A path smoothing method, device, electronic equipment and storage medium

Abstract

The application discloses a path smoothing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a current vehicle preview distance, a global desired path, and a corresponding relationship between a turning radius of the current vehicle and a front wheel deflection angle; determining a current turning radius of the current vehicle according to a current position of the current vehicle, the preview distance and the global desired path; calculating a target front wheel deflection angle of the current vehicle according to the current turning radius and the corresponding relationship; extending a target direction corresponding to the target front wheel deflection angle by a preset step length to obtain a target position, and planning the target position into a target track; updating the target position to the current position, and returning to perform the operation of determining the current turning radius until a new target position is obtained and the new target position is planned into the target track. The technical scheme can smooth the drivable track of the vehicle, so that the user has good driving comfort when driving the vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicles, and in particular to a path smoothing method and device, an electronic device, and a storage medium. BACKGROUND

[0002] With the promotion and popularization of different levels of assisted driving functions on today's vehicles, more and more vehicles have assisted driving capabilities, thereby helping users to perform part of the driving work such as following a vehicle, changing lanes, and parking.

[0003] To realize the functions of automatic merging into a main road, automatic getting on and off a ramp, automatic merging or road branching, the global desired path needs to be used as a reference line, and the reference line needs to be tracked and executed. However, the map reference line often does not satisfy the continuity of curvature, and tracking and executing such a path can easily cause oscillation of the vehicle control system and easily cause accidents and safety risks. Therefore, how to make the path of the vehicle smoother has become one of the focuses of researchers in the related field. SUMMARY

[0004] The present application provides a path smoothing method, device, electronic device, and storage medium to improve the smoothness of path planning.

[0005] According to an aspect of the present application, a path smoothing method is provided, the method comprising:

[0006] obtaining a preview distance of a current vehicle, a global desired path, and a corresponding relationship between a turning radius of the current vehicle and a front wheel deflection angle of the current vehicle;

[0007] determining a current turning radius of the current vehicle according to a current position of the current vehicle, the preview distance, and the global desired path;

[0008] calculating a target front wheel deflection angle of the current vehicle according to the current turning radius and the corresponding relationship;

[0009] extending a target direction corresponding to the target front wheel deflection angle by a preset step length to obtain a target position, and planning the target position into a target trajectory;

[0010] updating the target position to the current position, and returning to perform the operation of determining the current turning radius of the current vehicle according to the current position of the current vehicle, the preview distance, and the global desired path, until a new target position is obtained and the new target position is planned into the target trajectory.

[0011] According to another aspect of the present application, a path smoothing device is provided, the device comprising:

[0012] The vehicle information acquisition module is configured to acquire a preview distance of the current vehicle, a global desired path, and a corresponding relationship between a turning radius and a front wheel deflection angle of the current vehicle.

[0013] The turning radius determination module is configured to determine a current turning radius of the current vehicle according to a current position of the current vehicle, the preview distance, and the global desired path.

[0014] The front wheel deflection angle determination module is configured to calculate a target front wheel deflection angle of the current vehicle according to the current turning radius and the corresponding relationship.

[0015] The target trajectory planning module is configured to extend a preset step length to a target direction corresponding to the target front wheel deflection angle to obtain a target position, and plan the target position into a target trajectory.

[0016] The path smoothing processing module is configured to update the target position to the current position, and return to perform the operation of determining the current turning radius of the current vehicle according to the current position of the current vehicle, the preview distance, and the global desired path, until a new target position is obtained and the new target position is planned into the target trajectory.

[0017] According to another aspect of the present application, an electronic device is provided, which comprises:

[0018] at least one processor; and

[0019] a memory connected to the at least one processor in communication; wherein

[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the path smoothing method according to any one of the embodiments of the present application.

[0021] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to perform the path smoothing method according to any one of the embodiments of the present application when executed by the processor.

[0022] According to another aspect of the present application, a computer program product is provided, which comprises a computer program for implementing the path smoothing method according to any one of the embodiments of the present application when executed by a processor.

[0023] In the technical solution of this application embodiment, the correspondence between the turning radius and the front wheel deflection angle is obtained, providing an accurate calculation basis for the subsequent calculation of the front wheel deflection angle; then, the current turning radius of the vehicle is obtained according to the pre-aiming distance and the global expected path, and the target front wheel deflection angle of the current vehicle is obtained by combining the correspondence, thereby determining the steering direction of the vehicle when planning a smooth path; planning the target trajectory based on the target front wheel deflection angle and the preset step size can save the current vehicle from calling third-party algorithm libraries, saving a lot of computing resources and improving computing efficiency, thereby helping the vehicle to determine a smooth path more quickly, successfully smoothing out the drivable trajectory of the vehicle, avoiding path abrupt changes and oscillations, and providing users with good driving comfort when driving the vehicle.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1A This is a flowchart of a path smoothing method provided according to Embodiment 1 of this application;

[0027] Figure 1B This is a schematic diagram of a vehicle kinematics modeling according to Embodiment 1 of this application;

[0028] Figure 1C This is a schematic diagram of another vehicle kinematics modeling provided according to Embodiment 1 of this application;

[0029] Figure 1D This is a schematic diagram of the calculation of the front wheel deflection angle according to Embodiment 1 of this application;

[0030] Figure 1E This is a schematic diagram of the path smoothing process provided according to Embodiment 1 of this application;

[0031] Figure 1F This is a schematic diagram comparing the path smoothing process before and after according to Embodiment 1 of this application;

[0032] Figure 2 This is a schematic diagram of a path smoothing device according to Embodiment 2 of this application;

[0033] Figure 3 FIG. 1 is a structural schematic diagram of an electronic device implementing a path smoothing method according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0035] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, method, product or device.

[0036] Embodiment One

[0037] Figure 1A A flowchart of a path smoothing method is provided for the first embodiment of the present application. The present embodiment can be applied to the case of path smoothing for intelligent vehicles. The method can be performed by a path smoothing device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device. As shown in FIG. 1, the method comprises: Figure 1A

[0038] S110, obtaining a current vehicle preview distance, a global desired path, and a corresponding relationship between a turning radius and a front wheel deflection angle of the current vehicle.

[0039] ​The current vehicle can be any vehicle that is currently planning a path and driving by automatic driving / assisted driving function. The front wheel deflection angle is the angle of the front wheel of the current vehicle when turning (and changing direction, U-turn, etc.) deviates from the angle of straight driving. It can be understood that, in the case of non-intelligent driving / assisted driving, the driver holds the steering wheel to change direction, and the steering wheel determines the size of the front wheel deflection angle. In the case of intelligent driving / assisted driving, the size of the front wheel deflection angle can be actively determined by the control system of the current vehicle. The turning radius has a theoretical relationship with the linear speed and the angular speed, and the heading of the vehicle also has a theoretical relationship with the front wheel deflection angle. Obtaining the corresponding relationship between the turning radius and the front wheel deflection angle helps the vehicle to plan the path during turning. The preview distance can be the driving observation distance that the driver's gaze direction extends when driving the current vehicle. The preview distance can not only reflect the desired direction of the vehicle driving (i.e., the direction that the driver hopes the vehicle to travel), but also reflect the approximate position to which the vehicle will travel in the future, and to a certain extent, serve as the reaction distance before an accident occurs. The preview distance can be set by the driver when using the automatic driving / assisted driving function of the vehicle, and thus can be directly obtained by the current vehicle. The specific value of the preview distance can be set by a relevant technical person according to experiments, or set by the driver according to experience, and the embodiments of the present application do not limit this.

[0040] In an optional embodiment, the preview distance is determined in the following manner: a preset preview time is obtained from an adaptive cruise control system of the current vehicle; and the preview distance is calculated according to the preview time and a current vehicle speed of the current vehicle.

[0041] The adaptive cruise control system (ACC) is a new system that adds a control function of maintaining a reasonable distance from a front vehicle to a system that controls cruising at a set speed. The ACC can preset a preview time gear, and different gears represent different degrees of preview. Generally, three gears can be set. The current vehicle can obtain the preview time gear from the ACC, multiply the preview time corresponding to the gear by the real-time vehicle speed of the current vehicle, and calculate the result of the preview distance. Of course, the preview time of different gears can also be set by a relevant technical person according to experiments, or set by the driver according to experience, and the embodiments of the present application do not limit this.

[0042] In addition, the global desired path can be a planned route obtained by the current vehicle from a map software, for example, a global path planned in the map by the navigation function after the destination has been confirmed.

[0043] In one optional implementation, obtaining the correspondence between the turning radius and the front wheel deflection angle of the current vehicle in S110 may include: obtaining the kinematic model of the current vehicle; obtaining a first calculation relationship between the front wheel deflection angle and the yaw rate, and a second calculation relationship between the yaw rate and the turning radius based on the kinematic model; and determining the correspondence between the turning radius and the front wheel deflection angle based on the first calculation relationship and the second calculation relationship.

[0044] The kinematic model can be a model built based on the inherent characteristics and physical properties of the current vehicle, used to represent the kinematic constraints of the current vehicle. For example, such as... Figure 1B and Figure 1C As shown, Oxy is the global coordinate system, (x f ,y f ) represents the center position of the vehicle's front axle, v f Let (x,y) be the front axle speed, (x,y) be the center position of the rear axle, v be the rear axle speed, l be the wheelbase, δ be the front wheel deflection angle, and θ be the vehicle heading angle.

[0045] When turning, the speed at the center of the rear axle is:

[0046]

[0047] Since the front and rear wheels have a velocity of 0 on the normal line, the following constraints can be obtained:

[0048]

[0049]

[0050] Based on equations (1) and (3), we obtain:

[0051]

[0052] Furthermore, there is a geometric relationship between the front and rear wheels:

[0053]

[0054] Differentiate equation (5):

[0055]

[0056] Substituting equations (4) and (6) into equation (2), we get:

[0057]

[0058] The kinematic model is obtained from (4) and (7):

[0059]

[0060] Including the rate of change of the front wheel deflection angle in the model, we obtain the state equation based on kinematics:

[0061]

[0062] In other words, by inputting linear velocity and angular velocity as control variables into the kinematic model, the continuous changes in the vehicle's position and heading can be obtained. Since the current vehicle's kinematic model is obtained, this model constrains the relationship between the vehicle's linear velocity, angular velocity, position, and heading during its motion. The turning radius has a theoretical relationship with both linear velocity and angular velocity, and the vehicle's heading also has a theoretical relationship with the front wheel deflection angle. Therefore, based on the current vehicle's kinematic model, the correspondence between the turning radius and the front wheel deflection angle can be determined.

[0063] Yaw rate is also one of the inherent properties of a vehicle. Continuing the previous example, the front wheel deflection angle δ and yaw rate... The first calculation relationship between them can be expressed by the above formula (4):

[0064]

[0065] Based on the theorem that linear velocity equals radius multiplied by angular velocity, the turning radius and yaw rate... The second computational relationship between them can be:

[0066]

[0067] Based on the above formulas (4) and (8), the relationship between the turning radius and the front wheel deflection angle can be derived:

[0068] δ=arctan(l / R)(9)

[0069] In the above embodiments, based on the kinematic model of the current vehicle, the relationship between the front wheel deflection angle and the yaw rate, and the relationship between the yaw rate and the turning radius are obtained respectively. Thus, the relationship between the turning radius and the front wheel deflection angle is calculated and derived, which provides a basis for the subsequent calculation of the turning radius of the current vehicle during the path smoothing process. This helps to improve the calculation efficiency of the current vehicle, and in turn, helps to improve the efficiency of the current vehicle in processing the path smoothing process.

[0070] S120. Determine the current turning radius of the current vehicle based on its current position, aiming distance, and global desired path.

[0071] The current position can be the position of the current vehicle. Since the global expected path is only based on the navigation map route, not the actual driving trajectory, the current position is not necessarily on the global expected path. Since theoretically the driver wants the driving path of the current vehicle to not deviate too far from the global expected path, the global expected path can be used as a reference for path planning and smoothing in the path smoothing process. The presence of the preview distance can help the current vehicle to converge to the global expected path based on the current position, that is, the preview direction corresponding to the preview distance can always converge to the global expected path. For example, a target point that meets the preview distance can be found on the global expected path from the current position as a reference point, and the turning radius required in this process, that is, the current turning radius, can be calculated when planning a path from the reference point to the target point. Of course, a machine learning model can also be pre-trained, the input of the model being the current position of the current vehicle, the preview distance, and the global expected path, and the output of the model being the current turning radius of the current vehicle in this path planning process. Of course, the machine learning model can be pre-trained by a person skilled in the art, for example, using a convolutional neural network, and the present application does not limit this.

[0072] In an optional embodiment, the determination of the current turning radius of the current vehicle according to the current position of the current vehicle, the preview distance, and the global expected path in S120 can include: determining a current expected position in the global expected path according to the current position and the preview distance; intercepting the current expected position in the global expected path from the current position as a starting point and the preview distance as a length; and determining the current turning radius of the current vehicle according to the current position, the current expected position, and the preview distance.

[0073] The current expected position can be a position that is expected to return to the global expected path (but in fact it may not necessarily return to the global expected path at this position, and the current expected position can be used as a target point for path planning and smoothing).

[0074] It should be noted that in path planning, the turning radius is fixed during the movement of the current vehicle from the current position to the current expected position, and the preview distance and the turning radius form a geometric relationship, so the current turning radius can be calculated based on the preview distance.

[0075] In a further optional embodiment, the determination of the current turning radius of the current vehicle according to the current position, the current expected position, and the preview distance can include: calculating a deviation angle between the heading direction of the current vehicle and the direction corresponding to the current expected position according to the current position and the current expected position; and calculating the current turning radius according to the deviation angle and the preview distance.

[0076] Here, the current vehicle's heading can be the direction the vehicle is currently traveling in. It's understood that there's a deviation angle between the direction formed by the current desired position and the current position, and the current vehicle's heading. Since the turning radius is fixed, a circular arc trajectory can be planned from the current position to the current desired position. The current vehicle's heading is precisely the tangent direction of this circular arc trajectory, and the line connecting the current position and the desired position is exactly the chord of the circular arc trajectory. Therefore, the current turning radius can be calculated geometrically based on this deviation angle and the pre-aiming distance.

[0077] Specifically, such as Figure 1D As shown, point S(x) v ,y v ) represents the current position of the vehicle (e.g., the center position of the rear axle), and L represents the aiming distance. Based on the aiming distance, the current desired position G(x) can be intercepted on the global desired path. G ,y G ).Depend on Figure 1D As can be seen, the two current turning radii R and the target aiming distance L form an isosceles triangle, and the deviation angle between the heading and the target position is:

[0078]

[0079] Since L is the chord corresponding to ∠GOS, the central angle corresponding to the desired arc path shown in Figure D1 is 2α.

[0080] It exists in triangle GOS:

[0081]

[0082] From equations (10) and (11), the current turning radius R can be derived as follows:

[0083]

[0084] In the above embodiments, based on the pre-aiming distance, this application provides a method for calculating the current turning radius of a vehicle. This method can obtain the current desired position on the globally desired path using only the pre-aiming distance, and perform geometric calculations based on this information, thereby efficiently obtaining the current turning radius and providing a basis for the vehicle's turning and direction changes. It also reduces reliance on third-party algorithm libraries to some extent, lowers the computational power required, and can be directly run on the vehicle's SOC (System on Chips) and MCU (Microcontroller Unit), thus improving computational efficiency to a certain extent.

[0085] S130, calculating the target front wheel deflection angle of the current vehicle according to the current turning radius and the corresponding relationship.

[0086] On the basis of the corresponding relationship between the turning radius and the front wheel deflection angle of the current vehicle in S110 and the current turning radius determined in S120, the target front wheel deflection angle required for the current vehicle to smoothly approach the global desired path is calculated.

[0087] Specifically, continuing the previous example, on the basis of the aforementioned formula (9) and formula (12), the target front wheel deflection angle δ can be obtained as:

[0088]

[0089] S140, extending a preset step length from the target direction corresponding to the target front wheel deflection angle to obtain a target position, and planning the target position into a target trajectory.

[0090] The preset step length is the forward step length in the path planning process, which can be set by relevant technical personnel according to experiments or actual situations, for example, it can be 1 meter or 2 meters, and the present application does not limit this. The target trajectory can be a relatively smooth trajectory planned to approach the global desired path, and is also the trajectory that the current vehicle needs to execute.

[0091] It can be understood that the target front wheel deflection angle represents the degree of the current vehicle about to turn, that is, the future yaw direction, and the preset step length represents each step in the process of planning the target trajectory. Therefore, advancing in the direction of the target front wheel deflection angle with the preset step length, the trajectory obtained can be planned into the target trajectory.

[0092] The target direction corresponding to the target front wheel deflection angle can be the driving direction that the current vehicle is about to change, and a preset step length is planned in this direction to obtain a target position, which is equivalent to that in the process of path planning, the current vehicle has taken a step to the target position in the target direction of the target front wheel deflection angle from the current position, and the target position is planned into the target trajectory.

[0093] The above embodiment provides a feasible path exploration scheme for the present application. Based on the target front wheel deflection angle calculated in the foregoing embodiment, the path is explored and planned in the target direction corresponding to the target front wheel deflection angle at the current position of the current vehicle, and the newly stepped step and the obtained target position point are planned into the target trajectory, which not only provides trajectory planning for the current vehicle to approach the global desired path, but also simultaneously completes the smoothing processing of the global desired path, so that the current vehicle maintains smooth steering during driving according to the navigation route, thereby improving the stability and safety of the vehicle.

[0094] S150, updating the target position as the current position, and returning to perform the operation of determining the current turning radius of the current vehicle according to the current position, the preview distance and the global desired path until a new target position is obtained, and the new target position is planned into the target trajectory.

[0095] The target position determined in the foregoing step can be used as the starting point of the next path exploration, that is, the target position is updated as the current position of the next time, and the foregoing steps S120-S140 are re-executed with the position as the starting point of path planning to achieve cyclic execution, and the target trajectory is obtained by accumulating the step length until the target trajectory meets the preset trajectory length, and the cycle is exited, and the current vehicle is controlled to execute the target trajectory. Through the iterative process of the cycle, the step length is accumulated, thereby planning a smoother trajectory for the current vehicle which is similar to the global desired path, which helps to improve the stability of the vehicle driving.

[0096] In an optional embodiment, the target position is updated as the current position in S150; correspondingly, after the new target position is planned into the target trajectory, the method further comprises: in response to the target trajectory meeting the trajectory length, determining that the target trajectory is the current smooth path, and controlling the current vehicle to execute the target trajectory.

[0097] The preset trajectory length can be a judgment basis for whether the target trajectory can be executed. It should be noted that since the current vehicle has a certain speed during driving, if the planned smooth trajectory is too short, it is not easy to be directly executed by the current vehicle which already has a speed; therefore, a relatively long smooth path needs to be planned to provide the current vehicle with an executable path. The trajectory length can be set by a relevant technical person according to experiments or actual situations, for example, it can be 20 meters or 30 meters, and the present application does not limit this.

[0098] Therefore, it's understandable that when the target trajectory doesn't meet the preset trajectory length requirement, the iteration of step size continues. To avoid oscillations in the vehicle control system, the current vehicle cannot be directly controlled to execute a target trajectory that doesn't meet the length requirement. Therefore, the target position determined in the previous steps can be used as the starting point for the next path exploration, updating the target position to the next current position. This position is then used as the starting point for path planning, and steps S130-S160 are repeated to achieve cyclic execution. The target trajectory is obtained by accumulating step size until it meets the preset trajectory length. At this point, the loop exits, and the current vehicle is controlled to execute the target trajectory. Through this iterative process, the step size accumulates, thus planning a trajectory that approximates the globally desired path but is smoother, improving vehicle stability. When the length of the planned target trajectory exceeds the preset trajectory length, the current vehicle can be controlled to execute that target trajectory, allowing it to complete the navigation route corresponding to the globally desired path with a smoother path. A smooth path ensures vehicle safety and stability.

[0099] For example, such as Figure 1E As shown (where the solid line represents the global desired path and the dashed line represents the smooth path), assume the current position of the vehicle is P. n After the path exploration described above, the target position P is obtained by extending the target direction corresponding to the target front wheel deflection angle by a preset step length. n+1 The step size of this segment, along with P n+1 All are planned into the target trajectory. At this point, it is determined whether the target trajectory matches the preset trajectory length. If it does, the vehicle can be controlled to execute the target trajectory; otherwise, P... n+1 Iterate from a new starting point, reusing the methods described in the aforementioned implementations, with P n+1 Using a base point, a desired position is determined in the global desired path using the pre-aiming distance. Based on this, the turning radius of the current vehicle is calculated, and the front wheel deflection angle is then calculated. The path is then extended by a preset step size according to the direction of the current front wheel deflection angle to perform path smoothing exploration until the target trajectory matches the preset trajectory length. It is important to note that within each loop, a new desired position needs to be determined on the global desired path based on the current position. The technical solution of this application embodiment can effectively smooth the global desired path, such as... Figure 1F As shown, the global path provided by the navigation software during the journey from A to B to C and then to D (as shown in the image) Figure 1F The solid lines in the text are rather harsh. Through the method provided in this application embodiment, the vehicle can travel along a smooth path. Figure 1F The dotted lines in the diagram ensure the safety and stability of the vehicle.

[0100] In the technical solutions of the embodiments of the present application, the corresponding relationship between the turning radius and the front wheel deflection angle is obtained, which provides an accurate calculation basis for subsequent calculation of the front wheel deflection angle; then the current turning radius of the vehicle is obtained according to the preview distance and the global desired path, and the target front wheel deflection angle of the current vehicle is obtained in combination with the corresponding relationship, so as to determine how the steering direction of the vehicle is planned when the smooth path is planned; the target trajectory is planned based on the target front wheel deflection angle and the preset step length, which can make the current vehicle free from calling a third-party algorithm library, save a large amount of computing resources, and improve the calculation efficiency, thereby helping the vehicle to determine the smooth path faster, successfully smooth the drivable trajectory of the vehicle, avoid the situation of path mutation and oscillation, and make the user have good driving comfort when driving the vehicle.

[0101] Embodiment Two

[0102] Figure 2 A structural schematic diagram of a path smoothing device provided in the second embodiment of the present application is shown in FIG. 2. As shown in the figure, the device 200 includes: Figure 2

[0103] A vehicle information acquisition module 210 is configured to acquire the preview distance of the current vehicle, the global desired path, and the corresponding relationship between the turning radius and the front wheel deflection angle of the current vehicle.

[0104] A turning radius determination module 220 is configured to determine the current turning radius of the current vehicle according to the current position, the preview distance, and the global desired path of the current vehicle.

[0105] A front wheel deflection angle determination module 230 is configured to calculate the target front wheel deflection angle of the current vehicle according to the current turning radius and the corresponding relationship.

[0106] A target trajectory planning module 240 is configured to extend a preset step length to the target direction corresponding to the target front wheel deflection angle to obtain a target position, and plan the target position into a target trajectory.

[0107] A path smoothing processing module 250 is configured to update the target position to the current position, and return to perform the operation of determining the current turning radius of the current vehicle according to the current position, the preview distance, and the global desired path of the current vehicle, until a new target position is obtained, and the new target position is planned into the target trajectory.

[0108] ​In the technical solution of the embodiment of the application, the corresponding relationship between the turning radius and the front wheel deflection angle is obtained, which provides an accurate calculation basis for subsequent calculation of the front wheel deflection angle; then the current turning radius of the vehicle is obtained according to the preview distance and the global desired path, and the target front wheel deflection angle of the current vehicle is obtained in combination with the corresponding relationship, so that how the steering direction of the vehicle is determined when the smooth path is planned; the target trajectory is planned based on the target front wheel deflection angle and the preset step length, which can enable the current vehicle to avoid calling a third-party algorithm library, save a large amount of computing resources, and improve the calculation efficiency, thereby helping the vehicle to determine the smooth path faster, successfully smooth the drivable trajectory of the vehicle, avoid the situation of path mutation and oscillation, and enable the user to have good driving comfort when driving the vehicle.

[0109] In an optional implementation, the target trajectory planning module 240 can be specifically configured to:

[0110] In response to the target trajectory not satisfying the preset trajectory length, updating the target position to the current position;

[0111] Correspondingly, the target trajectory planning module 240 can also be specifically configured to:

[0112] In response to the target trajectory satisfying the trajectory length, determining the target trajectory as the current smooth path, and controlling the current vehicle to execute the target trajectory.

[0113] In an optional implementation, the turning radius determination module 220 can include:

[0114] The desired position determination unit is configured to determine a current desired position in the global desired path according to the current position and the preview distance;

[0115] The radius determination unit is configured to determine the current turning radius of the current vehicle according to the current position, the current desired position and the preview distance.

[0116] In an optional implementation, the radius determination unit can include:

[0117] The deflection angle determination subunit is configured to calculate a deflection angle between the heading of the current vehicle and the direction corresponding to the current desired position according to the current position and the current desired position;

[0118] The radius calculation subunit is configured to calculate the current turning radius according to the deflection angle and the preview distance.

[0119] In an optional implementation, the corresponding relationship determination module 210 can include:

[0120] The kinematic model acquisition unit is configured to acquire a kinematic model of the current vehicle;

[0121] Two calculation relationship determining units are configured to obtain a first calculation relationship between the front wheel deflection angle and the yaw rate and a second calculation relationship between the yaw rate and the turning radius according to the kinematic model;

[0122] A radius and deflection angle corresponding relationship determining unit is configured to determine a corresponding relationship between the turning radius and the front wheel deflection angle according to the first calculation relationship and the second calculation relationship.

[0123] In an optional implementation, the device 200 further comprises a pre-look distance determining module, which can comprise:

[0124] A pre-look time obtaining unit is configured to obtain a pre-set pre-look time from an adaptive cruise control system of the current vehicle;

[0125] A pre-look distance calculating unit is configured to calculate the pre-look distance according to the pre-look time and a current speed of the current vehicle.

[0126] The path smoothing device provided by the embodiments of the present application can execute the path smoothing method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of executing each path smoothing method.

[0127] Embodiment three

[0128] Figure 3 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headgear, eyewear, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0129] Their functions are merely examples and are not intended to limit implementations of the present application described and / or claimed in this document.

[0130] As Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0132] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the 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 appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the path smoothing method.

[0133] Embodiments of the present application also provide a vehicle, which can be provided with the electronic device described above, for implementing the path smoothing method provided by any embodiment of the present application.

[0134] In some embodiments, the path smoothing method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the path smoothing method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the path smoothing method by any other appropriate means, such as by means of firmware.

[0135] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0136] Computer programs used to implement the processes of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0137] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0138] To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; 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 acoustic, speech, or tactile input.

[0139] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0140] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0141] The embodiments of the present application further disclose a computer program product, which comprises a computer program, and the computer program, when executed by a processor, implements the path smoothing method provided in any of the embodiments of the present application. The program product and the path smoothing method disclosed in the embodiments of the present application belong to the same inventive concept, and thus will not be repeated here.

[0142] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present application. For example, the steps recited in the present application can be executed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, and the present application is not limited herein.

[0143] The foregoing detailed description has set forth various embodiments of the devices and / or processes via the use of specific terminology. However, embodiments thereof can be practiced with the exact description not being set forth but with the same essence; the principles set forth herein can be practiced to achieve the present application. The scope of protection is not limited to the embodiments described and shown.

Claims

1. A path smoothing method characterized by, The method comprises: acquiring a preview distance of a current vehicle, a global desired path, and a corresponding relationship between a turning radius and a front wheel deflection angle of the current vehicle; determining a current turning radius of the current vehicle according to a current position of the current vehicle, the preview distance, and the global desired path; calculating a target front wheel deflection angle of the current vehicle according to the current turning radius and the corresponding relationship; extending a preset step length from the target front wheel deflection angle to obtain a target position, and planning the target position into a target trajectory; updating the target position to the current position, and returning to perform the operation of determining the current turning radius of the current vehicle according to the current position of the current vehicle, the preview distance, and the global desired path until a new target position is obtained and the new target position is planned into the target trajectory.

2. The method of claim 1, wherein, The updating of the target position to the current position comprises: updating the target position to the current position in response to the target trajectory not satisfying a preset trajectory length; Correspondingly, after the new target position is planned into the target trajectory, the method further comprises: determining the target trajectory as a current smooth path in response to the target trajectory satisfying the trajectory length, and controlling the current vehicle to perform the target trajectory.

3. The method of claim 1, wherein the determining of the current turning radius of the current vehicle according to the current position of the current vehicle, the preview distance, and the global desired path comprises: determining a current desired position in the global desired path according to the current position and the preview distance; determining the current turning radius of the current vehicle according to the current position, the current desired position, and the preview distance.

4. The method of claim 3, wherein, The determining of the current turning radius of the current vehicle according to the current position, the current desired position, and the preview distance comprises: calculating a deviation angle of a heading direction of the current vehicle and a corresponding direction of the current desired position according to the current position and the current desired position; calculating the current turning radius according to the deviation angle and the preview distance.

5. The method of claim 1, wherein, The acquiring of the corresponding relationship between the turning radius and the front wheel deflection angle of the current vehicle comprises: acquiring a kinematic model of the current vehicle; obtaining a first calculation relationship between the front wheel deflection angle and a yaw rate and a second calculation relationship between the yaw rate and the turning radius according to the kinematic model; determining the corresponding relationship between the turning radius and the front wheel deflection angle according to the first calculation relationship and the second calculation relationship.

6. The method of claim 1, wherein, The preview distance is determined in the following manner: acquiring a preset preview time from an adaptive cruise control system of the current vehicle; calculating the preview distance according to the preview time and a current speed of the current vehicle.

7. A path smoothing device characterized by comprising: The device comprises: a vehicle information acquisition module configured to acquire a preview distance of a current vehicle, a global desired path, and a corresponding relationship between a turning radius and a front wheel deflection angle of the current vehicle; a turning radius determination module, configured to determine a current turning radius of the current vehicle according to a current position of the current vehicle, the preview distance, and the global desired path; a front wheel deflection angle determination module, configured to calculate a target front wheel deflection angle of the current vehicle according to the current turning radius and the corresponding relationship; a target trajectory planning module, configured to extend a target direction corresponding to the target front wheel deflection angle by a preset step length to obtain a target position, and plan the target position into a target trajectory; a path smoothing processing module, configured to update the target position to the current position, and return to perform the operation of determining the current turning radius of the current vehicle according to the current position of the current vehicle, the preview distance, and the global desired path, until a new target position is obtained and the new target position is planned into the target trajectory.

8. The apparatus of claim 7, wherein, The target trajectory planning module can be specifically configured to: update the target position to the current position in response to the target trajectory not satisfying a preset trajectory length; Correspondingly, the target trajectory planning module can also be specifically configured to: determine the target trajectory as a current smoothing path and control the current vehicle to perform the target trajectory in response to the target trajectory satisfying the trajectory length.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the path smoothing method in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to enable the processor to perform the path smoothing method in any one of claims 1-6 when executed.

Images