Path planning method, device and equipment of autonomous vehicle and medium

Abstract

Embodiments of the present application disclose a path planning method, device and equipment for an autonomous vehicle, and a medium. The method comprises: in response to a path planning instruction, determining target driving data of a target vehicle in at least two preset driving stages in a target scene; performing a double independent sample T test on the target driving data according to reference driving data in the target scene, and determining a driving characteristic parameter of the target vehicle according to a sample test result; wherein the target vehicle is adapted to a target object, and the driving characteristic parameter is used to reflect a driving behavior characteristic of the target object in the target scene; determining an environment potential field of the target scene according to the driving characteristic parameter, and performing path planning on the target vehicle according to the environment potential field. The technical solution can determine an individualized driving characteristic parameter through real driving data, effectively overcomes the problems of driving data distortion and subjective evaluation, and improves the scientificity and rationality of vehicle path planning.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a path planning method, apparatus, device, and medium for autonomous vehicles. Background Technology

[0002] With the rapid development of vehicle technology, autonomous vehicles are gradually becoming more common in daily life. Autonomous vehicles serve people and need to consider personalized driving needs. In real-world traffic environments, different drivers exhibit significantly different driving behaviors, and autonomous driving decision-making and control methods based on a single behavior pattern cannot adapt to the diverse driving needs of different drivers.

[0003] Currently, there are two main approaches to studying the driving behavior characteristics of different drivers. The first is through methods such as questionnaires and measurement scales, and the second is through simulation experiments using driving simulators. The first method is highly subjective and the amount of data obtained is significantly limited, resulting in results that cannot accurately reflect real-world conditions. The second method suffers from distortions in driving scenarios and environments, making it difficult to obtain data that closely approximates real-world driving behavior, and similarly, it fails to accurately reflect actual conditions, thus making it difficult to meet real-world driving needs. Summary of the Invention

[0004] This invention provides a path planning method, apparatus, device, and medium for autonomous vehicles, which can determine personalized driving characteristic parameters through real driving data, effectively overcoming the problems of driving data distortion and subjective evaluation, and improving the scientificity and rationality of vehicle path planning.

[0005] According to one aspect of the present invention, a path planning method for an autonomous vehicle is provided, the method comprising:

[0006] In response to path planning instructions, determine target driving data for the target vehicle in at least two preset driving stages in the target scenario;

[0007] Based on reference driving data in the target scenario, a two-independent-samples t-test is performed on the target driving data, and the driving characteristic parameters of the target vehicle are determined based on the sample test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters are used to reflect the driving behavior characteristics of the target object in the target scenario;

[0008] The environmental potential field of the target scene is determined based on the driving characteristic parameters, and the target vehicle is path planned based on the environmental potential field.

[0009] According to another aspect of the present invention, a path planning device for an autonomous vehicle is provided, comprising:

[0010] The target driving data determination module is used to determine the target driving data of the target vehicle in at least two preset driving stages in the target scenario in response to the path planning command.

[0011] The driving characteristic parameter determination module is used to perform a two-independent-samples t-test on the target driving data based on reference driving data in the target scenario, and determine the driving characteristic parameters of the target vehicle based on the sample test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters are used to reflect the driving behavior characteristics of the target object in the target scenario;

[0012] The target vehicle path planning module is used to determine the environmental potential field of the target scene based on the driving characteristic parameters, and to plan the path of the target vehicle based on the environmental potential field.

[0013] According to another aspect of the present invention, a path planning electronic device for an autonomous vehicle is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the path planning method for an autonomous vehicle according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the path planning method for an autonomous vehicle according to any embodiment of the present invention.

[0018] The technical solution of this invention, in response to a path planning command, determines target driving data for a target vehicle in at least two preset driving stages within a target scenario; performs a two-independent-samples t-test on the target driving data based on reference driving data in the target scenario, and determines the driving characteristic parameters of the target vehicle based on the t-test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters reflect the driving behavior characteristics of the target object in the target scenario; the environmental potential field of the target scenario is determined based on the driving characteristic parameters, and path planning is performed on the target vehicle based on the environmental potential field. This technical solution can determine personalized driving characteristic parameters through real driving data, effectively overcoming the problems of driving data distortion and subjective evaluation, and improving the scientificity and rationality of vehicle path planning.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a path planning method for an autonomous vehicle according to Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a path planning method for an autonomous vehicle according to Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of a path planning device for an autonomous vehicle according to Embodiment 3 of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a path planning method for an autonomous vehicle according to an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1 This is a flowchart of a path planning method for an autonomous vehicle provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where vehicle path planning is performed based on personalized driving characteristic parameters. This method can be executed by a path planning device for the autonomous vehicle, which can be implemented in hardware and / or software. This path planning device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0029] S110, in response to the path planning instruction, determines the target driving data of the target vehicle in at least two preset driving stages in the target scenario.

[0030] The path planning instruction can refer to an operational instruction that allows vehicle path planning. The target vehicle can refer to an autonomous vehicle waiting for path planning. The target scenario can refer to the actual driving scenario of the target vehicle. For example, the target scenario can include a car-following scenario or a lane-changing scenario. The preset driving stage can refer to a pre-set vehicle driving stage, which can be determined according to the target scenario. For example, assuming the target scenario is a car-following scenario, the corresponding preset driving stage can include the approaching vehicle stage, the car-following driving stage, and the separation stage from the vehicle in front. Assuming the target scenario is a lane-changing scenario, the corresponding preset driving stage can include a longitudinal driving stage and a lateral driving stage. The longitudinal driving stage includes the approaching vehicle stage, the car-following driving stage, and the separation stage from the vehicle in front, while the lateral driving stage includes the lane-changing preparation stage, the lane-changing execution stage, and the lane-changing termination stage. That is, the lane-changing scenario includes the car-following scenario. The target driving data can refer to the driving data of the target vehicle in at least two preset driving stages in the target scenario.

[0031] In this embodiment, if a path planning instruction is detected, the target driving data for at least two preset driving stages of the target vehicle in the target scenario is first determined. Optionally, determining the target driving data for at least two preset driving stages of the target vehicle in the target scenario includes: acquiring first driving data of the target vehicle in the target scenario; performing Kalman filtering on the first driving data to obtain second driving data; and performing fuzzy C-means clustering based on time-series constraints on the second driving data to obtain the target driving data for at least two preset driving stages of the target vehicle in the target scenario.

[0032] The first driving data can refer to the raw driving data of the target vehicle in the target scenario. Specifically, the first driving data can be obtained through multiple sensors on the target vehicle. This first driving data can include multiple vehicle driving parameters, which can be determined based on the target scenario. For example, in a car-following scenario, vehicle driving parameters can include headway, longitudinal speed, and longitudinal acceleration; in a lane-changing scenario, vehicle driving parameters can include headway, longitudinal speed, longitudinal acceleration, lane departure, heading angle, yaw rate, and yaw acceleration. Headway can be understood as representing the distance between the target vehicle and the vehicle in front over time, and can be expressed as the ratio of the longitudinal distance between the target vehicle and the vehicle in front to the longitudinal speed of the target vehicle. The second driving data can refer to the vehicle driving data obtained after applying Kalman filtering to the first driving data.

[0033] For example, taking a car-following scenario, the driver's driving behavior characteristics are mainly reflected in the vehicle's longitudinal operations. Therefore, the headway, longitudinal speed, and longitudinal acceleration can be selected as the vehicle driving parameters for the car-following scenario, and the first driving data corresponding to these parameters can be obtained. The second driving data can be obtained by processing the first driving data using a Kalman filter. Specifically, the state variable used in the Kalman filter is as follows: X(t) = [s...] n (t),v n (t),a n (t)] T , where s n (t) represents the headway of the target vehicle, v n (t) represents the longitudinal speed of the target vehicle, a n (t) represents the longitudinal acceleration of the target vehicle.

[0034] Based on the physical properties, the following state-space equations can be established:

[0035] X(t+1)=F t ×X(t)+V(t); Y(t)=H t ×X(t)+W(t).

[0036] in, β is the acceleration transfer coefficient, V(t) and W(t) are white noise, X represents the state variable, and Y represents the observed value. Based on this, a corresponding Kalman filter can be designed, as shown in the following equation:

[0037]

[0038]

[0039]

[0040] in, This represents all observed values ​​Y0,…,Y N The estimated X t The value, To estimate the covariance of the state, a Kalman filter can be used to perform Kalman filtering on the first driving data to obtain the second driving data.

[0041] After obtaining the second driving data, the second driving data in the car-following scenario can be classified using a time-constrained fuzzy C-means clustering method, ultimately yielding the stages of approaching the preceding vehicle, following the preceding vehicle, and separating from the preceding vehicle. Specifically, the membership value between each second driving data point and each stage is first determined. Then, the cluster centers are calculated using the following formula. in, For the Kalman-filtered data (i.e., the second driving data), m = 2 is selected. Then, the new membership values ​​are calculated using the following formula: in, express The distance to the i-th cluster center. Finally, the iteration can be determined based on a preset threshold using the following formula: in, express The distance to cluster center i is chosen with a weight value of α = 3. When... The iteration stops when the value is less than a preset threshold; otherwise, it continues. The preset threshold can be a reference value pre-set based on the target scenario, which can be used as the basis for determining whether to stop the iteration. This embodiment does not limit this setting.

[0042] For example, taking a lane-changing scenario, the driver's driving behavior characteristics are reflected in the vehicle's combined lateral and longitudinal operations. Therefore, the headway, longitudinal speed, longitudinal acceleration, lane departure, heading angle, yaw rate, and yaw acceleration can be selected as vehicle driving parameters for the lane-changing scenario, and the first driving data corresponding to these parameters can be obtained. The second driving data can be obtained by processing the first driving data using a Kalman filter. Specifically, the state variables used in the Kalman filter are as follows:

[0043] X(t)=[s n (t),v n (t),a n (t),L h (t),φ(t),ω(t),r(t)] T Among them, L h Let φ(t) be the lane departure, φ(t) be the heading angle, ω(t) be the yaw rate, and r(t) be the yaw acceleration. Similarly, based on the physical properties, the following state-space equations can be established:

[0044] X(t+1)=F t ×X(t)+V(t); Y(t)=H t ×X(t)+W(t).

[0045] in,

[0046] The corresponding Kalman filter is the same as that in the car-following scenario, so it will not be described again here.

[0047] After obtaining the second driving data, the second driving data in the lane-changing scenario can be classified according to the fuzzy C-means clustering method based on time-series constraints, ultimately yielding the preparation stage, the execution stage, and the end stage of lane change. The specific clustering process can be found in the following scenario section, and will not be elaborated here.

[0048] This solution uses Kalman filtering to smooth the original vehicle driving data, which can eliminate outliers while reducing fluctuations. For the problem of unclear boundaries between data in different driving stages, a fuzzy C-means clustering method based on time constraints is used to classify the data in the target scenario, while ensuring that the classified data still maintains the original time order.

[0049] In this embodiment, optionally, before performing Kalman filtering on the first driving data to obtain the second driving data, the method further includes: performing time synchronization processing on the first driving data.

[0050] In this embodiment, considering that the collection of original vehicle driving data requires the use of multiple sensors, and the data collected by different sensors may be out of sync in time, the vehicle driving data collected by multiple sensors can be synchronized in time before the first driving data is processed by Kalman filtering to obtain the second driving data, thereby improving the accuracy of data collection.

[0051] S120, based on the reference driving data in the target scenario, perform a two-independent-samples T-test on the target driving data, and determine the driving characteristic parameters of the target vehicle based on the sample test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters are used to reflect the driving behavior characteristics of the target object in the target scenario.

[0052] Reference driving data can refer to vehicle driving data used as a reference. Driving feature parameters can be used to reflect the driving behavior characteristics of the target object in the target scenario, and the target vehicle is adapted to the target object; that is, when different target objects drive the same vehicle, they can be regarded as different target vehicles. It should be noted that the reference driving data and the target driving data are driving data obtained through the same processing procedure (e.g., Kalman filtering and time-constrained fuzzy C-means clustering). The reference driving data can be vehicle driving data corresponding to drivers other than the target object driving the target vehicle or other vehicles in the target scenario.

[0053] In this embodiment, optionally, a two-independent-samples t-test is performed on the target driving data based on the reference driving data in the target scenario, and the driving characteristic parameters of the target vehicle are determined based on the sample test results. This includes: performing a two-independent-samples t-test on the target driving parameters based on the reference driving data and the target driving data to obtain the target test parameters of the target driving parameters; wherein, the target test parameters are determined based on the proportion of insignificant T-values ​​of the target driving parameters; and based on the ascending order of the target test parameters, the target driving parameters corresponding to the first preset number of target test parameters are determined as the driving characteristic parameters of the target vehicle.

[0054] The target driving parameters refer to the parameter variables corresponding to the target driving data, which can be determined based on the target scenario. For example, in a car-following scenario, the driver's driving behavior is mainly reflected in the vehicle's longitudinal operation; therefore, headway, longitudinal speed, and longitudinal acceleration can be selected as the target driving parameters for this scenario. In a lane-changing scenario, the driver's driving behavior is reflected in the combined lateral and longitudinal operation; therefore, headway, longitudinal speed, longitudinal acceleration, lane departure, heading angle, yaw rate, and yaw acceleration can be selected as the target driving parameters for this scenario. Target verification parameters can serve as the basis for determining the driving characteristic parameters of the target vehicle. These parameters can be determined based on the proportion of insignificant T-values ​​of the target driving parameters. The preset quantity refers to the number of pre-set driving characteristic parameters, which can be set according to the actual needs of the target scenario.

[0055] In this embodiment, firstly, the driving data corresponding to each target driving parameter is determined from the target driving data and the reference driving data, and each pair of corresponding driving data is taken as a data group to be tested. For example, assume the target driving parameters are headway, longitudinal speed, and longitudinal acceleration. The target driving data corresponding to headway includes s1 and s2, and the reference driving data includes s1... ′ and s2 ′ For the target driving parameter of headway, four sets of data to be tested can be formed, namely s1 and s1 ′ s1 and s2 ′ s2 and s1 ′ s2 and s2 ′ .

[0056] After determining the test data set corresponding to each target driving parameter, a two-independent-samples t-test is performed on each test data set to obtain the corresponding t-value. The significance (significant or insignificant) of the t-value is then determined. Next, the ratio of the number of insignificant t-values ​​corresponding to each target driving parameter to the total amount of corresponding target driving data is calculated. This yields the proportion of insignificant t-values ​​for each target driving parameter, thus determining the target test parameter for each target driving parameter. Furthermore, the target test parameters (i.e., the proportion of insignificant t-values) for each target driving parameter can be arranged in ascending order. Based on the ascending order, the target driving parameters corresponding to the first predetermined number of smaller target test parameters are taken as the driving characteristic parameters of the target vehicle.

[0057] For example, in a car-following scenario, assuming a preset quantity of 2, the headway and longitudinal acceleration can be determined as driving characteristic parameters of the target vehicle. In a lane-changing scenario, assuming a preset quantity of 3, the headway, longitudinal acceleration, and yaw rate can be determined as driving characteristic parameters of the target vehicle.

[0058] This solution uses a two-independent-samples t-test to compare the significance of differences in various variables among different drivers, and uses the proportion of insignificant t-values ​​for each variable to extract the variable indicators that best reflect the differences in driver style in the target scenario.

[0059] S130 determines the environmental potential field of the target scene based on driving characteristic parameters, and performs path planning for the target vehicle based on the environmental potential field.

[0060] The environmental potential field refers to the force field generated based on the motion environment of the target vehicle in the target scene. This environmental potential field can include gravitational and repulsive fields. Specifically, the target point (predicted motion point) of the target vehicle and obstacles in the target scene can be considered as objects exerting gravitational and repulsive forces on the target vehicle, respectively. The target vehicle will move along the direction of the resultant force of these gravitational and repulsive forces. The potential field generated by the target point is the gravitational field, and the potential field generated by the obstacles is the repulsive field.

[0061] It should be noted that the environmental potential field should primarily consider two elements: the static traffic environment and the dynamic traffic environment. The static traffic environment mainly includes elements such as lane markings and fixed obstacles. The dynamic traffic environment mainly includes vehicles and pedestrians. Generally, static elements such as lane markings (boundary lines and lane dividers) ensure that vehicles travel stably within their lanes along the road. The overall environmental potential field can be represented as: U all =U lane +U road +U car +U goal +U obstacle , among which, U goal The potential field generated for the target point, U lane The potential field generated by the lane line, U road The potential field generated by the road boundary line, U obstacle U is the potential field generated by the obstacle. car For the potential field generated by the vehicle in the environment, U all For the overall environmental potential field.

[0062] In this embodiment, optionally, the target scenario is a car-following scenario; the preset driving stages include a approaching vehicle stage, a car-following stage, and a separation stage from the vehicle in front; driving characteristic parameters include headway and longitudinal acceleration; correspondingly, the environmental potential field of the target scenario is determined based on the driving characteristic parameters, including: determining the target potential field coefficient based on the longitudinal acceleration during the approaching vehicle stage, and determining the target potential field of the car-following scenario based on the target potential field coefficient; wherein, the target potential field is used to characterize the driving direction of the target vehicle; determining the longitudinal stable safety distance of the target vehicle based on the headway during the car-following stage, and determining the longitudinal attenuation coefficient based on the longitudinal stable safety distance and the target potential field; determining the longitudinal potential field of the car-following scenario based on the longitudinal attenuation coefficient and the headway during the separation stage from the vehicle in front; wherein, the longitudinal potential field is used to reflect the longitudinal safety distance of the target vehicle.

[0063] Here, the target potential field can refer to the potential field (U) generated by the target point. goal The longitudinal potential field (or longitudinal potential field) can be used to characterize the direction of travel of the target vehicle. The longitudinal stability safety distance refers to the longitudinal safety distance between the target vehicle and the surrounding vehicle when the target potential field and the longitudinal potential field are in equilibrium; that is, the longitudinal safety distance between the target vehicle and the surrounding vehicle during the car-following phase. The longitudinal potential field can refer to the longitudinal potential field generated by the surrounding vehicle, which can be used to reflect the longitudinal safety distance of the target vehicle. It should be noted that in the car-following scenario, since the target vehicle only travels along its own lane and its control decisions are only affected by the vehicle in front, the environmental potential field in the car-following scenario can include both the target potential field and the longitudinal potential field.

[0064] In this embodiment, the target potential field of the target vehicle in the car-following scenario is first determined. The function of this target potential field is to cause the target vehicle to travel in a predetermined direction. The formula for the target potential field is as follows: Where κ is the target potential coefficient. The predetermined driving direction is used. It should be noted that the predetermined driving direction in a car-following scenario is the longitudinal direction along the road lane. During the approach phase, the acceleration of different drivers is generally positive; therefore, using the acceleration during this approach phase to calibrate the target potential field coefficient κ better reflects the driver's acceleration characteristics. For example, the target potential field coefficient can be determined based on the average longitudinal acceleration during the approach phase, specifically expressed as κ = μ. C1,a ×g. Where, μ C1,a denoted by , where g represents the average longitudinal acceleration during the approach phase to the vehicle in front, and g represents the gravitational acceleration.

[0065] It should be noted that, according to the decay law of the longitudinal potential field, the longitudinal potential field decreases as the distance between the target vehicle and the vehicles in front increases. In a car-following scenario, the longitudinal potential field and the target potential field are in opposite directions, and when the target vehicle reaches the car-following equilibrium position, the magnitudes of the longitudinal potential field and the target potential field are equal.

[0066] In this embodiment, when determining the longitudinal potential field in a car-following scenario, the longitudinal stable safety distance of the target vehicle is first determined based on the headway during the car-following phase. Assuming that the target vehicle and the vehicles in front have the same speed during the car-following phase (stable car-following), the longitudinal stable safety distance can be determined using the following formula: in, μ represents the longitudinal stability safety distance. C2,THW u represents the average headway during the following driving phase. front Let S be the speed of the vehicle being followed in front, and S be the safe following distance from the vehicle in front. The longitudinal attenuation coefficient is then determined using the following formula: in, A represents the longitudinal potential field at the carousel equilibrium position. car,long Let λ be the longitudinal potential field coefficient (known), and λ be the longitudinal attenuation coefficient. Finally, the longitudinal potential field for the car-following scenario can be determined using the following formula: Among them, U car,long For the longitudinal potential field, D car,long This indicates the headway at the point of separation from the vehicle in front.

[0067] This solution, through this setting, can determine the environmental potential field of the car-following scenario based on the driving characteristic parameters of the target vehicle in the car-following scenario, so as to realize personalized path planning for the target vehicle in the subsequent process based on the environmental potential field.

[0068] In this embodiment, optionally, path planning for the target vehicle based on the environmental potential field includes: determining the first velocity information of the target vehicle in the vehicle coordinate system based on the environmental potential field; determining the second velocity information of the target vehicle in the reference coordinate system based on the offset angle of the vehicle coordinate system and the first velocity information; and determining the target movement distance of the target vehicle in the reference coordinate system based on the second velocity information, so as to perform path planning for the target vehicle based on the target movement distance.

[0069] The vehicle coordinate system can be a two-dimensional coordinate system established with the target vehicle as the origin, the target vehicle's travel direction as the vertical axis, and the direction perpendicular to the target vehicle's travel direction as the horizontal axis. The first speed information refers to the target vehicle's speed information in the vehicle coordinate system, specifically including speed information along the horizontal and vertical axes. The information reference coordinate system can be a pre-defined reference coordinate system used to calibrate the target vehicle's speed information, such as a geodetic coordinate system. For example, the information reference coordinate system can be a two-dimensional coordinate system established with the target vehicle as the origin, with the horizontal axis along the lane direction and the vertical axis perpendicular to the lane direction, respectively. The offset angle refers to the rotation angle of the vehicle coordinate system relative to the reference coordinate system. The second speed information refers to the target vehicle's speed information in the reference coordinate system, similarly including speed information along the horizontal and vertical axes. The target movement distance refers to the predicted movement distance of the target vehicle, which can be used as a basis for path planning for the target vehicle.

[0070] In this embodiment, the environmental potential field can be represented as U in the vehicle coordinate system. all =[APF x APF y ], among which, APF x and APF y These represent the potential field along the horizontal axis and the potential field along the vertical axis, respectively. In a car-following scenario, since the target vehicle only travels along its own lane, and the environmental potential field includes both the target potential field and the longitudinal potential field, the APF (Advanced Persistent Potential Field) is... x APF is 0. y This is the vector sum of the target potential field and the longitudinal potential field. From this, the first velocity information of the target vehicle in the vehicle coordinate system can be obtained, as shown below:

[0071] v1(i)=v1(i-1)+m×T×APF x (i);

[0072] v2(i)=v2(i-1)+n×T×APF y (i).

[0073] Where v1 and v2 represent the horizontal and vertical velocity information in the vehicle coordinate system, respectively; m and n are pre-set constant coefficients (to prevent v1 and v2 from exceeding their limits, usually set to 1); and T represents the step time, which can be set according to actual needs. In a car-following scenario, v1 = 0.

[0074] After determining the target vehicle's first velocity information in the vehicle coordinate system, this first velocity information can be transformed to the reference coordinate system based on the offset angle of the vehicle coordinate system, thereby determining the target vehicle's second velocity information in the reference coordinate system. For example, the transformation from the vehicle coordinate system to the reference coordinate system can be achieved using the following formula:

[0075] u1(i)=v2(i)×cos(θ(i))-v1(i)×sin(θ(i));

[0076] u2(i)=v1(i)×cos(θ(i))+v2(i)×sin(θ(i)).

[0077] Where u1 and u2 represent the horizontal and vertical velocity information in the reference coordinate system, respectively, and θ represents the offset angle of the vehicle coordinate system. In the car-following scenario, θ = 0.

[0078] After determining the second velocity information of the target vehicle in the reference coordinate system, the target travel distance of the target vehicle in the reference coordinate system can be further determined based on the second velocity information, so as to perform path planning for the target vehicle based on the target travel distance. For example, the target travel distance of the target vehicle in the reference coordinate system can be determined by the following formula:

[0079] D X (i+1)=u1(i)×T+X(i); D Y (i+1)=u2(i)×T+Y(i).

[0080] Among them, D X and D Y These represent the distance the target vehicle moves along the horizontal axis and the vertical axis of the reference coordinate system, respectively. In a car-following scenario, D... X =0.

[0081] This solution, through this setting, can determine the target vehicle's target movement distance in the reference coordinate system based on the environmental potential field determined by driving characteristic parameters, so as to perform personalized path planning for the target vehicle according to the target movement distance.

[0082] The technical solution of this invention, in response to a path planning command, determines target driving data for a target vehicle in at least two preset driving stages within a target scenario; performs a two-independent-samples t-test on the target driving data based on reference driving data in the target scenario, and determines the driving characteristic parameters of the target vehicle based on the t-test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters reflect the driving behavior characteristics of the target object in the target scenario; the environmental potential field of the target scenario is determined based on the driving characteristic parameters, and path planning is performed on the target vehicle based on the environmental potential field. This technical solution can determine personalized driving characteristic parameters through real driving data, effectively overcoming the problems of driving data distortion and subjective evaluation, and improving the scientificity and rationality of vehicle path planning.

[0083] Example 2

[0084] Figure 2 This is a flowchart of a path planning method for an autonomous vehicle provided in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and optimized. Specifically, the optimization is as follows: the target scenario is a lane-changing scenario; the preset driving stages include a longitudinal driving stage and a lateral driving stage. The longitudinal driving stage includes a stage of approaching the preceding vehicle, a stage of following the preceding vehicle, and a stage of separating from the preceding vehicle. The lateral driving stage includes a stage of preparing to change lanes, a stage of executing a lane change, and a stage of ending the lane change. The driving characteristic parameters include the vehicle headway, longitudinal acceleration, and yaw acceleration. Correspondingly, the environmental potential field of the target scenario is determined according to the driving characteristic parameters, including: determining the target potential field coefficient based on the longitudinal acceleration of the stage of approaching the preceding vehicle, and determining the target potential field of the lane-changing scenario based on the target potential field coefficient. In this context, the target potential field is used to characterize the driving direction of the target vehicle; the longitudinal stable safety distance of the target vehicle is determined based on the headway during the following phase, and the longitudinal attenuation coefficient is determined based on the longitudinal stable safety distance and the target potential field; the longitudinal potential field of the lane-changing scenario is determined based on the longitudinal attenuation coefficient and the headway during the separation phase from the preceding vehicle; the longitudinal potential field reflects the longitudinal safety distance of the target vehicle; the lateral attenuation coefficient is determined based on the yaw acceleration during the lane-changing phase, and the lateral potential field of the lane-changing scenario is determined based on the lateral attenuation coefficient; the lateral potential field reflects the lateral safety distance of the target vehicle.

[0085] like Figure 2 As shown, the method in this embodiment specifically includes the following steps:

[0086] S210, in response to the path planning instruction, determines the target driving data of the target vehicle in at least two preset driving stages in the lane-changing scenario.

[0087] The preset driving phases include a longitudinal driving phase and a lateral driving phase. The longitudinal driving phase includes the phase of approaching the vehicle in front, the phase of following the vehicle, and the phase of separating from the vehicle in front. The lateral driving phase includes the phase of preparing to change lanes, the phase of executing the lane change, and the phase of ending the lane change.

[0088] S220, based on the reference driving data and target driving data in the lane-changing scenario, a two-independent-samples T-test is performed on the target driving parameters to obtain the target test parameters of the target driving parameters; wherein, the target test parameters are determined based on the proportion of insignificant T-values ​​of the target driving parameters.

[0089] S230, based on the ascending order of the target inspection parameters, determine the target driving parameters corresponding to the first preset number of target inspection parameters as the driving characteristic parameters of the target vehicle.

[0090] The preset quantity is 3, and the driving characteristic parameters include headway, longitudinal acceleration, and yaw acceleration.

[0091] S240, determine the target potential field coefficient based on the longitudinal acceleration during the approach phase of the vehicle in front, and determine the target potential field for the lane-changing scenario based on the target potential field coefficient; wherein, the target potential field is used to characterize the driving direction of the target vehicle.

[0092] S250 determines the longitudinal stable safety distance of the target vehicle based on the headway during the following driving phase, and determines the longitudinal attenuation coefficient based on the longitudinal stable safety distance and the target potential field.

[0093] S260 determines the longitudinal potential field of the lane-changing scenario based on the longitudinal attenuation coefficient and the headway during the separation phase from the preceding vehicle; wherein, the longitudinal potential field is used to reflect the longitudinal safety distance of the target vehicle.

[0094] The specific implementation of S210-S260 can be referred to the description process of the car-following scenario in Embodiment 1, and will not be repeated here.

[0095] S270 determines the lateral attenuation coefficient based on the yaw acceleration during the lane-changing phase, and determines the lateral potential field of the lane-changing scenario based on the lateral attenuation coefficient; wherein, the lateral potential field is used to reflect the lateral safe distance of the target vehicle.

[0096] It should be noted that in lane-changing scenarios, since the driver's driving behavior is reflected in the combined lateral and longitudinal operations of the vehicle, the environmental potential field in a lane-changing scenario can include a target potential field, a longitudinal potential field, and a lateral potential field. For lane-changing scenarios, in addition to the target and longitudinal potential fields, the lateral potential field also needs to be calibrated. The lateral potential field can refer to the lateral potential field generated by the surrounding vehicle and can be used to reflect the lateral safe distance of the target vehicle. Specifically, the lateral potential field can be represented as follows:

[0097]

[0098] Among them, U car,lateral σ represents the lateral potential field; d represents the lateral distance between the target vehicle and the surrounding vehicle; car It is the lateral attenuation coefficient, which can be calibrated according to the lane width and the yaw acceleration during the lane change phase. The setting principle is that it should not affect vehicles in adjacent lanes, while guiding vehicles approaching from behind to change lanes.

[0099] It should be noted that a better lane-changing effect can be achieved when the magnitude of the lateral potential field at the lane-separating line is equal to the average yaw acceleration during the lane-changing phase. Therefore, the lateral attenuation coefficient σ can be calibrated using the following formula. car : in, w represents the average yaw acceleration during the lane-changing phase. lane Indicates the lane width; in this embodiment, w is selected. lane =3.5.

[0100] S280 determines the environmental potential field of the lane-changing scenario based on driving characteristic parameters, and performs path planning for the target vehicle based on the environmental potential field.

[0101] The environmental potential field includes the target potential field, the longitudinal potential field, and the lateral potential field. The implementation of S280 can refer to the description of the following scenario in Embodiment 1, the difference being that, in the process of determining the environmental potential field of the lane-changing scenario based on driving characteristic parameters, the APF... x The potential field is the horizontal field; during the path planning process for the target vehicle based on the environmental potential field, v1, θ, and D... X None of them are 0.

[0102] The technical solution of this invention can determine personalized driving characteristic parameters through real driving data, and perform path planning for target vehicles in lane-changing scenarios based on driving characteristic parameters. This effectively overcomes the problems of driving data distortion and subjective evaluation, and improves the scientificity and rationality of vehicle path planning in lane-changing scenarios.

[0103] Example 3

[0104] Figure 3 This is a schematic diagram of a path planning device for an autonomous vehicle according to Embodiment 3 of the present invention. This device can execute the path planning method for an autonomous vehicle provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. For example... Figure 3 As shown, the device includes:

[0105] The target driving data determination module 310 is used to determine the target driving data of the target vehicle in at least two preset driving stages in the target scenario in response to the path planning command.

[0106] The driving characteristic parameter determination module 320 is used to perform a two-independent-samples t-test on the target driving data based on the reference driving data in the target scenario, and determine the driving characteristic parameters of the target vehicle based on the sample test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters are used to reflect the driving behavior characteristics of the target object in the target scenario;

[0107] The target vehicle path planning module 330 is used to determine the environmental potential field of the target scene based on the driving characteristic parameters, and to perform path planning for the target vehicle based on the environmental potential field.

[0108] Optionally, the target driving data determination module 310 is used for:

[0109] Acquire the first driving data of the target vehicle in the target scene, and perform Kalman filtering on the first driving data to obtain the second driving data;

[0110] The second driving data is subjected to fuzzy C-means clustering based on time constraints to obtain target driving data of the target vehicle in at least two preset driving stages in the target scenario.

[0111] Optionally, the target driving data determination module 310 is further configured to:

[0112] Before performing Kalman filtering on the first driving data to obtain the second driving data, the first driving data is time-synchronized.

[0113] Optionally, the driving characteristic parameter determination module 320 is used for:

[0114] Based on the reference driving data and the target driving data, a two-independent-samples t-test is performed on the target driving parameters to obtain the target test parameters of the target driving parameters; wherein, the target test parameters are determined based on the proportion of insignificant T-values ​​of the target driving parameters;

[0115] Based on the ascending order of the target inspection parameters, the target driving parameters corresponding to the first preset number of target inspection parameters are determined as the driving characteristic parameters of the target vehicle.

[0116] Optionally, the target scenario is a following scenario; the preset driving stages include the approaching stage, the following stage, and the separation stage; the driving characteristic parameters include the headway and longitudinal acceleration.

[0117] Accordingly, the target vehicle route planning module 330 is used for:

[0118] The target potential field coefficient is determined based on the longitudinal acceleration during the approach phase to the vehicle in front, and the target potential field of the following scenario is determined based on the target potential field coefficient; wherein, the target potential field is used to characterize the driving direction of the target vehicle;

[0119] The longitudinal stable safety distance of the target vehicle is determined based on the headway during the following driving phase, and the longitudinal attenuation coefficient is determined based on the longitudinal stable safety distance and the target potential field.

[0120] The longitudinal potential field of the following scenario is determined based on the longitudinal attenuation coefficient and the headway during the separation phase from the preceding vehicle; wherein the longitudinal potential field is used to reflect the longitudinal safety distance of the target vehicle.

[0121] Optionally, the target scenario is a lane-changing scenario; the preset driving phase includes a longitudinal driving phase and a lateral driving phase, the longitudinal driving phase includes a phase of approaching the vehicle in front, a phase of following the vehicle, and a phase of separating from the vehicle in front, the lateral driving phase includes a phase of preparing to change lanes, a phase of executing a lane change, and a phase of ending the lane change; the driving characteristic parameters include the vehicle headway, longitudinal acceleration, and yaw rate acceleration.

[0122] Accordingly, the target vehicle route planning module 330 is used for:

[0123] The target potential field coefficient is determined based on the longitudinal acceleration during the approach phase to the vehicle in front, and the target potential field of the lane-changing scenario is determined based on the target potential field coefficient; wherein, the target potential field is used to characterize the driving direction of the target vehicle;

[0124] The longitudinal stable safety distance of the target vehicle is determined based on the headway during the following driving phase, and the longitudinal attenuation coefficient is determined based on the longitudinal stable safety distance and the target potential field.

[0125] The longitudinal potential field of the lane-changing scenario is determined based on the longitudinal attenuation coefficient and the headway during the separation phase from the preceding vehicle; wherein the longitudinal potential field is used to reflect the longitudinal safety distance of the target vehicle.

[0126] The lateral attenuation coefficient is determined based on the yaw acceleration during the lane-changing phase, and the lateral potential field of the lane-changing scenario is determined based on the lateral attenuation coefficient; wherein, the lateral potential field is used to reflect the lateral safety distance of the target vehicle.

[0127] Optionally, the target vehicle route planning module 330 is further configured to:

[0128] The first velocity information of the target vehicle in the vehicle coordinate system is determined based on the environmental potential field.

[0129] Based on the offset angle of the vehicle coordinate system and the first speed information, the second speed information of the target vehicle in the reference coordinate system is determined;

[0130] The target vehicle's target movement distance in the reference coordinate system is determined based on the second speed information, and path planning for the target vehicle is performed based on the target movement distance.

[0131] The path planning device for an autonomous vehicle provided in this embodiment of the invention can execute the path planning method for an autonomous vehicle provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0132] Example 4

[0133] Figure 4A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0134] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0135] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0136] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as path planning methods for autonomous vehicles.

[0137] In some embodiments, the path planning method for an autonomous vehicle may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the path planning method for an autonomous vehicle described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the path planning method for an autonomous vehicle by any other suitable means (e.g., by means of firmware).

[0138] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0139] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0140] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0141] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0142] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0143] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0144] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0145] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A path planning method for an autonomous vehicle, characterized in that, The method includes: In response to path planning instructions, determine target driving data for the target vehicle in at least two preset driving stages in the target scenario; Based on reference driving data in the target scenario, a two-independent-samples t-test is performed on the target driving data, and the driving characteristic parameters of the target vehicle are determined based on the sample test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters are used to reflect the driving behavior characteristics of the target object in the target scenario; The environmental potential field of the target scene is determined based on the driving characteristic parameters, and the target vehicle is path planned based on the environmental potential field. Specifically, based on reference driving data in the target scenario, a two-independent-samples t-test is performed on the target driving data, and the driving characteristic parameters of the target vehicle are determined based on the sample test results, including: Based on the reference driving data and the target driving data, a two-independent-samples t-test is performed on the target driving parameters to obtain the target test parameters of the target driving parameters; wherein, the target test parameters are determined based on the proportion of insignificant T-values ​​of the target driving parameters; Based on the ascending order of the target inspection parameters, the target driving parameters corresponding to the first preset number of target inspection parameters are determined as the driving characteristic parameters of the target vehicle.

2. The method according to claim 1, characterized in that, Determine target driving data for the target vehicle in at least two preset driving phases within the target scenario, including: First driving data of the target vehicle in the target scene is obtained, and second driving data is obtained by performing Kalman filtering on the first driving data. The second driving data is subjected to fuzzy C-means clustering based on time constraints to obtain target driving data of the target vehicle in at least two preset driving stages in the target scenario.

3. The method according to claim 2, characterized in that, Before performing Kalman filtering on the first driving data to obtain the second driving data, the method further includes: The first driving data is processed for time synchronization.

4. The method according to claim 1, characterized in that, The target scenario is a car-following scenario; the preset driving stages include the approaching stage, the car-following stage, and the separation stage from the car in front; the driving characteristic parameters include the headway and longitudinal acceleration. Accordingly, determining the environmental potential field of the target scene based on the driving characteristic parameters includes: The target potential field coefficient is determined based on the longitudinal acceleration during the approach phase to the vehicle in front, and the target potential field of the following scenario is determined based on the target potential field coefficient; wherein, the target potential field is used to characterize the driving direction of the target vehicle; The longitudinal stable safety distance of the target vehicle is determined based on the headway during the following driving phase, and the longitudinal attenuation coefficient is determined based on the longitudinal stable safety distance and the target potential field. The longitudinal potential field of the following scenario is determined based on the longitudinal attenuation coefficient and the headway during the separation phase from the preceding vehicle; wherein the longitudinal potential field is used to reflect the longitudinal safety distance of the target vehicle.

5. The method according to claim 1, characterized in that, The target scenario is a lane-changing scenario; the preset driving stages include a longitudinal driving stage and a lateral driving stage. The longitudinal driving stage includes a stage of approaching the vehicle in front, a stage of following the vehicle, and a stage of separating from the vehicle in front. The lateral driving stage includes a stage of preparing to change lanes, a stage of executing a lane change, and a stage of ending the lane change. The driving characteristic parameters include the vehicle headway, longitudinal acceleration, and yaw rate acceleration. Accordingly, determining the environmental potential field of the target scene based on the driving characteristic parameters includes: The target potential field coefficient is determined based on the longitudinal acceleration during the approach phase to the vehicle in front, and the target potential field of the lane-changing scenario is determined based on the target potential field coefficient; wherein, the target potential field is used to characterize the driving direction of the target vehicle; The longitudinal stable safety distance of the target vehicle is determined based on the headway during the following driving phase, and the longitudinal attenuation coefficient is determined based on the longitudinal stable safety distance and the target potential field. The longitudinal potential field of the lane-changing scenario is determined based on the longitudinal attenuation coefficient and the headway during the separation phase from the preceding vehicle; wherein the longitudinal potential field is used to reflect the longitudinal safety distance of the target vehicle. The lateral attenuation coefficient is determined based on the yaw acceleration during the lane-changing phase, and the lateral potential field of the lane-changing scenario is determined based on the lateral attenuation coefficient; wherein, the lateral potential field is used to reflect the lateral safety distance of the target vehicle.

6. The method according to claim 1, characterized in that, Path planning for the target vehicle based on the environmental potential field includes: The first velocity information of the target vehicle in the vehicle coordinate system is determined based on the environmental potential field. Based on the offset angle of the vehicle coordinate system and the first speed information, the second speed information of the target vehicle in the reference coordinate system is determined; The target vehicle's target movement distance in the reference coordinate system is determined based on the second speed information, and path planning for the target vehicle is performed based on the target movement distance.

7. A path planning device for an autonomous vehicle, characterized in that, The device includes: The target driving data determination module is used to determine the target driving data of the target vehicle in at least two preset driving stages in the target scenario in response to the path planning command. The driving characteristic parameter determination module is used to perform a two-independent-samples t-test on the target driving data based on reference driving data in the target scenario, and determine the driving characteristic parameters of the target vehicle based on the sample test results; wherein, the target vehicle is adapted to the target object, and the driving characteristic parameters are used to reflect the driving behavior characteristics of the target object in the target scenario; The target vehicle path planning module is used to determine the environmental potential field of the target scene based on the driving characteristic parameters, and to perform path planning for the target vehicle based on the environmental potential field. The driving characteristic parameter determination module is specifically used for: Based on the reference driving data and the target driving data, a two-independent-samples t-test is performed on the target driving parameters to obtain the target test parameters of the target driving parameters; wherein, the target test parameters are determined based on the proportion of insignificant T-values ​​of the target driving parameters; Based on the ascending order of the target inspection parameters, the target driving parameters corresponding to the first preset number of target inspection parameters are determined as the driving characteristic parameters of the target vehicle.

8. A path planning electronic device for an autonomous vehicle, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the path planning method for the autonomous vehicle according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the path planning method for an autonomous vehicle according to any one of claims 1-6.

Images