Automatic driving path planning method, device, equipment and medium

Abstract

The present invention provides a method, apparatus, device, and medium for autonomous driving path planning. The method comprises: obtaining environmental information, including target vehicle motion parameters and target vehicle position information; establishing a cost function, including mass cost, reference line cost, smoothing cost, and center cost; establishing constraints for the cost function, and calculating a target driving path corresponding to the target vehicle based on the cost function and the constraints. The present invention can add consideration of the cost of target vehicle mass to the path planning problem of active lane change, proposes a definition of the cost function and constraints for the path optimization problem, accurately models the total cost function, utilizes nonlinear optimization to obtain an exact solution, and obtains an optimized path through real-time constraint verification. This improves the driving safety of autonomous driving vehicles with large mass and high center of mass, such as commercial vehicles, in road cornering scenarios.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to an autonomous driving path planning method, device, equipment and medium. Background Art

[0002] For point-to-point autonomous driving tasks on structured roads such as highways, in addition to basic lateral lane keeping and longitudinal adaptive cruise control, autonomous vehicles are also required to have the ability to automatically enter and exit ramps, actively switch interactive driving, and actively overtake and change lanes. Although many patents have been published for the path planning problem of active lane change in autonomous driving, such as Chinese patent CN202211363523.3, which discloses an autonomous driving control method based on driver characteristics, the method uses a first controller and a second controller to consider the impact of driver characteristics on autonomous driving in multiple scenarios and dimensions, thereby controlling the vehicle's driving parameters. However, the lane change path planning methods in the prior art only cover all driving scenarios in a general way. In the case of road curves, for autonomous driving vehicles with larger mass and higher center of mass positions, such as commercial vehicles, if the mass of the vehicle is not taken into account during the path planning process of the lane change process, it is easy to cause the vehicle to roll over when changing lanes, posing a potential driving safety hazard. Summary of the Invention

[0003] In view of the above shortcomings of the prior art, the present invention provides an autonomous driving path planning method to solve the above technical problems.

[0004] The present invention provides an autonomous driving path planning method, comprising:

[0005] Acquiring environmental information, including target vehicle motion parameters and target vehicle position information;

[0006] Establish a cost function, which includes quality cost, reference line cost, smoothing cost and center cost. The quality cost is obtained based on the target vehicle motion parameters, and the reference line cost, smoothing cost and center cost are all obtained based on the target vehicle position information.

[0007] Constraints are established for the cost function, and the target driving path corresponding to the target vehicle is calculated based on the cost function and the constraints. In one embodiment of the present invention, based on the above scheme, the cost function is:

[0008] J=J ref +J smooth +J mid +J m ,

[0009] Among them, J is the cost function, J ref is the reference line cost, J smooth is the smoothing cost, J midFor the central price, J m The price of quality.

[0010] In one embodiment of the present invention, based on the above solution, the reference line cost formula is:

[0011]

[0012] The smoothing cost formula is:

[0013]

[0014] The central cost formula is:

[0015]

[0016] The target vehicle mass cost formula is:

[0017] J m =w cost_m m,

[0018] Among them, w cost_ref is the weight coefficient of the reference line cost, l i is the lateral displacement of the vehicle's center of mass at point i from the road centerline, l i+1 is the lateral displacement of the vehicle's center of mass from the road centerline at the point below point i along the vehicle's forward direction, l' i l i The first derivative of w cost_dl is the first-order weight coefficient of the smoothing cost, l' i ' is l i The second derivative of l' i ' +1 l i+1 The second derivative of w cost_ddl is the second-order weight coefficient of the smoothing cost, w cost_dddl is the third-order weight coefficient of the smoothing cost, w cost_mid is the central cost weight coefficient, w cost_m is the target vehicle mass cost weight coefficient, m is the target vehicle mass, l min is the maximum lateral displacement of the vehicle's center of mass from the road centerline in the first direction, l max It is the maximum lateral displacement of the center of mass of the vehicle from the center line of the road in the second direction, wherein the first direction and the second direction are opposite to each other.

[0019] In one embodiment of the present invention, based on the above solution, the constraints established include equality constraints and inequality constraints. The equality constraints are:

[0020] A eq x = b eq ,

[0021] in,

[0022]

[0023]

[0024]

[0025] The inequality constraints are:

[0026] A1·x≤b1,

[0027] in,

[0028]

[0029]

[0030]

[0031] Among them, A eq is the coefficient matrix of the equality constraint, b eq is the constant term of the equality constraint, n is the total number of points to be planned, and Δs is s i With s i+1 The increment, s i is the position of point i on the road centerline, s i+1 is the position of the next point on the road centerline along the vehicle's forward direction, A1 is the first coefficient matrix of the inequality constraint, b1 is the second coefficient matrix of the inequality constraint, d1 is the distance from the vehicle's center of mass to the front of the vehicle, d2 is the distance from the vehicle's center of mass to the rear of the vehicle, w is the width of the vehicle, and lb i is the S axis of the Frenet coordinate system (s i -d2,s i +d1) in l maxi The minimum value of ub i is the L axis of the Frenet coordinate system (s i -d2,s i +d1) in l mini The maximum value of .

[0032] In one embodiment of the present invention, based on the aforementioned solution, the target vehicle position information includes the position information of the target vehicle in the Frenet coordinate system.

[0033] In one embodiment of the present invention, based on the above-mentioned solution, a mass cost is established, including: obtaining a target vehicle mass based on a target vehicle mass estimation formula and target vehicle motion parameters; and establishing a mass cost according to the target vehicle mass.

[0034] In one embodiment of the present invention, based on the above solution, the target vehicle mass estimation formula is:

[0035] F x -0.5ρC d Av 2 =m(a+gf),

[0036] Among them, F x is the longitudinal resistance, ρ is the air density, C d is the air resistance coefficient, A is the frontal area of ​​the car, v is the vehicle speed, m is the target vehicle mass, a is the acceleration, g is the acceleration of gravity, and f is the rolling resistance coefficient.

[0037] According to one aspect of an embodiment of the present invention, an autonomous driving path planning device is also provided, including: an acquisition module, configured to acquire environmental information, the environmental information including target vehicle motion parameters and target vehicle position information; an establishment module, configured to establish a cost function, the cost function including quality cost, reference line cost, smoothing cost and central cost, wherein the quality cost is obtained based on the target vehicle motion parameters, and the reference line cost, smoothing cost and central cost are all obtained based on the target vehicle position information; a calculation module, configured to establish constraints for the cost function, and calculate the target driving path corresponding to the target vehicle based on the cost function and the constraints.

[0038] According to one aspect of an embodiment of the present invention, an autonomous driving path planning device is also provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the autonomous driving path planning device implements any of the above-mentioned autonomous driving path planning methods.

[0039] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes any of the above-mentioned autonomous driving path planning methods.

[0040] Beneficial effects of the present invention: The present invention first obtains environmental information, which includes target vehicle motion parameters and target vehicle position information; then establishes a cost function based on the environmental information, which includes mass cost, reference line cost, smoothing cost, and center cost, wherein the mass cost is obtained based on the target vehicle motion parameters; then establishes constraints for the cost function, and calculates the target driving path corresponding to the target vehicle based on the cost function and the constraints. It can be seen that the present invention can add the cost of considering the mass of the target vehicle to the path planning problem of active lane change, proposes the definition of the cost function and constraints of the path optimization problem, accurately models the total cost function, uses nonlinear optimization to solve the exact solution, and obtains the optimized path through real-time verification of the constraints, thereby improving the driving safety of autonomous driving vehicles with large mass and high center of mass position such as commercial vehicles in road cornering scenarios.

[0041] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0043] Figure 1 is a top view of a target definition diagram shown in an exemplary embodiment of the present application;

[0044] Figure 2 1 is a schematic diagram of an implementation environment of an autonomous driving path planning method according to an exemplary embodiment of the present application;

[0045] Figure 3 is a flow chart of an autonomous driving path planning method shown in an exemplary embodiment of the present application;

[0046] Figure 4 This is an illustration of the longitudinal and lateral sampling diagrams of autonomous driving path planning shown in an exemplary embodiment of the present application;

[0047] Figure 5 is a block diagram of an autonomous driving path planning device shown in an exemplary embodiment of the present application;

[0048] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing an autonomous driving path planning device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0050] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0051] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0052] First, it's important to note that in the era of artificial intelligence, with the advancement of multi-sensor fusion and decision-making planning technologies, the demand for autonomous vehicles is growing stronger. Autonomous vehicles can be categorized into five levels, from L1 to L5, based on usage scenarios and technical capabilities. L2 represents advanced driver assistance, L3 is conditional autonomous driving, L4 is fully autonomous driving in limited areas, and L5 is fully autonomous driving. The industry is currently focusing on mass production of L2 and L3 autonomous driving technologies. These two levels primarily address autonomous driving on highways and urban expressways, including key features such as lateral lane keeping, longitudinal adaptive cruise control, and automatic lane changing. For point-to-point autonomous driving on structured roads like highways, in addition to basic lateral lane keeping and longitudinal adaptive cruise control, autonomous vehicles are also required to possess capabilities such as automatic on- and off-ramps, active interactive driving, and active overtaking and lane changing. The active lane change function means that when the global path is turned on, if there is a slow-moving vehicle in the vehicle's lane and the traffic speed in the adjacent lane is faster, the vehicle can actively execute the lane change and overtaking command to improve the overall traffic efficiency; automatically change lanes to a lane that can enter and exit the ramp or the interchange so as to complete the next stage of driving.

[0053] Figure 1 FIG. 1 is a top view of a target definition diagram shown in an exemplary embodiment of the present application. Figure 1 As shown, the target vehicle is HostVehicle, with target obstacle No. 1 directly in front of the target vehicle, target obstacle No. 3 in the front left, target obstacle No. 4 in the front right, target obstacle No. 7 to the left, target obstacle No. 8 to the right, target obstacle No. 9 to the rear left, target obstacle No. 10 to the rear right, and target obstacle No. 11 directly behind. The target vehicle's optional lanes are lane ①, lane ②, and lane ③. During the driving process of the target vehicle HostVehicle, it is necessary to plan multiple feasible active lane change plans based on the obstacles and lane conditions, and decide on the optimal plan so that the target vehicle can successfully and safely complete the active lane change action. It should be understood that this embodiment does not limit the lane conditions and the position of the target vehicle on the lane. For example, the target obstacle can be other vehicles or other obstacles that appear in the lane due to unexpected situations, such as animals, landslide debris, etc.

[0054] Currently, many patents have been published for the problem of path planning for active lane changes in autonomous driving. The lane change path planning methods in these patents generally cover all driving scenarios. However, in the case of road curves, for autonomous vehicles such as commercial vehicles with large mass and high center of mass, if the mass of the vehicle is not taken into account during the path planning process of the lane change process, it is easy to cause the vehicle to roll over during the lane change, posing a potential driving safety hazard. To address these issues, the embodiments of the present application respectively propose an autonomous driving path planning method, an autonomous driving path planning device, an autonomous driving path planning equipment, a computer-readable storage medium, and a computer program product. These embodiments are described in detail below.

[0055] Figure 2 This is a schematic diagram of the application environment of a vehicle control method shown in an exemplary embodiment of the present application, wherein, during the automatic driving process of the vehicle 210, the surrounding environment information is obtained by using various sensors carried by the vehicle, and then communicates with the smart terminal 220. The smart terminal 220 establishes a cost function based on the environmental information; establishes constraints for the cost function, and calculates the target driving path based on the cost function and constraints to realize the planning of the vehicle path.

[0056] For example, smart terminal 220 can be installed on vehicle 210 or on a server. Smart terminal 220 can be any terminal device that supports the installation of navigation map software, such as a smartphone, an in-vehicle computer, a tablet computer, a laptop computer, or a wearable device, but is not limited thereto. Vehicle 210 can communicate with smart terminal 220 via a wireless network such as 3G (third generation mobile information technology), 4G (fourth generation mobile information technology), or 5G (fifth generation mobile information technology), and this is not limited herein.

[0057] The intelligent terminal sends instructions to the central controller of the vehicle, which in turn sends instructions to the speed controller to control the vehicle speed.

[0058] like Figure 3 As shown, in an exemplary embodiment, the method for road condition automatic driving path planning includes at least steps S310 to S330, which are described in detail as follows:

[0059] Step S310: Acquire environmental information, which includes target vehicle motion parameters and target vehicle position information.

[0060] For example, environmental information is obtained by a variety of sensors carried by the target vehicle, which may be mass-produced corner radars, cameras, etc.; the target vehicle position information is obtained by obtaining lane line information and the current motion parameters of the vehicle.

[0061] It can be seen from this that the present invention can use mass-produced corner radars, cameras and other sensors to obtain environmental information and perform lateral path planning for active lane changes. The hardware solution is reliable, mature and cost-controlled.

[0062] Step S320, establishing a cost function, which includes quality cost, reference line cost, smoothing cost and center cost, wherein the quality cost is obtained based on the target vehicle motion parameters, and the reference line cost, smoothing cost and center cost are all obtained based on the target vehicle position information.

[0063] Exemplarily, the step of establishing the cost function includes: establishing a Frenet coordinate system according to the target vehicle position information; and establishing the cost function based on the Frenet coordinate system.

[0064] Step S330 : establishing constraints for the cost function, and calculating a target driving path corresponding to the target vehicle based on the cost function and the constraints.

[0065] For example, based on the cost function and constraints established in the aforementioned scheme, the optimal path planning solution for each lane change space is calculated. This is a nonlinear optimization problem, so it can be solved using a corresponding mathematical algorithm. In this embodiment, a quadratic programming algorithm (QP) is used. If an optimal path solution exists (i.e., the calculation converges and satisfies the constraints), it is output, completing the active lane change path planning. If no optimal path solution exists, the target vehicle mass estimation is repeated.

[0066] It can be seen from this that the present invention can add the cost of considering the mass of the target vehicle to the path planning problem of active lane changing, propose the definition of the cost function and constraints of the path optimization problem, accurately model the total cost function, use nonlinear optimization to solve the exact solution, and obtain the optimized path through real-time verification of the constraints, thereby improving the driving safety of autonomous driving vehicles with larger mass and higher center of mass position, such as commercial vehicles, in road curve scenarios.

[0067] In an exemplary embodiment, based on the above solution, the cost function is:

[0068] J=J ref +J smooth +J mid +J m ,

[0069] Among them, J is the cost function, J ref is the reference line cost, J smooth is the smoothing cost, J mid For the central price, J m The price of quality.

[0070] It's important to note that in the Frenet coordinate system, with the road centerline as the reference, s represents the longitudinal position on the road centerline, and l represents the lateral displacement of the vehicle's center of mass from the road centerline. When driving on structured roads, the SL coordinate system is more suitable for practical needs than the XY coordinate system.

[0071] In an exemplary embodiment, based on the above solution, the reference line cost formula is:

[0072]

[0073] The smoothing cost formula is:

[0074]

[0075] The central cost formula is:

[0076]

[0077] The target vehicle mass cost formula is:

[0078] J m =w cost_m m,

[0079] Among them, w cost_ref is the weight coefficient of the reference line cost, l i is the lateral displacement of the vehicle's center of mass at point i from the road centerline, l i+1 is the lateral displacement of the vehicle's center of mass from the road centerline at the point below point i along the vehicle's forward direction, l'i l i The first derivative of w cost_dl is the first-order weight coefficient of the smoothing cost, l' i ' is l i The second derivative of l' i ' +1 l i+1 The second derivative of w cost_ddl is the second-order weight coefficient of the smoothing cost, w cost_dddl is the third-order weight coefficient of the smoothing cost, w cost_mid is the central cost weight coefficient, w cost_m is the target vehicle mass cost weight coefficient, m is the target vehicle mass, l min is the maximum lateral displacement of the vehicle's center of mass from the road centerline in the first direction, l max It is the maximum lateral displacement of the center of mass of the vehicle from the center line of the road in the second direction, wherein the first direction and the second direction are opposite to each other.

[0080] It can be seen that the present invention achieves the specific performance of lateral path planning by calibrating the weight parameters of various costs, which can better reflect the driving styles of drivers such as conservative, ordinary, and aggressive, and is close to the driver's intention; the path planning results of active lane changes take into account the vehicle's cornering scenario during road driving, especially for vehicles with larger mass and higher center of gravity such as commercial vehicles, and take into account the safety of active lane changes.

[0081] In an exemplary embodiment, based on the above solution, the established constraints include equality constraints and inequality constraints. The equality constraints are:

[0082] A eq x = b eq ,

[0083] in,

[0084]

[0085]

[0086]

[0087] The inequality constraints are:

[0088] A1·x≤b1,

[0089] in,

[0090]

[0091]

[0092]

[0093] Among them, A eq is the coefficient matrix of the equality constraint, b eq is the constant term of the equality constraint, n is the total number of points to be planned, and Δs is s i With s i+1 The increment, s i is the position of point i on the road centerline, s i+1 is the position of the next point on the road centerline along the vehicle's forward direction, A1 is the first coefficient matrix of the inequality constraint, b1 is the second coefficient matrix of the inequality constraint, d1 is the distance from the vehicle's center of mass to the front of the vehicle, d2 is the distance from the vehicle's center of mass to the rear of the vehicle, w is the width of the vehicle, and lb i is the S axis of the Frenet coordinate system (s i -d2,s i +d1) in l maxi The minimum value of ub i is the L axis of the Frenet coordinate system (s i -d2,s i +d1) in l mini The maximum value of .

[0094] In an exemplary embodiment, based on the aforementioned solution, the target vehicle position information includes position information of the target vehicle in a Frenet coordinate system.

[0095] See also Figure 4 , Figure 4 This is an illustration of the longitudinal and lateral sampling diagrams of path planning shown in an exemplary embodiment of the present application.

[0096] For example, the S axis represents the center line of the road, and the direction indicated by the L axis represents the direction perpendicular to the center line of the road. min With L = l max Represents the two sides of the lane. Target obstacle 1 represents the obstacle in front of the vehicle. A series of “×” represents a series of discrete points searched by dynamic programming in the Frenet coordinate system. A series of discrete points and L=l min Open up a convex space for subsequent quadratic planning.

[0097] It should be understood that this embodiment does not limit the curvature of the lane.

[0098] In an exemplary embodiment, based on the above-mentioned solution, establishing a mass cost includes: obtaining a target vehicle mass based on a target vehicle mass estimation formula and target vehicle motion parameters; and establishing a mass cost according to the target vehicle mass.

[0099] In an exemplary embodiment, based on the above scheme, the target vehicle mass estimation formula is:

[0100] F x -0.5ρC d Av 2 =m(a+gf),

[0101] Among them, F x is the longitudinal resistance, ρ is the air density, C d is the air resistance coefficient, A is the frontal area of ​​the car, v is the vehicle speed, m is the target vehicle mass, a is the acceleration, g is the acceleration of gravity, and f is the rolling resistance coefficient.

[0102] In this embodiment, the basic formula of vehicle longitudinal dynamics is given based on automobile theory:

[0103] F x =F f +F w +F i +F j ,

[0104] Among them, F x Indicates longitudinal resistance, F f Indicates rolling resistance, F w Indicates air resistance, F i Indicates slope resistance, F j Indicates acceleration resistance.

[0105] The formula expands to:

[0106]

[0107] Among them, m is the mass of the target vehicle, g is the acceleration of gravity, θ is the slope signal, v is the vehicle speed, is the derivative of vehicle speed, ρ is air density, C d is the air resistance coefficient, A is the frontal area of ​​the car, m is the mass of the target vehicle, a is the acceleration, g is the acceleration due to gravity, and f is the rolling resistance coefficient.

[0108] For the slope resistance term, since both mass and slope signals are coupled, there is no way to directly use the least squares algorithm. Considering that the vehicle is equipped with a longitudinal acceleration sensor, the acceleration a it measures has the following relationship:

[0109]

[0110] Therefore, the longitudinal dynamics formula can be simplified to the following form, which is the target vehicle mass estimation formula:

[0111] F x -0.5ρC d Av2 =m(a+gf),

[0112] For example, after obtaining the vehicle longitudinal force, vehicle speed, and acceleration signals through sensors installed on the vehicle, the vehicle mass can be estimated using the least squares method.

[0113] During the process of automatic driving of a vehicle: first, environmental information such as the target vehicle motion parameters and target vehicle position information is obtained through the various sensors carried by the vehicle, and then the target vehicle mass is estimated based on the target vehicle motion parameters to obtain the target vehicle mass; a cost function is established according to the environmental information, including mass cost, reference line cost, smoothing cost and central cost; constraints are established for the cost function, and quadratic programming is solved for the cost function and constraints; it is determined whether the calculation results converge and meet the constraints. If not, the target vehicle mass is re-estimated; if so, the target path planning is completed.

[0114] It can be seen from this that the present invention can add the cost of considering the mass of the target vehicle to the path planning problem of active lane changing, propose the definition of the cost function and constraints of the path optimization problem, accurately model the total cost function, use nonlinear optimization to solve the exact solution, and obtain the optimized path through real-time verification of the constraints, thereby improving the driving safety of autonomous driving vehicles with larger mass and higher center of mass position, such as commercial vehicles, in road curve scenarios.

[0115] Figure 5 This is a block diagram of an automatic driving path planning device shown in an exemplary embodiment of the present application. The device can be applied to Figure 2 The implementation environment shown in FIG2 is specifically configured in the smart terminal 220. The apparatus may also be applicable to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the apparatus is applicable.

[0116] like Figure 5 As shown, the exemplary autonomous driving path planning device includes: an acquisition module 501, configured to acquire environmental information, the environmental information including target vehicle motion parameters and target vehicle position information; an establishment module 502, configured to establish a cost function, the cost function including quality cost, reference line cost, smoothing cost and center cost, wherein the quality cost is obtained based on the target vehicle motion parameters, and the reference line cost, smoothing cost and center cost are all obtained based on the target vehicle position information; a calculation module 503, configured to establish constraints for the cost function, and calculate the target driving path corresponding to the target vehicle according to the cost function and the constraints.

[0117] It should be noted that the autonomous driving path planning device provided in the above embodiment and the autonomous driving path planning method provided in the above embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the autonomous driving path planning device provided in the above embodiment can, as needed, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0118] An embodiment of the present application also provides an autonomous driving path planning device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by one or more processors, the autonomous driving path planning device implements the autonomous driving path planning method provided in the above-mentioned embodiments.

[0119] Figure 6 The following is a schematic diagram showing the structure of a computer system suitable for implementing the automatic driving path planning device of the embodiment of the present application. Figure 6 The computer system 600 of the autonomous driving path planning device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0120] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 into the random access memory (RAM) 603, such as executing the method in the above embodiment. Various programs and data required for system operation are also stored in the RAM 603. The CPU 601, ROM 602 and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0121] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, and the like; an output section 607 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. Removable media 611, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 610 as needed, so that computer programs read therefrom can be installed into the storage section 608 as needed.

[0122] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the various functions defined in the system of the present application are executed.

[0123] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0126] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon. When executed by a computer processor, the computer program causes the computer to perform the aforementioned autonomous driving path planning method. The computer-readable storage medium may be included in the autonomous driving path planning device described in the above embodiments, or may exist independently and not be incorporated into the device.

[0127] Another aspect of the present application provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the autonomous driving path planning method provided in each of the above embodiments.

[0128] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, any equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A method for autonomous driving path planning, characterized in that: The method comprises: Acquiring environmental information, wherein the environmental information includes target vehicle motion parameters and target vehicle position information; Establishing a cost function, the cost function including a mass cost, a reference line cost, a smoothing cost, and a center cost, wherein the mass cost is obtained based on the motion parameters of the target vehicle, and the reference line cost, the smoothing cost, and the center cost are all obtained based on the target vehicle position information; Establishing constraints for the cost function, and calculating a target driving path corresponding to a target vehicle based on the cost function and the constraints; The cost function is: J=J ref +J smooth +J mid +J m , Among them, J is the cost function, J ref is the reference line cost, J smooth is the smoothing cost, J mid For the central price, J m The price of quality; The reference line cost formula is: The smoothing cost formula is: The central cost formula is: The target vehicle mass cost formula is: J m =w cost_m m, Among them, W cost_ref is the weight coefficient of the reference line cost, l i is the lateral displacement of the vehicle's center of mass at point i from the road centerline, l i+1 is the lateral displacement of the vehicle's center of mass from the road centerline at the point below point i along the vehicle's forward direction, l' i l i The first derivative of W cost_dl is the first-order weight coefficient of the smoothing cost, l″ i l i The second derivative of l″ i+1 l i+1 The second derivative of W cost_ddl is the second-order weight coefficient of the smoothing cost, W cost_dddl is the third-order weight coefficient of the smoothing cost, W cost_mid is the central cost weight coefficient, W cost_m is the target vehicle mass cost weight coefficient, m is the target vehicle mass, l min is the maximum lateral displacement of the vehicle's center of mass from the road centerline in the first direction, l max It is the maximum lateral displacement of the center of mass of the vehicle from the center line of the road in the second direction, wherein the first direction and the second direction are opposite to each other.

2. The automatic driving path planning method according to claim 1, characterized in that: The established constraints include equality constraints and inequality constraints. The equality constraints are: A eq ·x=b eq , in, The inequality constraints are: A1·x≤b1, in, Among them, A eq is the coefficient matrix of the equality constraint, b eq is the constant term of the equality constraint, n is the total number of points to be planned, and Δs is s i With s i+1 The increment, s i is the position of point i on the road centerline, s i+1 is the position of the next point on the road centerline along the vehicle's forward direction, A1 is the first coefficient matrix of the inequality constraint, b1 is the second coefficient matrix of the inequality constraint, d1 is the distance from the vehicle's center of mass to the front of the vehicle, d2 is the distance from the vehicle's center of mass to the rear of the vehicle, w is the width of the vehicle, and lb i is the S axis of the Frenet coordinate system (s i -d2,s i +d1) in l maxi The minimum value of ub i is the L axis of the Frenet coordinate system (s i -d2,s i +d1) in l mini The maximum value of .

3. The automatic driving path planning method according to claim 1, wherein: The target vehicle position information includes the position information of the target vehicle in the Frenet coordinate system.

4. The automatic driving path planning method according to claim 1, wherein: Establish the quality cost, including: Obtaining a target vehicle mass based on a target vehicle mass estimation formula and the target vehicle motion parameters; A mass cost is established according to the target vehicle mass.

5. The automatic driving path planning method according to claim 3, characterized in that: The target vehicle mass estimation formula is: F x -0.5ρC d Av 2 =m(a+gf), Among them, F x is the longitudinal resistance, ρ is the air density, C d is the air resistance coefficient, A is the frontal area of ​​the car, v is the vehicle speed, m is the target vehicle mass, a is the acceleration, g is the acceleration of gravity, and f is the rolling resistance coefficient.

6. An autonomous driving path planning device based on the autonomous driving path planning method according to any one of claims 1 to 5, characterized in that: The device comprises: An acquisition module is used to acquire environmental information, wherein the environmental information includes target vehicle motion parameters and target vehicle position information; An establishment module is used to establish a cost function, wherein the cost function includes a mass cost, a reference line cost, a smoothing cost, and a center cost, wherein the mass cost is obtained based on the motion parameters of the target vehicle, and the reference line cost, the smoothing cost, and the center cost are all obtained based on the target vehicle position information; The calculation module is used to establish constraints for the cost function and calculate the target driving path corresponding to the target vehicle according to the cost function and the constraints.

7. An autonomous driving path planning device, characterized in that: The device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the device to implement the autonomous driving path planning method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the automatic driving path planning method according to any one of claims 1 to 5.

Images