using information on the rate of change of lateral acceleration to measure the comfort cost of the path J t :

[0080]

[0081] The lane-changing efficiency of a movement path that approaches the edge is measured using the distance from the road boundary reference line.d :

[0082]

[0083] The overall cost of the edge action path is described as follows:

[0084] J = k t ·J t +k d ·J d

[0085] Where, k t k d These are the cost coefficients for comfort and efficiency costs, respectively.

[0086] Step S304: Issue vehicle control command.

[0087] Once the optimal stopping path is calculated, it is sent to the vehicle's control module, which converts it into vehicle control commands to execute the stopping maneuver. Path tracking control algorithms include, but are not limited to, pure tracking algorithms, linear quadratic regulators, advanced process control methods, and sliding mode control.

[0088] During the parking process, when the vehicle's current position meets the parking completion requirements, the minimum risk strategy module sends a deceleration request to slow the vehicle to a standstill, apply the parking brake, and activate the hazard warning lights. The parking completion determination is based on the vehicle's current lateral relative position information, and the determination method is as follows:

[0089]

[0090] Where, d dis d is the minimum lateral distance between the vehicle and the reference road boundary. deg The vehicle's lateral angle after parking marks the end of the minimum risk strategy execution process. The vehicle has completed the minimum risk strategy process based on the current environmental information and has reached the minimum risk state.

[0091] In this embodiment, when the vehicle is in an abnormal state or the vehicle is in a faulty state, the system requests the vehicle's planned path, obtains the vehicle's current speed, and if the speed exceeds the minimum risk strategy action speed, reduces the speed to the minimum risk strategy action speed. When the vehicle is within the coverage area of ​​a high-precision map, based on the distance information between the vehicle's current position and the safe parking area, and the remaining length information of the safe parking area, the system determines the safe parking area and drives into it. The system obtains the parameters for the path planning of the vehicle entering the parking area, and generates a planned path equation based on the parameters of the planned path and the vehicle's longitudinal endpoint position information. The planned path equation is then evaluated, thus solving the technical problem of high risk during the process of parking on the side of the road and achieving the technical effect of reducing the risk of parking on the side of the road.

[0092] Example 3

[0093] According to an embodiment of the present invention, a vehicle path planning device is also provided. It should be noted that this vehicle path planning device can be used to execute the vehicle path planning method in Embodiment 1.

[0094] Figure 4 This is a schematic diagram of a vehicle route planning device according to an embodiment of the present invention. Figure 4 As shown, the vehicle path planning device 400 may include: an acquisition unit 401, a determination unit 402, and a generation unit 403.

[0095] The first acquisition unit 401 is used to acquire the vehicle's first lateral position information at the current time and the second lateral position information at a future time.

[0096] The determining unit 402 is used to determine the parameters of the planned path of the vehicle based on the first lateral position information and the second lateral position information, wherein the planned path is used to represent the path with the lowest risk of collision with the vehicle's surrounding obstacles during the parking process from the current time to a future time.

[0097] The generation unit 403 is used to generate a planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at future times.

[0098] Optionally, the device further includes: a second acquisition unit, configured to acquire a first driving speed of the vehicle at the current moment before acquiring a first lateral position information of the vehicle at the current moment and a second lateral position information at a future moment; a first processing unit, configured to reduce the first driving speed to the second driving speed in response to the first driving speed being greater than the second driving speed of the vehicle traveling along the planned path at a future moment; and a second processing unit, configured to determine the safe parking area of ​​the vehicle and drive into the safe parking area based on the distance information between the vehicle's current position and the safe parking area and the remaining length information of the safe parking area in response to the vehicle being within the coverage area of ​​a high-precision map, wherein the safe parking area includes at least one of the following: an emergency parking lane or an emergency lane, and the remaining length information is the length of the safe parking area excluding the vehicle when the vehicle enters the safe parking area.

[0099] Optionally, the processing module is configured to request the planned path of the vehicle in response to the vehicle's driving object being in an abnormal state or the vehicle being in a fault state, before obtaining the vehicle's first driving speed at the current moment.

[0100] Optionally, the first acquisition unit 401 may include: a detection module, configured to detect a first distance of the vehicle relative to the boundary line of the safe parking area in the coordinate system at the current moment, wherein the first lateral position information includes the first distance; and a determination module, configured to determine a second distance of the vehicle relative to the boundary line of the safe parking area in the coordinate system at a future moment based on the first distance, wherein the second lateral position information includes the second distance.

[0101] Optionally, the determining unit 402 may include a processing module, used to perform linear processing or derivative processing on the planned path of the vehicle using the first lateral position information and the second lateral position information to obtain the parameters of the planned path.

[0102] Optionally, the device further includes: a third processing unit, used to generate a planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at a future time, and then integrate the derivative of the planned path of the vehicle within a longitudinal position information threshold and a range of longitudinal position information to obtain a comfort index of the planned path, wherein the longitudinal position information threshold is the longitudinal position information of the vehicle at the current time, and comfort is used to characterize the speed at which the vehicle enters the safe parking area; a fourth processing unit, used to integrate the square of the minimum risk parking path of the vehicle within a range of longitudinal position information threshold and longitudinal position information to obtain a lane-changing result of the planned path, wherein the lane-changing result is used to characterize the distance between the first lateral position information at the current time and the second lateral position information at a future time according to the planned path; and a fifth processing unit, used to perform linear processing on the comfort index, comfort index coefficient, lane-changing result, and lane-changing result coefficient to obtain an evaluation result of the planned path.

[0103] Optionally, the device further includes: a sixth processing unit, configured to, after generating a planned path based on parameters of the planned path and the longitudinal position information of the vehicle at a future time, control the vehicle to park according to the planned path, and obtain a first distance of the vehicle relative to the boundary line of the safe parking area in the coordinate system at the current time, and a second distance of the vehicle's lateral distance to the boundary line of the safe parking area at the current time; and a seventh processing unit, configured to, in response to the difference between the first distance and the second distance being less than a lateral distance threshold and the derivative of the first distance being less than a lateral angle threshold of the vehicle, determine that the parking of the vehicle according to the planned path has ended.

[0104] In this embodiment, the first acquisition unit is used to acquire the vehicle's first lateral position information at the current time and the second lateral position information at a future time; the determination unit is used to determine the parameters of the vehicle's planned path based on the first and second lateral position information, wherein the planned path represents the path with the lowest risk of collision with surrounding obstacles during the vehicle's parking process from the current time to the future time; the generation unit is used to generate the planned path based on the parameters of the planned path and the vehicle's longitudinal position information at the future time, thereby solving the technical problem of high risk during the vehicle's parallel parking process and achieving the technical effect of reducing the risk of the vehicle during parallel parking.

[0105] Example 4

[0106] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the storage medium including a stored program, wherein the program executes the vehicle path planning method of Embodiment 1.

[0107] Example 5

[0108] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program executes the vehicle path planning method in Embodiment 1 during runtime.

[0109] Example 6

[0110] According to an embodiment of the present invention, a vehicle is also provided for executing the vehicle path planning method in Embodiment 1 of the present invention.

[0111] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0117] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method of planning a path for a vehicle, characterized by, The method comprises: obtaining first lateral position information of the vehicle at a current time and second lateral position information of the vehicle at a future time; determining parameters of a planned path of the vehicle based on the first lateral position information and the second lateral position information, wherein the planned path is used to represent a path with the minimum risk of collision with surrounding obstacles of the vehicle during parking of the vehicle from the current time to the future time; generating the planned path based on the parameters of the planned path and longitudinal position information of the vehicle at the future time; obtaining first lateral position information of the vehicle at a current time and second lateral position information of the vehicle at a future time comprises: detecting a first distance of the vehicle at the current time relative to a boundary line of a safe parking area in a coordinate system, wherein the first lateral position information comprises the first distance; and determining a second distance of the vehicle at the future time relative to the boundary line of the safe parking area in the coordinate system corresponding to the first distance based on the first distance, wherein the second lateral position information comprises the second distance.

2. The method of claim 1, wherein, Before obtaining the first lateral position information of the vehicle at the current time and the second lateral position information of the vehicle at the future time, the method further comprises: obtaining a first driving speed of the vehicle at the current time; in response to the first driving speed being greater than a second driving speed of the vehicle driving along the planned path at the future time, reducing the first driving speed to the second driving speed; in response to the vehicle being in a high-precision map coverage range, determining a safe parking area of the vehicle based on distance information between a current position of the vehicle and the safe parking area and remaining length information of the safe parking area, and driving the vehicle into the safe parking area, wherein the safe parking area comprises at least one of the following information: an emergency parking lane and an emergency lane, and the remaining length information is a length of the safe parking area excluding the vehicle when the vehicle drives into the safe parking area.

3. The method of claim 2, wherein, Before obtaining the first driving speed of the vehicle at the current time, the method further comprises: in response to a driving object of the vehicle being in an abnormal state and / or the vehicle being in a fault state, requesting a planned path of the vehicle.

4. The method of claim 1, wherein, The method further comprises: performing linear processing or derivation processing on the planned path of the vehicle using the first lateral position information and the second lateral position information to obtain the parameters of the planned path.

5. The method of claim 1, wherein, After generating the planned path based on the parameters of the planned path and the longitudinal position information of the vehicle at the future time, the method further comprises: integrating the derivative of the planned path of the vehicle within a longitudinal position information threshold and a longitudinal position information range to obtain a comfort index of the planned path, wherein the longitudinal position information threshold is the longitudinal position information of the vehicle at the current time, and the comfort index is used to represent a speed of the vehicle entering the safe parking area. in response to the minimum risk parking path of the vehicle being within the longitudinal position information threshold and the longitudinal position information range, integrating the square of the minimum risk parking path of the vehicle to obtain a lane-changing result of the planning path, wherein the lane-changing result is used to represent a distance between a first lateral position information of the vehicle at a current time and a second lateral position information of the vehicle at a future time according to the planning path; linearly processing the comfort index, the comfort index coefficient, the lane-changing result and the lane-changing result coefficient to obtain an evaluation result of the planning path.

6. The method of any one of claim 5, wherein, After generating the planning path based on the parameters of the planning path and the longitudinal position information of the vehicle at the future time, the method further comprises: controlling the vehicle to park according to the planning path of the vehicle, and obtaining a first distance of the vehicle at the current time from a boundary line of a safe parking area in a coordinate system and a second distance of the vehicle at the current time from the boundary line of the safe parking area; in response to a difference between the first distance and the second distance being less than a lateral distance threshold and a derivative of the first distance being less than a lateral angle threshold of the vehicle, determining that the vehicle has finished parking according to the planning path of the vehicle.

7. A planned path device of a vehicle, characterized by, comprise: a first obtaining unit, configured to obtain a first lateral position information of a vehicle at a current time and a second lateral position information of the vehicle at a future time; a determining unit, configured to determine parameters of a planning path of the vehicle based on the first lateral position information and the second lateral position information, wherein the planning path is used to represent a path with a minimum risk of collision with surrounding obstacles of the vehicle during a parking process of the vehicle from the current time to the future time; a generating unit, configured to generate the planning path based on the parameters of the planning path and a longitudinal position information of the vehicle at the future time. The first obtaining unit is further configured to obtain the first lateral position information of the vehicle at the current time and the second lateral position information of the vehicle at the future time by: detecting a first distance of the vehicle at the current time from a boundary line of a safe parking area in a coordinate system, wherein the first lateral position information comprises the first distance; and determining a second distance of the vehicle at the future time from the boundary line of the safe parking area in the coordinate system corresponding to the first distance based on the first distance, wherein the second lateral position information comprises the second distance.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program controls a device in which the computer readable storage medium is located to execute the method in any one of claims 1 to 6 when the program is running.

9. A vehicle characterized by comprising: The vehicle is configured to execute the method in any one of claims 1 to 6.

Images