Driving path planning method and system and storage medium

Abstract

The invention relates to the technical field of automatic driving, and provides a driving path planning method and system and a storage medium, and the method comprises the steps: recognizing the type of a current driving scene of a vehicle according to the current state information of the vehicle, environment perception information, driving behavior decision information and the predicted trajectory information of an obstacle; then dynamically adjusting the weight corresponding to the driving scene type in the trajectory optimization cost function, and constructing an optimized trajectory optimization cost function by using each adjusted weight coefficient; and solving the optimized trajectory optimization cost function to obtain an optimal trajectory as a local driving path planning result. According to the invention, the technical effect of carrying out accurate self-adaptive adjustment on the weight according to the changeable traffic environment, the real-time state of the vehicle and the obstacle is realized.

Description

Driving route planning methods, systems and storage media Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a driving path planning method, system, and computer-readable storage medium. Background Technology

[0002] In the development of intelligent driving, local path planning, as a key link in decision-making and control, directly affects the safety and efficiency of intelligent driving. Current mainstream planning algorithms mostly rely on predefined cost functions with fixed weights. This fixed-weight strategy has the following technical drawbacks when facing driving scenarios such as low-speed parking, high-speed cruising, emergency obstacle avoidance, and active lane changing: 1) In lane-changing scenarios requiring rapid lateral displacement and following scenarios requiring stable centering, fixed weights can easily lead to lateral overshoot at the end of lane changes or slow lateral convergence during centering; 2) If the following distance error weight cannot be dynamically adjusted with vehicle speed, it may lead to following too closely in low-speed congestion, increasing the risk of collision; while at high speeds, it may lead to following too far, reducing road efficiency; 3) The smoothness weight used to penalize acceleration or rate of curvature change, if it does not consider the vehicle's current dynamic limits, may generate control commands that exceed the actuator's response range, affecting ride comfort; 4) If the planning process fails to fully consider the relative attitude relationship between the vehicle and the endpoint of the reference path, it may lead to lateral deviation or heading deviation at the end of the trajectory, affecting driving safety.

[0003] Current improvements to fixed-weight strategies only involve simple linear adjustments or offline parameter tuning, which are insufficient to achieve precise adaptive adjustments of weights based on changing traffic conditions, real-time vehicle status, and obstacles during vehicle operation.

[0004] Therefore, there is an urgent need for a driving path planning technology based on weight adaptive adjustment that is applicable to various scenarios, in order to ensure the efficiency and safety of intelligent driving. Summary of the Invention

[0005] This invention provides a driving path planning method, system, and storage medium that can solve the problem of not being able to accurately and adaptively adjust weights based on changing traffic environments, real-time vehicle status, and obstacles during vehicle operation.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, embodiments of the present invention provide a driving path planning method applied to an electronic device, comprising: determining obstacles that pose a risk to vehicle driving based on pre-acquired vehicle current state information, environmental perception information, and driving behavior decision information, and acquiring predicted trajectory information of the obstacles; identifying the driving scenario type currently in which the vehicle is located based on the vehicle current state information, the environmental perception information, the driving behavior decision information, and the predicted trajectory information of the obstacles; wherein the driving scenario type includes lane centering and following, lane change response, and emergency obstacle avoidance; dynamically adjusting the weights corresponding to the driving scenario type in the trajectory optimization cost function based on the vehicle's current position and the relative positional relationship between the current position and the endpoint of a reference path, and constructing an optimized trajectory optimization cost function using the adjusted weight coefficients; solving the trajectory optimization cost function using an improved CILQR algorithm to obtain the optimal trajectory, and using it as a local driving path planning result.

[0007] In addition, an optional technical solution is that the weights include lateral position weights, heading angle weights, longitudinal following distance weights, obstacle weights, and control quantity smoothing weights.

[0008] In addition, an optional technical solution is that when the current driving scenario of the vehicle is lane centering and following or lane changing response, the method for dynamically adjusting the weights corresponding to the driving scenario type in the trajectory optimization cost function includes: dynamically adjusting the lateral position weight and the heading angle weight using an exponential decay function; dynamically adjusting the longitudinal following distance error weight using an error square function; and dynamically adjusting the control quantity smoothing weight using a dynamic limit function.

[0009] Alternatively, an optional technical solution is to dynamically adjust the lateral position weight and the heading angle weight using an exponential decay function, achieved through the following formula: ;in, The adjusted weights, Here, k represents the initial weights, and k is the decay coefficient. The vehicle's current location. As the starting point for planning, The longitudinal following distance error weight is dynamically adjusted using the error square function, with the reference path endpoint as the reference. This adjustment is achieved through the following formula. ;in, The adjusted following weight, As the initial car-following weight, The current speed of the vehicle; Speed ​​limits for roads, This represents the speed of the vehicle in front of the current vehicle.

[0010] Alternatively, an optional technical solution is to dynamically adjust the smoothing weights of the control quantity using a dynamic limit function, achieved through the following formula: ;in, Smooth the weights of the adjusted control values; Smoothing weights for the initial control input; The current acceleration; It is the change in acceleration; This represents the maximum acceleration at the current vehicle speed. for The maximum change in acceleration within the permissible range.

[0011] In addition, an optional technical solution is to use an improved CILQR algorithm to solve the optimized trajectory optimization cost function, which includes setting a condition number threshold based on the Hessian matrix of the cost function, dynamically adjusting the regularization parameter based on the condition number threshold; setting a current acceleration change threshold, adaptively adjusting the forward propagation step size based on the current acceleration change threshold; and applying enhanced constraint weights to the lateral position error and heading angle error of the planned trajectory endpoint in lane-changing or centering-following scenarios.

[0012] In addition, an optional technical solution is that the step of obtaining the optimal trajectory as the local driving path planning result further includes verifying the optimal trajectory and using the optimal trajectory that passes the verification as the local driving path planning result; wherein, the verification includes collision risk detection, vehicle dynamics feasibility verification, and ride comfort assessment.

[0013] Secondly, the present invention provides a driving path planning system, comprising: a data acquisition unit, configured to determine obstacles that pose a risk to vehicle driving based on pre-acquired vehicle current state information, environmental perception information, and driving behavior decision information, and to acquire predicted trajectory information of the obstacles; an identification unit, configured to identify the driving scenario type currently in which the vehicle is located based on the vehicle current state information, the environmental perception information, the driving behavior decision information, and the predicted trajectory information of the obstacles; wherein the driving scenario type includes lane centering and following, lane change response, and emergency obstacle avoidance; a weight adjustment unit, configured to dynamically adjust the weights corresponding to the driving scenario type in the trajectory optimization cost function based on the driving scenario type currently in which the vehicle is located, the vehicle's current position, and the relative positional relationship between the current position and the endpoint of the reference path, and to construct an optimized trajectory optimization cost function using the adjusted weight coefficients; and a driving path acquisition unit, configured to solve the trajectory optimization cost function using an improved CILQR algorithm to obtain the optimal trajectory, and to use it as a local driving path planning result.

[0014] Thirdly, the present invention provides an electronic device, the electronic device including a memory, a processor and a driving route planning program stored in the memory and executable on the processor, wherein the driving route planning program, when executed by the processor, implements the driving route planning method as described above.

[0015] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing instructions that, when executed on an electronic device, cause the electronic device to perform a driving route planning method as described in any of the first aspects.

[0016] Based on the driving path planning method, system, and storage medium of the present invention, a complete local path planning system based on scene recognition, adaptive weight adjustment, trajectory optimization, and trajectory verification is provided. Through a dynamic weight adaptive mechanism, it can adapt to various complex scenarios such as low-speed parking, high-speed cruising, emergency obstacle avoidance, and lane changing / overtaking; by adaptively adjusting the control quantity to smooth the weights, it avoids abrupt changes in control quantity and improves ride comfort; through a hard constraint mechanism at the end of the trajectory, it avoids lateral overshoot or heading angle deviation at the end of the trajectory; and through adaptive regularization and dynamic step size search mechanisms, it improves the algorithm's convergence efficiency and meets real-time requirements.

[0017] Understandably, the system described in the second aspect, the electronic device described in the third aspect, and the computer storage medium described in the fourth aspect are all used to execute the corresponding method in the first aspect provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding method provided above, and will not be repeated here. Attached Figure Description

[0018] Figure 1 is a flowchart of the driving route planning method provided in an embodiment of this application; Figure 2 is a block diagram of the driving route planning system provided in an embodiment of this application; Figure 3 is a structural schematic diagram of an electronic device provided in an embodiment of this application.

[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0021] CILQR (Constrained Iterative Linear Quadratic Regulator) is an improved version of the traditional iLQR algorithm, specifically designed to handle optimal control problems of constrained nonlinear systems. It updates the control input and state based on iLQR; if the constraints are exceeded, it projects them back to the constraints; and then continues the next optimization step after projection.

[0022] A cost function, used in mathematical optimization, statistics, econometrics, decision theory, machine learning, and computational neuroscience, is also called a loss function or error function. It maps the threshold of one or more variables to an intuitive representation of that event. An optimization problem attempts to minimize the loss function. The objective function is the loss function or its negative, which in this case, it is maximized. Optimization refers to the task of changing x to minimize or maximize a function f(x). Minimizing f(x) is commonly used to refer to most optimization problems. Maximization can be achieved by minimizing −f(x) using a minimization algorithm.

[0023] Local path planning is typically used in unknown or partially known environments. The system uses sensors to acquire real-time information about environmental obstacles and makes corresponding plans. After obtaining destination information, a roughly feasible route is first planned through global path planning. Then, the local path planner is invoked to plan the robot's specific action strategies based on this route and costmap information. Commonly used local path planning algorithms include Dynamic Window (DWA), Time Flexible Band (TEB), and Model Predictive Control (MPC).

[0024] This invention provides a driving path planning method. An environmental perception module transmits processed positioning information, obstacle information, and road structure information to a decision module via a high-speed data interface. The decision module integrates the received environmental information, vehicle status information, and driving behavior decision commands from the upper layer. Subsequently, it executes a series of steps including scene recognition, dynamic adaptive weight adjustment, trajectory optimization, and verification, ultimately generating a trajectory point sequence with speed information. The decision module sends the generated trajectory point sequence to the vehicle control module via the vehicle's CAN bus or a higher-speed communication link. The vehicle control module (typically including a longitudinal throttle / brake controller and a lateral steering controller) receives the trajectory commands and tracks the vehicle's position and speed using underlying control algorithms. Simultaneously, the vehicle control module feeds back the current actual vehicle state (such as actual speed and steering wheel angle) to the decision module in real time via the CAN bus, forming a state closed loop. Based on the feedback of the actual vehicle state, the decision module corrects the planning starting point or state estimate in the next planning cycle, thereby enabling path planning to adapt to the vehicle's actual dynamic response and improving the accuracy and robustness of trajectory tracking. Through the dynamic weight adaptive mechanism and improved optimization algorithm of this invention, the system can achieve high-quality and high-reliability local path planning in complex real-time traffic environments.

[0025] This invention provides a driving route planning method. Referring to Figure 1, which is a flowchart illustrating the driving route planning method provided in an embodiment of this invention, the method can be executed by a device, which can be implemented in software and / or hardware.

[0026] As shown in Figure 1, the present invention provides a driving route planning method including the following steps.

[0027] S110. Based on the pre-acquired vehicle current status information, environmental perception information, and driving behavior decision information, identify obstacles that pose a risk to vehicle driving, and acquire the predicted trajectory information of the obstacles.

[0028] It should be noted that the vehicle's current state information, i.e., its own vehicle state information, includes, but is not limited to, real-time parameters such as vehicle speed, acceleration, heading angle, and yaw rate obtained from the vehicle bus. Environmental perception information mainly includes positioning information, obstacle information, and road structure information. Positioning information refers to the vehicle's global position and attitude. Obstacle information includes the type, position, speed, and predicted trajectory of surrounding dynamic and static obstacles. Road structure information includes geometric and semantic information such as lane lines, curbs, and traffic signs. It should be noted that road structure information can include reference path information and road boundary information. Reference path information is the sequence of desired driving path points issued from the global planner or generated based on the road structure. Road boundary information is the geometric description of the left and right boundaries of the vehicle's driving area. Driving behavior decision commands, i.e., driving behavior decision information, are generated by the upper-level behavior planning module, indicating the current driving intention, such as lane centering and following the vehicle in front, lane change response, and emergency obstacle avoidance. Obstacles can include vehicles ahead in the same lane, vehicles to the side in adjacent lanes, and vehicles coming from the opposite lane; they can also include pedestrians, non-motorized vehicles, etc.; and can also include construction area signs, temporary roadblocks, broken-down parked vehicles, fallen objects, curbs, medians, bridge piers, guardrails, etc.

[0029] In the specific implementation process, obstacles that pose a risk to vehicle driving are identified based on the vehicle's current state information, environmental perception information, and driving behavior decision information. This can be achieved through a classification and recognition network, for example, by calculating the collision based on the vehicle's trajectory and the predicted trajectory of the obstacle.

[0030] In addition, for obtaining the predicted trajectory information of the identified obstacles, the predicted trajectory of the obstacles is the input and can be calculated based on a deep learning neural network in a separate obstacle prediction module.

[0031] S120. Based on the vehicle's current status information, the environmental perception information, the driving behavior decision information, and the predicted trajectory information of the obstacle, identify the driving scenario type in which the vehicle is currently located; wherein, the driving scenario type includes lane centering and following, lane change response, and emergency obstacle avoidance.

[0032] Based on the vehicle's current state information, the environmental perception information, the preset driving behavior decision information, and the predicted trajectory information of the obstacles, the identification of the driving scenario type currently in which the vehicle is located can be achieved through a decision state machine, a rule-based classifier, or a lightweight model.

[0033] S130. Based on the current driving scenario type of the vehicle, and according to the vehicle's current position and its relative position to the endpoint of the reference path, the weights corresponding to the driving scenario type in the trajectory optimization cost function are dynamically adjusted. The optimized trajectory optimization cost function is then constructed using the adjusted weight coefficients. The cost function is as follows: in, For adaptive lateral position weights; Let i be the lateral position of the i-th planned trajectory point; Let i be the horizontal position of the i-th reference point; For adaptive heading angle weighting; Let be the heading angle of the i-th planned trajectory point; Let be the heading angle of the i-th reference point; The adjusted following weight; The speed of the vehicle; The speed of the vehicle in front of the current vehicle; Smooth the weights for the adjusted control values.

[0034] In the specific implementation process, the weights include lateral position weight, heading angle weight, longitudinal following distance weight, obstacle weight, and control quantity smoothing weight.

[0035] When the current driving scenario of the vehicle is either lane centering and following another vehicle or lane changing response, the method for dynamically adjusting the weights corresponding to the driving scenario type in the trajectory optimization cost function includes: S1301, dynamically adjusting the lateral position weights and the heading angle weights using an exponential decay function. That is, based on the vehicle's current position and its relative position to the endpoint of the reference path, the lateral position weights and the heading angle weights are dynamically adjusted using an exponential decay function.

[0036] Specifically, the dynamic adjustment of the lateral position weight and the heading angle weight using the exponential decay function is achieved through the following formula: ;in, The adjusted weights, Here, k represents the initial weights, and k is the decay coefficient. The vehicle's current location. As the starting point for planning, This is the endpoint of the reference path.

[0037] S1302. The longitudinal following distance error weight is dynamically adjusted using the error square function.

[0038] The longitudinal following distance error weight is dynamically adjusted using the error square function, which is achieved through the following formula. ;in, The adjusted following weight, As the initial car-following weight, The current speed of the vehicle; Speed ​​limits for roads, This represents the speed of the vehicle in front of the current vehicle.

[0039] S1303. The smoothing weight of the control quantity is dynamically adjusted using the dynamic limit function.

[0040] In all driving scenario types, the smoothing weights of the control quantity need to be dynamically adjusted using the dynamic limit function, which is achieved through the following formula: ;in, Smooth the weights of the adjusted control values; Smoothing weights for the initial control input; The current acceleration; It is the change in acceleration; This represents the maximum acceleration at the current vehicle speed. for The maximum permissible change in acceleration.

[0041] This is the acceleration control value for the current frame; This is the acceleration control value from the previous frame.

[0042] S140. The improved CILQR algorithm is used to solve the trajectory optimization cost function to obtain the optimal trajectory, which is then used as the result of local driving path planning.

[0043] The method for solving the optimized trajectory optimization cost function using the improved CILQR algorithm includes steps S141-S143.

[0044] S141. Set the condition number threshold according to the cost function Hessian matrix, and dynamically adjust the regularization parameter according to the condition number threshold.

[0045] The Hessian matrix (or Hessian) is a square matrix composed of the second-order partial derivatives of a real-valued function whose independent variable is a vector. In specific implementations, the condition number threshold can be 1e. -3 For example, when the average condition number < 1e -3 If the regularization parameter λ is increased by a factor of 2, it is to avoid numerical ill-conditioning. When the mean condition number > 1e... 3 If the regularization parameter λ is reduced by a factor of 0.7, the convergence efficiency will be improved.

[0046] S142. Set the current acceleration change threshold, and adaptively adjust the forward propagation step size according to the current acceleration change threshold.

[0047] For example, the current acceleration change is >1 m / s². 2 If the forward propagation step size α is halved, it is to avoid abrupt changes in control variables; the current acceleration change is <0.5 m / s². 2 If the forward propagation step size α is increased by 1.5 times, the convergence speed will be improved.

[0048] S143. In lane-changing or center-following scenarios, apply enhanced constraint weights to the lateral position error and heading angle error of the planned trajectory endpoint.

[0049] Specifically, when the vehicle is currently in a lane-centering and following scenario or a lane-changing response, the lateral position of the planned trajectory endpoint and the heading angle weights are forcibly constrained according to preset thresholds. For example, when the driving scenario is a lane-changing scenario, the weight of the lateral position error at the end is increased by a factor of 10,000. When the driving scenario is a lane-centering and following scenario, the weight of the heading angle error at the end is increased by a factor of 1,000 to avoid end-point overshoot.

[0050] S150 (not shown in the figure), the step of obtaining the optimal trajectory as the local driving path planning result, further includes verifying the optimal trajectory and using the optimal trajectory that passes the verification as the local driving path planning result; wherein, the verification includes collision risk detection, vehicle dynamics feasibility verification and ride comfort assessment.

[0051] For example, collision risk detection can be performed using the common OBB algorithm. Vehicle dynamics feasibility verification and ride comfort assessment can be directly evaluated by checking whether the state and control variables at the planned trajectory points meet thresholds.

[0052] The driving path planning method of this invention provides a complete local path planning system based on scene recognition, adaptive weight adjustment, trajectory optimization, and trajectory verification. Through a dynamic weight adaptation mechanism, it can adapt to various complex scenarios such as low-speed parking, high-speed cruising, emergency obstacle avoidance, and lane changing / overtaking. By adaptively adjusting the control quantity to smooth the weights, it avoids abrupt changes in control quantity and improves ride comfort. Through a hard constraint mechanism at the end of the trajectory, it avoids lateral overshoot or heading angle deviation at the end of the trajectory. Through adaptive regularization and dynamic step size search mechanisms, it improves the algorithm's convergence efficiency and meets real-time requirements.

[0053] Figure 2 shows a block diagram of the driving route planning system of the present invention.

[0054] The driving route planning system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the driving route planning system may include: a data acquisition unit 101, a recognition unit 102, a weight adjustment unit 103, and a driving route acquisition unit 104. The units described in this invention can also be called modules, which mainly refer to a series of computer program segments that can be executed by the processor of an electronic device and can perform fixed functions, and are stored in the memory of the electronic device.

[0055] In this embodiment, the functions of each module / unit are as follows: The data acquisition unit 101 is used to determine obstacles that pose a risk to the vehicle's driving based on the pre-acquired vehicle current status information, environmental perception information, and driving behavior decision information, and to acquire the predicted trajectory information of the obstacles.

[0056] The identification unit 102 is used to identify the driving scenario type currently in which the vehicle is located based on the vehicle's current state information, the environmental perception information, the preset driving behavior decision information, and the predicted trajectory information of the obstacle; wherein, the driving scenario type includes lane centering and following, lane change response, and emergency obstacle avoidance; the weight adjustment unit 103 is used to dynamically adjust the weights corresponding to the driving scenario type in the trajectory optimization cost function based on the driving scenario type currently in which the vehicle is located, the vehicle's current position, and the relative positional relationship between the current position and the endpoint of the reference path, and construct an optimized trajectory optimization cost function using the adjusted weight coefficients; the driving path acquisition unit 104 is used to solve the trajectory optimization cost function using an improved CILQR algorithm to obtain the optimal trajectory, and use it as the result of local driving path planning.

[0057] The driving path planning system 100 described in this invention provides a complete local path planning system based on scene recognition, adaptive weight adjustment, trajectory optimization, and trajectory verification. Through a dynamic weight adaptive mechanism, it can adapt to various complex scenarios such as low-speed parking, high-speed cruising, emergency obstacle avoidance, and lane changing / overtaking. By adaptively adjusting the control quantity to smooth the weights, it avoids abrupt changes in control quantity, improving ride comfort. Through a hard constraint mechanism at the end of the trajectory, it avoids lateral overshoot or heading angle deviation at the end. Through adaptive regularization and dynamic step size search mechanisms, it improves algorithm convergence efficiency and meets real-time requirements.

[0058] It should be noted that the embodiments of the driving route planning system and the driving route planning method described above can be used for reference, and will not be elaborated further here.

[0059] Figure 3 is a schematic diagram of the electronic device that implements the driving path planning method of the present invention.

[0060] As shown in Figure 3, the electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program, such as a driving route planning program 12, stored in the memory 11 and capable of running on the processor 10.

[0061] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 can include both internal and external storage units of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a driving route planning program, but also to temporarily store data that has been output or will be output.

[0062] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules (such as driving route planning programs) stored in the memory 11, and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0063] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0064] Figure 3 only shows an electronic device with components. Those skilled in the art will understand that the structure shown in Figure 3 does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0065] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0066] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0067] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0068] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0069] The driving route planning program 12 stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can implement a driving route planning method.

[0070] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0071] In the several embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A driving route planning method, applied to electronic devices, characterized in that, The method includes: identifying obstacles that pose a risk to vehicle driving based on pre-acquired vehicle current state information, environmental perception information, and driving behavior decision information, and acquiring predicted trajectory information of the obstacles; identifying the driving scenario type currently in which the vehicle is located based on the vehicle current state information, the environmental perception information, the driving behavior decision information, and the predicted trajectory information of the obstacles; wherein, the driving scenario type includes lane centering and following, lane change response, and emergency obstacle avoidance; dynamically adjusting the weights corresponding to the driving scenario type in the trajectory optimization cost function based on the vehicle's current position and the relative positional relationship between the current position and the endpoint of the reference path, and constructing an optimized trajectory optimization cost function using the adjusted weight coefficients; solving the trajectory optimization cost function using an improved CILQR algorithm to obtain the optimal trajectory, which is used as the local driving path planning result.

2. The driving route planning method as described in claim 1, characterized in that, The weights include lateral position weight, heading angle weight, longitudinal following distance weight, obstacle weight, and control quantity smoothing weight.

3. The driving route planning method as described in claim 2, characterized in that, When the current driving scenario of the vehicle is lane centering and following or lane changing response, the method for dynamically adjusting the weights corresponding to the driving scenario type in the trajectory optimization cost function includes: dynamically adjusting the lateral position weight and the heading angle weight using an exponential decay function; dynamically adjusting the longitudinal following distance error weight using an error square function; and dynamically adjusting the control quantity smoothing weight using a dynamic limit function.

4. The driving route planning method as described in claim 3, characterized in that, The dynamic adjustment of the lateral position weight and the heading angle weight using an exponential decay function is achieved through the following formula: ;in, The adjusted weights, Here, k represents the initial weights, and k is the decay coefficient. The vehicle's current location. As the starting point for planning, The longitudinal following distance error weight is dynamically adjusted using the error square function, with the reference path endpoint as the reference. This adjustment is achieved through the following formula. ;in, The adjusted following weight, As the initial car-following weight, The current speed of the vehicle; Speed ​​limits for roads, This represents the speed of the vehicle in front of the current vehicle.

5. The driving route planning method as described in claim 3, characterized in that, The smoothing weights of the control quantity are dynamically adjusted using the dynamic limit function, which is achieved through the following formula: ;in, Smooth the weights of the adjusted control values; Smoothing weights for the initial control input; The current acceleration; It is the change in acceleration; This represents the maximum acceleration at the current vehicle speed. for The maximum change in acceleration within the permissible range.

6. The driving route planning method as described in claim 1, characterized in that, The method for solving the optimized trajectory optimization cost function using the improved CILQR algorithm includes setting a condition number threshold based on the Hessian matrix of the cost function, and dynamically adjusting the regularization parameter based on the condition number threshold. Set a current acceleration change threshold, and adaptively adjust the forward propagation step size based on the current acceleration change threshold; in lane changing or centering following scenarios, apply enhanced constraint weights to the lateral position error and heading angle error of the planned trajectory endpoint.

7. The driving route planning method as described in claim 1, characterized in that, The step of obtaining the optimal trajectory as the local driving path planning result further includes verifying the optimal trajectory and using the optimal trajectory that passes the verification as the local driving path planning result; wherein, the verification includes collision risk detection, vehicle dynamics feasibility verification, and ride comfort assessment.

8. A driving route planning system, characterized in that, include: The data acquisition unit is used to determine obstacles that pose a risk to the vehicle's driving based on pre-acquired vehicle current status information, environmental perception information, and driving behavior decision information, and to acquire the predicted trajectory information of the obstacles. The identification unit is used to identify the driving scenario type currently in which the vehicle is located based on the vehicle's current state information, the environmental perception information, the driving behavior decision information, and the predicted trajectory information of the obstacle; wherein, the driving scenario type includes lane centering and following, lane change response, and emergency obstacle avoidance; The weight adjustment unit is used to dynamically adjust the weights corresponding to the driving scenario type in the trajectory optimization cost function based on the current driving scenario type of the vehicle, the current position of the vehicle, and the relative positional relationship between the current position and the endpoint of the reference path. The adjusted weight coefficients are used to construct the optimized trajectory optimization cost function. The driving path acquisition unit is used to solve the trajectory optimization cost function using the improved CILQR algorithm to obtain the optimal trajectory and use it as the local driving path planning result.

9. An electronic device, characterized in that, The system includes a memory, a processor, and a driving route planning program stored in the memory and executable on the processor, wherein the driving route planning program, when executed by the processor, implements the driving route planning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing instructions, characterized in that, When the instructions are executed on an electronic device, the electronic device causes the electronic device to perform the driving route planning method as described in any one of claims 1-7.

Images