Path planning method and device, vehicle, and storage medium

Abstract

The application discloses a path planning method and device, a vehicle and a storage medium. The method comprises the following steps: acquiring road condition information, wherein the road condition information comprises at least one of the following: boundary information of a road on which a vehicle travels, driving information of a first lane on which the vehicle travels, and driving information of at least one second lane; the road comprises the first lane and the at least one second lane, and the second lane is an adjacent lane of the first lane; based on the road condition information and a preset optimization target, a mathematical model based on space-time joint planning is generated; and a planning path of the vehicle is acquired according to the mathematical model based on space-time joint planning. The technical scheme provided by the application can provide accurate driving guidance when the vehicle has a lane changing demand or a merging demand, improve the accuracy of path planning in a lane changing scene or a merging scene, and thus improve driving safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a path planning method and device, a vehicle, and a storage medium. BACKGROUND

[0002] Path planning refers to finding a collision-free path from a starting state to a target state in an environment with obstacles according to certain evaluation criteria.

[0003] In related technologies, in a lane changing scenario, a vehicle will perform lane changing only when the following logical judgments are met: whether the lane changing distance is sufficient at the current speed, whether the rear vehicle of the target lane has a collision risk with the ego vehicle during lane changing, and the like.

[0004] However, the above logical judgment method is usually not accurate enough. SUMMARY

[0005] The present application provides a path planning method and device, a vehicle, and a storage medium.

[0006] In a first aspect, an embodiment of the present application provides a path planning method, including: obtaining road condition information, the road condition information including at least one of the following: boundary information of a road on which a vehicle travels, driving information of a first lane on which the vehicle travels, and driving information of at least one second lane; the road including the first lane and the at least one second lane, the second lane being an adjacent lane of the first lane; generating a mathematical model based on spatio-temporal joint planning based on the road condition information and a preset optimization target; and obtaining a planning path of the vehicle according to the mathematical model based on spatio-temporal joint planning.

[0007] In a second aspect, an embodiment of the present application provides a path planning device, including: an information obtaining module configured to obtain road condition information, wherein the road condition information includes at least one of the following: boundary information of a road on which a vehicle travels, driving information of a first lane on which the vehicle travels, and driving information of at least one second lane; the road including the first lane and the at least one second lane, the second lane being an adjacent lane of the first lane; a model generating module configured to generate a mathematical model based on spatio-temporal joint planning based on the road condition information and a preset optimization target; and a path planning module configured to obtain a planning path of the vehicle according to the mathematical model based on spatio-temporal joint planning.

[0008] In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a memory; and one or more application programs stored in the memory and configured to be executed by the one or more processors, the one or more application programs being configured to perform the path planning method according to the first aspect.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions that can be invoked by a processor to execute the path planning method as described in the first aspect.

[0010] Fifthly, embodiments of this application provide a computer program product that, when executed, enables the implementation of the path planning method as described in the first aspect.

[0011] Compared to existing technologies, the path planning method provided in this application obtains vehicle road condition information, including the driving information of the lane the vehicle is traveling in and the driving information of adjacent lanes. Path planning is then performed based on this road condition information and a preset optimization objective. Since the road condition information can determine the constraints that the vehicle must meet (such as not going off the road, maintaining a distance greater than the minimum safe distance from other vehicles, and satisfying the vehicle's kinematic equations), and the preset optimization objective can ensure driving at a lower cost, the mathematical model based on spatiotemporal joint planning generated from the above two factors can ensure that a planned path that satisfies vehicle safety and has a lower cost is obtained. This method can provide accurate driving guidance when the vehicle needs to change lanes or cut in line, improving the accuracy of path planning in lane-changing or cutting-in scenarios, thereby improving driving safety. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the implementation environment provided in the embodiments of this application.

[0014] Figure 2 This is a flowchart of a path planning method provided in one embodiment of this application.

[0015] Figure 3 This is a flowchart of a path planning method provided in another embodiment of this application.

[0016] Figure 4 This is a structural block diagram of a path planning device provided in one embodiment of this application.

[0017] Figure 5 This is a structural block diagram of a vehicle provided in one embodiment of this application.

[0018] Figure 6 This is a structural block diagram of a computer storage medium provided in one embodiment of this application. Detailed Implementation

[0019] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0020] To enable those skilled in the art to better understand the solutions of this application, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0021] Please see Figure 1 This diagram illustrates an implementation environment provided in one embodiment of the present application. The implementation environment includes a vehicle 100, which refers to a means of transportation driven or towed by a power unit for the purpose of carrying people or transporting goods, including but not limited to cars, suburban utility vehicles (SUVs), multi-purpose vehicles (MPVs), etc.

[0022] Vehicle 100 includes a path planning module, which performs path planning. Path planning refers to finding a collision-free path from a starting state to a target state in an environment with obstacles, according to certain evaluation criteria. In this embodiment, the path planning module determines the planned path based on the driving information of the lane in which vehicle 100 is traveling (e.g., the speed and position of vehicles traveling in the same lane as vehicle 100 and at a distance less than a first predetermined distance), the driving information of adjacent lanes (e.g., the speed and position of vehicles traveling in adjacent lanes and at a distance less than a second predetermined distance), and road boundary information (e.g., the geodetic coordinates of road edges and lane lines). Because the determined planned path fully considers the driving information of adjacent lanes, it can provide accurate driving guidance when vehicle 100 needs to change lanes or cut in, improving the accuracy of path planning in lane-changing or cutting-in scenarios, thereby improving driving safety.

[0023] The path planning module employs at least one of the following algorithms for path planning: Linear Quadratic Regulator (LQR) algorithm, Model Predictive Control (MPC) algorithm, Iterative LQR algorithm, etc., Constrained Iterative Linear Quadratic Regulator (CILQR) algorithm. In this embodiment, only the CILQR algorithm is used as an example for path planning.

[0024] In some embodiments, the vehicle 100 further includes a detection module for detecting information about obstacles around the vehicle 100 (such as shape, speed, and distance from the vehicle 100), including other vehicles, pedestrians, roadblocks, etc., traveling in front of the vehicle 100. The detection module includes, but is not limited to, millimeter-wave radar, lidar, ultrasonic radar, etc. In some embodiments, the vehicle 100 further includes an image acquisition module for acquiring environmental information around the vehicle 100, such as road boundary information, current traffic light color information, etc. In some embodiments, the vehicle 100 further includes a positioning module for locating the current position of the vehicle 100. The positioning module may be a Global Positioning System (GPS) module. In some embodiments, the vehicle 100 further includes various sensors for acquiring various parameters of the vehicle 100 during driving, including, but not limited to, speed sensors, acceleration sensors, wheel speed sensors, temperature sensors, etc.

[0025] Please see Figure 2 The diagram illustrates a flowchart of a path planning method provided in one embodiment of this application, which includes the following steps.

[0026] Step S201: Obtain traffic information.

[0027] Traffic information is used to describe the environment of the road on which a vehicle is traveling. Traffic information for a vehicle includes at least one of the following: boundary information of the road on which the vehicle is traveling, travel information of the first lane on which the vehicle is traveling, and travel information of at least one second lane.

[0028] The boundary information of the road on which the vehicle travels can be represented by the geodetic coordinates of the curb and lane lines. The road on which the vehicle travels includes a first lane and at least one second lane. In some embodiments, the vehicle acquires image data using an image acquisition device (such as a surround-view camera), and then extracts the road boundaries, such as the curb shape and lane line shape, using a dedicated image recognition algorithm to determine the boundary information. The image recognition algorithm includes, but is not limited to, template-matching-based image recognition algorithms, deep learning-based image recognition algorithms, etc. In other embodiments, the vehicle uses a detection component to detect the curb and obtain point cloud data of the curb to determine the boundary information.

[0029] The driving information for the first lane in which the vehicle is traveling includes: the vehicle's own driving information, including its speed, position, etc. Optionally, the driving information for the first lane includes the vehicle's driving information within a first predetermined time period. The first predetermined time period is set based on experiments or experience, and is 4 seconds. The vehicle's own driving information can be detected by sensors installed in the vehicle, such as obtaining the driving speed through a speed sensor and obtaining the driving position through a positioning module, etc.

[0030] The driving information for the first lane also includes the driving information of the first vehicle in the same lane as the vehicle, including its speed, position, and distances between other vehicles. This first vehicle can be traveling in front of or behind the vehicle. Optionally, the driving information for the first lane also includes the driving information of the first vehicle within a second preset time period, which is set based on experiments or experience, such as 4 seconds. It should be noted that the distance between the first vehicles is less than a first predetermined distance, which can be set based on experiments or experience, such as 200 meters. The vehicle can detect the speed and position of the first vehicle, as well as the distances between other vehicles, using detection components. These detection components can include image acquisition devices, lidar, millimeter-wave radar, ultrasonic radar, etc.

[0031] The driving information for the second lane includes the driving information of the second vehicle traveling in the second lane, including its speed, position, and distance between vehicles. The second lane is adjacent to the first lane. There can be one or two second lanes. If one lane line of the first lane is a road boundary, the second lane is one; if neither lane line of the second lane is a road boundary, there are two second lanes. The second vehicle can be traveling to the left front or right front of the first lane, or to the left rear or right rear of the first lane. Optionally, the driving information for the second lane also includes the driving information of the second vehicle within a third preset time period, which is set based on experiments or experience, such as 4 seconds. It should be noted that the distance between the second vehicles is less than a second predetermined distance, which can be set based on experiments or experience, such as 200 meters.

[0032] Step S202: Based on road condition information and preset optimization objectives, generate a mathematical model based on spatiotemporal joint planning.

[0033] Spatiotemporal decoupling programming involves decomposing a spatiotemporal trajectory into a path and a velocity curve, reducing the difficulty of each problem by solving the path and velocity separately. However, spatiotemporal joint programming does not perform the above decomposition steps; it directly solves for the optimal spatiotemporal trajectory.

[0034] In this embodiment of the application, the vehicle processes road condition information and preset optimization objectives through a preset path planning algorithm to obtain a mathematical model based on spatiotemporal joint planning. Since the constraints that the vehicle must meet for driving can be determined based on the road condition information (such as not driving out of the road boundary, the distance between the vehicle and other vehicles is always greater than the minimum safe distance, and the vehicle's kinematic equations are satisfied, etc.), and the preset optimization objectives can ensure that driving is carried out at a low cost, the mathematical model based on spatiotemporal joint planning generated based on the above two items can ensure that a planned path that satisfies the vehicle's safe driving and has a low driving cost can be obtained.

[0035] Step S203: Obtain the planned path of the vehicle based on the mathematical model of spatiotemporal joint planning.

[0036] The vehicle solves the mathematical model based on spatiotemporal joint programming to obtain the planned path of the vehicle.

[0037] In summary, the technical solution provided in this application obtains road condition information of the vehicle, including the driving information of the lane in which the vehicle is traveling and the driving information of adjacent lanes. Subsequently, path planning is performed based on the above road condition information and a preset optimization objective. Since the constraints that the vehicle must meet for driving can be determined based on the road condition information (such as not driving out of the road boundary, the distance between the vehicle and other vehicles is always greater than the minimum safe distance, and the vehicle's kinematic equations are satisfied, etc.), and the preset optimization objective can ensure that driving is carried out at a low cost, the mathematical model based on spatiotemporal joint planning generated by the above two factors can ensure that a planned path that meets the requirements of safe driving and has a low driving cost can be obtained. It can provide accurate driving guidance when the vehicle has a need to change lanes or cut in line, improve the accuracy of path planning in lane-changing or cutting-in scenarios, and thus improve driving safety.

[0038] Please refer to Figure 3 The diagram illustrates a flowchart of a path planning method provided in one embodiment of this application. The method includes the following steps.

[0039] Step S301: Obtain traffic information.

[0040] Traffic information includes at least one of the following: boundary information of the road the vehicle is traveling on, travel information of the first lane the vehicle is traveling on, and travel information of at least one second lane. The road includes a first lane and at least one second lane. The second lane is the lane adjacent to the first lane.

[0041] In some embodiments, road condition information is acquired when a lane-change requirement is detected. Optionally, the vehicle determines a lane-change requirement when a detection component detects an obstacle within a preset distance ahead. The preset distance is set based on experiments or experience, and this embodiment does not limit it. Optionally, the vehicle acquires a navigation route; if the navigation route contains an intersection that is not connected to the vehicle's current lane, a lane-change requirement is determined.

[0042] In some embodiments, the vehicle obtains traffic information upon receiving a lane change planning instruction. Optionally, if the driver determines that a lane change is necessary, they can trigger a designated button in the vehicle to initiate the lane change planning instruction. The vehicle then obtains traffic information and executes subsequent route planning steps.

[0043] In some embodiments, the vehicle acquires road condition information when the lane change planning function is enabled. Optionally, the driver can choose to enable the lane change planning function as an assistance feature. When this function is enabled, the vehicle continuously acquires road condition information and performs subsequent route planning steps.

[0044] In some embodiments, the vehicle may also acquire current road information, and if the current road driving information indicates that the lane in which the vehicle is traveling is not a single lane, acquire road condition information and perform subsequent path planning steps.

[0045] By using the above methods, the timing of lane change route planning can be determined reasonably, avoiding unnecessary route planning and effectively saving vehicle energy consumption.

[0046] Step S302: Based on road condition information, determine the constraints that the vehicle must meet to drive.

[0047] In this embodiment of the application, the vehicle determines the constraints that the vehicle needs to meet for driving based on road condition information, and performs path planning based on the constraints, so that the planned path meets the safe driving conditions of the vehicle.

[0048] In some embodiments, the vehicle determines a first constraint based on the boundary information of the road it travels on. The first constraint indicates the vehicle's travel range. That is, the first constraint can be described by an inequality to indicate that the vehicle's travel range should be within the road boundary.

[0049] In some embodiments, the vehicle determines a second constraint based on driving information from a first lane and at least one second lane. This second constraint instructs the vehicle, when traveling along the planned path, to maintain a distance greater than a minimum safe distance from a target vehicle, which includes other vehicles in the first lane and vehicles in the second lane. This second constraint can also be described using an inequality. Specifically, the vehicle determines a functional relationship between the driving position and speed of each vehicle based on the driving information from each lane, and then ensures that the absolute value of the difference between the driving position of each vehicle and its own driving position is greater than the aforementioned minimum safe distance.

[0050] In some embodiments, the vehicle determines a third constraint based on its kinematic equations. The third constraint instructs the vehicle to follow its kinematic equations when traveling along the planned path.

[0051] In some embodiments, the vehicle determines a fourth constraint based on its current position. The fourth constraint indicates that the vehicle's speed and steering wheel angle at the current position should meet certain conditions.

[0052] In some embodiments, a fifth constraint is determined based on the vehicle's planned destination position. The fifth constraint indicates that the vehicle's speed and steering wheel angle at the planned destination position must meet certain conditions.

[0053] In a specific example, the CILQR algorithm is used as an example for path planning. In this embodiment, for an autonomous driving system with state and control input constraints, the vehicle uses the CILQR algorithm to pre-plan state variables such as the vehicle's lateral position (x-coordinate in the geodetic coordinate system), longitudinal position (y-coordinate in the geodetic coordinate system), and lateral angle (the angle between the vehicle and the horizontal axis in the geodetic coordinate system), and uses these as the initial feasible trajectory for the LMPC control strategy. The vehicle path planning problem is then formulated as follows:

[0054]

[0055] st x k+1 =f k (x k u k ), k = 0, 1, ..., N-1 (2)

[0056] x0=x start (3)

[0057] g k (x k u k )<0,k=,0,1,...,N-1 (4)

[0058] g N (x N )<0 (5)

[0059] Where, x k It is the state variable when the time step is K, u k This is the control variable when the time step number is K, and N is the number of time steps required for the vehicle to complete this lane change. N It is the endpoint state variable. It is the cost of the final state stage, L K (x k u k ) is the stage cost when the number of time steps is K, x * u * These are the state and control sequence when the cost function reaches its minimum. `st` is an abbreviation for `subject to`, indicating that it is constrained by `xx`. The second formula contains `f(x)`. k u k () represents the vehicle's dynamic equations. x0 is the initial state variable, x start This is the initial state value set. k (x k u k ) represents control input constraints and state constraint inputs. N (x N) indicates the last state input constraint.

[0060] The vehicle processes the constraints required for its operation based on the five calculation formulas mentioned above, resulting in inequalities applicable to lane change path planning scenarios.

[0061] Step S303: Determine the cost function based on the preset optimization objective.

[0062] In some embodiments, the preset optimization objective includes at least one of the following: a first parameter, a second parameter, a third parameter, and a fourth parameter.

[0063] The first parameter indicates the distance between the planned path and the reference path. The driving cost calculated based on the cost function is positively correlated with the first parameter. That is, the smaller the distance between the planned path and the reference path, the lower the driving cost of the vehicle; the larger the distance between the planned path and the reference path, the higher the driving cost of the vehicle.

[0064] The second parameter indicates the smoothness of the planned path. The driving cost calculated based on the cost function is negatively correlated with the second parameter. That is, the smoother the planned path, the lower the driving cost; the less smooth the planned path, the higher the driving cost.

[0065] The third parameter indicates the difference between the planned speed and the vehicle's current speed on the planned path. The travel cost calculated based on the cost function is positively correlated with the third parameter. That is, the smaller the difference between the planned speed and the current speed, the lower the travel cost; the larger the difference, the higher the travel cost.

[0066] The fourth parameter indicates the vehicle's acceleration and deceleration performance. The driving cost calculated based on the cost function is negatively correlated with the fourth parameter. That is, the better the vehicle's acceleration and deceleration performance, the lower the driving cost; the worse the vehicle's acceleration and deceleration performance, the higher the driving cost.

[0067] In some embodiments, the cost function can be expressed by the following formula:

[0068] cost=w1∑f target +w2∑f kappa +w3∑f vel +w4∑f acc

[0069] Where ω1 is the first weight, f target ω1 is the first parameter. ω2 is the second weight, kappa is the second parameter. w3 is the third weight, f is the third parameter. velw4 is the third parameter. f is the fourth weight. acc This is the fourth parameter.

[0070] Step S304: Based on the cost function and the constraints that the vehicle needs to satisfy for driving, generate a mathematical model based on spatiotemporal joint programming.

[0071] In some embodiments, step S204 is specifically implemented as follows: at least one of the first constraint, the second constraint, the third constraint, the fourth constraint, and the fifth constraint is added to the cost function through the obstacle function algorithm to obtain a mathematical model based on spatiotemporal joint programming.

[0072] Since the aforementioned problem involves state constraints and control constraints, these constraints can be implemented by introducing penalties. The basic idea is to transform the constraint function into a barrier function and add it to the original cost function. The barrier function can be in logarithmic form or other forms, which are not limited in this embodiment. In this embodiment, only the logarithmic barrier function is used as an example for illustration. On the one hand, it can ensure hard constraints; on the other hand, the logarithmic barrier function can asymptotically converge to the indicator function; finally, the logarithmic barrier function is twice differentiable, and its derivative is easy to calculate.

[0073] Step S305: Obtain the initial state variable, initial control variable, and initial penalty factor.

[0074] The initial state variables, initial control variables, and initial penalty factors can be customized by the vehicle based on its current driving state.

[0075] Step S306: Using a preset algorithm, and based on the initial state variables and the initial penalty factor, the mathematical model based on spatiotemporal joint planning is iterated to obtain the planned path of the vehicle.

[0076] Optionally, during the i-th iteration, the vehicle's driving cost is calculated based on the target penalty factor, target state variable, target control variable, and a mathematical model based on spatiotemporal joint programming, where i is a positive integer. If the vehicle's driving cost does not meet the preset conditions, the gradient information of the state variable and the gradient information of the control variable are obtained. The updated state variable is obtained based on the gradient information of the state variable, the updated control variable is obtained based on the gradient information of the control variable, and the updated penalty factor is obtained. If the vehicle's driving cost meets the preset conditions, the planned path of the vehicle is generated based on the target state variable and the target control variable.

[0077] When i is 1, the target state variable is the initial state variable, the target control variable is the initial control variable, and the target penalty factor is the initial penalty factor; when i is greater than 1, the target state variable is the updated state variable obtained in the (i-1)th iteration, the target control variable is the updated control variable obtained in the (i-1)th iteration, and the target penalty factor is the updated penalty factor obtained in the (i-1)th iteration.

[0078] The vehicle can substitute the target penalty factor, target state variable, and target control variable into the aforementioned spatiotemporal joint programming-based mathematical model to obtain the vehicle's driving cost. The preset condition is that the vehicle's driving cost is less than a preset cost value, which is determined based on the path planning accuracy; the higher the path planning accuracy, the smaller the preset cost value. The vehicle can calculate the gradients of each state variable and control variable, and then use a quasi-Newton algorithm based on these gradients to update the state variable and control variable. The penalty factor needs to be increased according to a preset step size to obtain the updated penalty factor. It should be noted that during the iteration process, the gradient update step size of the control variable and the gradient update step size of the state variable need to be adjusted in real time.

[0079] In summary, the technical solution provided in this application obtains road condition information of the vehicle, including the driving information of the lane in which the vehicle is traveling and the driving information of adjacent lanes. Subsequently, path planning is performed based on the above road condition information and a preset optimization objective. Since the constraints that the vehicle must meet for driving can be determined based on the road condition information (such as not driving out of the road boundary, the distance between the vehicle and other vehicles is always greater than the minimum safe distance, and the vehicle's kinematic equations are satisfied, etc.), and the preset optimization objective can ensure that driving is carried out at a low cost, the mathematical model based on spatiotemporal joint planning generated by the above two factors can ensure that a planned path that meets the requirements of safe driving and has a low driving cost can be obtained. It can provide accurate driving guidance when the vehicle has a need to change lanes or cut in line, improve the accuracy of path planning in lane-changing or cutting-in scenarios, and thus improve driving safety.

[0080] Please refer to Figure 4 The diagram illustrates a block diagram of a path planning device according to an embodiment of this application. The path planning device includes: an information acquisition module 410, a model generation module 420, and a path planning module 430.

[0081] The information acquisition module 410 is used to acquire road condition information, which includes at least one of the following: boundary information of the road on which the vehicle travels, driving information of the first lane on which the vehicle travels, and driving information of at least one second lane; the road includes a first lane and at least one second lane, wherein the second lane is an adjacent lane to the first lane.

[0082] The model generation module 420 is used to generate a mathematical model based on spatiotemporal joint planning based on road condition information and preset optimization objectives.

[0083] The path planning module 430 is used to obtain the planned path of the vehicle based on a mathematical model based on spatiotemporal joint planning.

[0084] In summary, the technical solution provided in this application obtains road condition information of the vehicle, including the driving information of the lane in which the vehicle is traveling and the driving information of adjacent lanes. Subsequently, path planning is performed based on the above road condition information and a preset optimization objective. Since the constraints that the vehicle must meet for driving can be determined based on the road condition information (such as not driving out of the road boundary, the distance between the vehicle and other vehicles is always greater than the minimum safe distance, and the vehicle's kinematic equations are satisfied, etc.), and the preset optimization objective can ensure that driving is carried out at a low cost, the mathematical model based on spatiotemporal joint planning generated by the above two factors can ensure that a planned path that meets the requirements of safe driving and has a low driving cost can be obtained. It can provide accurate driving guidance when the vehicle has a need to change lanes or cut in line, improve the accuracy of path planning in lane-changing or cutting-in scenarios, and thus improve driving safety.

[0085] In some embodiments, the model generation module 420 is configured to: determine the constraints that the vehicle needs to meet for driving based on road condition information; determine the cost function based on a preset optimization objective; and generate a mathematical model based on spatiotemporal joint programming based on the cost function and the constraints that the vehicle needs to meet for driving.

[0086] In some embodiments, the model generation module 420 is configured to: determine a first constraint based on the boundary information of the road the vehicle travels on, the first constraint indicating the vehicle's travel range; and / or, determine a second constraint based on the travel information of a first lane and at least one second lane, the second constraint indicating that when the vehicle travels along the planned path, the distance between it and a target vehicle is greater than a safe distance, the target vehicle including other vehicles in the first lane and vehicles in the second lane; and / or, determine a third constraint based on the vehicle's kinematic equations; and / or, determine a fourth constraint based on the vehicle's current position; and / or, determine a fifth constraint based on the vehicle's planned endpoint position; the model generation module is further configured to: add at least one of the first, second, third, fourth, and fifth constraints to a cost function using an obstacle function algorithm to obtain a mathematical model based on spatiotemporal joint programming.

[0087] In some embodiments, the preset optimization objective includes at least one of the following: a first parameter, a second parameter, a third parameter, and a fourth parameter; the first parameter indicates the distance between the planned path and the reference path, and the driving cost calculated based on the cost function is positively correlated with the first parameter; the second parameter indicates the smoothness of the planned path, and the driving cost calculated based on the cost function is negatively correlated with the second parameter; the third parameter indicates the difference between the planned speed of the vehicle on the planned path and the current speed of the vehicle, and the driving cost calculated based on the cost function is positively correlated with the third parameter; the fourth parameter indicates the acceleration and deceleration performance of the vehicle, and the driving cost calculated based on the cost function is negatively correlated with the fourth parameter.

[0088] In some embodiments, the path planning module 430 is used to obtain initial state variables, initial control variables, and initial penalty factors; adopt a preset algorithm, and iterate the mathematical model based on spatiotemporal joint planning based on the initial state variables and initial penalty factors to obtain the planned path of the vehicle.

[0089] In some embodiments, the path planning module 430 is specifically used for: calculating the vehicle's driving cost based on the target penalty factor, target state variable, target control variable, and a mathematical model based on spatiotemporal joint planning during the i-th iteration, where i is a positive integer; if the vehicle's driving cost does not meet the preset conditions, obtaining the gradient information of the state variable and the gradient information of the control variable, obtaining the updated state variable based on the gradient information of the state variable, obtaining the updated control variable based on the gradient information of the control variable, and obtaining the updated penalty factor; if the vehicle's driving cost meets the preset conditions, generating the vehicle's planned path based on the target state variable and the target control variable; if i is 1, the target state variable is the initial state variable, the target control variable is the initial control variable, and the target penalty factor is the initial penalty factor; if i is greater than 1, the target state variable is the updated state variable obtained in the (i-1)-th iteration, the target control variable is the updated control variable obtained in the (i-1)-th iteration, and the target penalty factor is the updated penalty factor obtained in the (i-1)-th iteration.

[0090] In some embodiments, the information acquisition module 410 is configured to: acquire road condition information when a vehicle is detected to have a lane change requirement; or / and, acquire road condition information when a lane change planning instruction is received; or / and, acquire road condition information when the lane change planning function is enabled.

[0091] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0092] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0093] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0094] Please see Figure 5 The illustration shows that an embodiment of this application also provides a vehicle 500, which includes one or more processors 510, a memory 520, and one or more application programs. The one or more application programs are stored in the memory and configured to be executed by the one or more processors, and are configured to perform the methods described in the above embodiments.

[0095] Processor 510 may include one or more processing cores. Processor 510 connects to various parts of the entire battery management system using various interfaces and lines, and performs various functions and processes data of the battery management system by running or executing instructions, programs, code sets, or instruction sets stored in memory 520, and by calling data stored in memory 520. Optionally, processor 510 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 510 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 510 and may be implemented separately using a communication chip.

[0096] The memory 520 may include random access memory (RAM) or read-only memory (ROM). The memory 520 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 520 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described above. The data storage area may also store data created during vehicle operation (e.g., phonebook, audio / video data, chat log data, etc.).

[0097] Please see Figure 6 The present application also provides a computer-readable storage medium 600, which stores computer program instructions 610 that can be invoked by a processor to perform the methods described in the above embodiments.

[0098] The computer-readable storage medium 600 may be, for example, flash memory, electrically erasable programmable read-only memory (EEPROM), electrically programmable read-only memory (EPROM), hard disk, or read-only memory (ROM). Optionally, the computer-readable storage medium includes non-transitory computer-readable storage medium. The computer-readable storage medium 600 has storage space for computer program instructions 610 that perform any of the method steps described above. These computer program instructions 610 may be read from or written to one or more computer program products.

[0099] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Although this application has disclosed preferred embodiments as above, it is not intended to limit this application. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the technical solution of this application. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A path planning method, characterized in that, The method includes: Obtain road condition information, which includes at least one of the following: boundary information of the road on which the vehicle is traveling, driving information of the first lane on which the vehicle is traveling, and driving information of at least one second lane; the road includes the first lane and at least one second lane, wherein the second lane is an adjacent lane to the first lane; Based on the road condition information and the preset optimization objectives, a mathematical model based on spatiotemporal joint planning is generated. Obtain the initial state variables, initial control variables, and initial penalty factors; Using a preset algorithm and based on the initial state variables and the initial penalty factor, the mathematical model based on spatiotemporal joint programming is iterated to obtain the planned path for the vehicle; The step of employing a preset algorithm and iterating the spatiotemporal joint programming-based mathematical model based on the initial state variables and the initial penalty factor to obtain the planned path for the vehicle includes: In the i-th iteration, the driving cost of the vehicle is calculated based on the target penalty factor, target state quantity, target control quantity, and the mathematical model based on spatiotemporal joint programming, where i is a positive integer; If the driving cost of the vehicle does not meet the preset conditions, the gradient information of the state quantity and the gradient information of the control quantity are obtained. The updated state quantity is obtained based on the gradient information of the state quantity, the updated control quantity is obtained based on the gradient information of the control quantity, and the updated penalty factor is obtained. If the vehicle's travel cost meets the preset conditions, a planned path for the vehicle is generated based on the target state variable and the target control variable. When i is 1, the target state variable is the initial state variable, the target control variable is the initial control variable, and the target penalty factor is the initial penalty factor; when i is greater than 1, the target state variable is the updated state variable obtained in the (i-1)th iteration process, the target control variable is the updated control variable obtained in the (i-1)th iteration process, and the target penalty factor is the updated penalty factor obtained in the (i-1)th iteration process.

2. The method according to claim 1, characterized in that, The step of generating a mathematical model based on spatiotemporal joint programming, based on the road condition information and a preset optimization objective, includes: Based on the road condition information, determine the constraints that the vehicle must meet to drive. Based on the preset optimization objective, the cost function is determined; Based on the cost function and the constraints that the vehicle needs to satisfy for driving, the mathematical model based on spatiotemporal joint programming is generated.

3. The method according to claim 2, characterized in that, Based on the road condition information, the constraints that the vehicle needs to meet to drive are determined, including: Based on the boundary information of the road the vehicle is traveling on, a first constraint condition is determined, which indicates the driving range of the vehicle; or / and, Based on the driving information of the first lane and the driving information of at least one of the second lanes, a second constraint is determined. This second constraint indicates that when the vehicle travels along the planned path, the distance between it and a target vehicle is greater than a safe distance. The target vehicle includes other vehicles in the first lane and vehicles in the second lane; or / and... Based on the vehicle's kinematic equations, determine the third constraint condition; or / and, Based on the vehicle's current position, determine the fourth constraint condition; or / and, Based on the planned destination location of the vehicle, the fifth constraint condition is determined; The generation of the spatiotemporal joint programming-based mathematical model, based on the cost function and the constraints that the vehicle must satisfy for driving, includes: By adding at least one of the first constraint, the second constraint, the third constraint, the fourth constraint, and the fifth constraint to the cost function using the obstacle function algorithm, the mathematical model based on spatiotemporal joint programming is obtained.

4. The method according to claim 2, characterized in that, The preset optimization objective includes at least one of the following: a first parameter, a second parameter, a third parameter, and a fourth parameter; The first parameter is used to indicate the distance between the planned path and the reference path, and the driving cost calculated based on the cost function is positively correlated with the first parameter; The second parameter is used to indicate the smoothness of the planned path, and the driving cost calculated based on the cost function is negatively correlated with the second parameter; The third parameter is used to indicate the difference between the planned speed of the vehicle traveling on the planned path and the current speed of the vehicle. The driving cost calculated based on the cost function is positively correlated with the third parameter. The fourth parameter is used to indicate the vehicle's acceleration and deceleration performance, and the driving cost calculated based on the cost function is negatively correlated with the fourth parameter.

5. The method according to any one of claims 1 to 4, characterized in that, The acquisition of road condition information includes: If a lane-changing request is detected in the vehicle, the road condition information is obtained; or / and, Upon receiving a lane change planning instruction, the road condition information is obtained; Or / and, when the lane change planning function is enabled, obtain the traffic information.

6. A path planning device, characterized in that, The device includes: An information acquisition module is used to acquire road condition information, wherein the road condition information includes at least one of the following: boundary information of the road on which the vehicle travels, driving information of the first lane on which the vehicle travels, and driving information of at least one second lane; the road includes the first lane and at least one second lane, wherein the second lane is an adjacent lane to the first lane; The model generation module is used to generate a mathematical model based on spatiotemporal joint planning based on the road condition information and the preset optimization objective. The path planning module is used to obtain the initial state variables, initial control variables, and initial penalty factors; and to iterate the mathematical model based on spatiotemporal joint planning using a preset algorithm based on the initial state variables and the initial penalty factors to obtain the planned path of the vehicle. Specifically, the path planning module is used for: calculating the vehicle's driving cost based on the target penalty factor, target state variable, target control variable, and the spatiotemporal joint planning mathematical model during the i-th iteration, where i is a positive integer; if the vehicle's driving cost does not meet preset conditions, obtaining the gradient information of the state variable and the gradient information of the control variable, obtaining an updated state variable based on the gradient information of the state variable, obtaining an updated control variable based on the gradient information of the control variable, and obtaining an updated penalty factor; if the vehicle's driving cost meets preset conditions, generating the vehicle's planned path based on the target state variable and the target control variable; when i is 1, the target state variable is the initial state variable, the target control variable is the initial control variable, and the target penalty factor is the initial penalty factor; when i is greater than 1, the target state variable is the updated state variable obtained in the (i-1)-th iteration, the target control variable is the updated control variable obtained in the (i-1)-th iteration, and the target penalty factor is the updated penalty factor obtained in the (i-1)-th iteration.

7. A vehicle, characterized in that, The vehicles include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that can be invoked by a processor to perform the method as described in any one of claims 1-5.

Images