A vehicle lane-changing path planning method and device, a storage medium and an electronic device

Abstract

The present application relates to a kind of vehicle lane-changing path planning method and device, storage medium, electronic equipment, comprising: obtaining the current time based on the current vehicle coordinate of Frenet coordinate system, current vehicle surrounding obstacle coordinate;Current time of current vehicle speed, current vehicle surrounding obstacle speed is obtained;Target reference line is obtained;According to the current time of current vehicle coordinate, current vehicle speed, current vehicle surrounding obstacle coordinate, current vehicle surrounding obstacle speed and the target reference line, the coordinate of multiple groups of Bezier curve control points is obtained;According to the coordinate of the multiple groups of Bezier curve control points, corresponding multiple Bezier curves are generated;The multiple Bezier curves are screened to obtain an optimal Bezier curve, and the corresponding vehicle lane-changing path is obtained according to the optimal Bezier curve.By the present application, the lane-changing path closer to actual optimal solution can be generated.

Description

TECHNICAL FIELD

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

[0002] An automatic driving system comprises a map positioning module, a perception fusion module, a decision module, a control execution module and the like. The planning module receives filtered surrounding environment information provided by the perception fusion module, current vehicle state provided by the map positioning module, and strategy instructions of the decision module and a preset planning algorithm to plan and output a best executable trajectory in the future for several meters, including a series of path points, curvatures, speeds, expected times, accelerations and the like, so as to be tracked by the control execution module. Therefore, the planning algorithm is crucial for the entire automatic driving system and is indispensable.

[0003] At present, the path planning module of most path-speed decoupling planning algorithms receives a target reference line, projects surrounding static obstacles and itself into a coordinate system, and searches for an optimal path in a free space. Such path-speed decoupling planning algorithm only considers static obstacles, and time-related factors such as dynamic obstacles, lane-changing time, and following distance at the end state of lane-changing are considered by the speed planning layer. It belongs to complete path-speed decoupling, the idea is clear, but it cannot search for a lane-changing path closer to the real optimal solution. SUMMARY

[0004] The present application aims to provide a vehicle lane-changing path planning method and device, a storage medium and an electronic device to solve the technical problem that most path planning modules at present only consider static obstacles and cannot generate a lane-changing path closer to the actual optimal solution.

[0005] To achieve the above-mentioned purpose, according to the first aspect of the present application, a vehicle lane-changing path planning method is provided, which comprises:

[0006] Obtaining the current vehicle coordinates and the surrounding obstacle coordinates based on the Frenet coordinate system;

[0007] Obtaining the current vehicle speed and the surrounding obstacle speed;

[0008] Obtaining a target reference line; the target reference line is the center line of the target lane for the vehicle to change lanes;

[0009] Obtaining the coordinates of a plurality of groups of Bezier curve control points according to the current vehicle coordinates, the current vehicle speed, the surrounding obstacle coordinates, the surrounding obstacle speed and the target reference line;

[0010] generating a plurality of Bezier curves according to the coordinates of the plurality of groups of Bezier curve control points;

[0011] screening the plurality of Bezier curves to obtain an optimal Bezier curve, and obtaining a corresponding vehicle lane-changing path according to the optimal Bezier curve.

[0012] Preferably, the coordinates of each group of Bezier curve control points include the coordinates of four control points; the four control points include a starting point, an ending point, a first intermediate point and a second intermediate point; the starting point is the current vehicle position; the ending point is the position of the vehicle merging into the target reference line; the first intermediate point is obtained by sampling within the range between the starting point and the ending point; and the second intermediate point is obtained by sampling within the range between the first intermediate point and the ending point, and the second intermediate point falls on the target reference line.

[0013] Preferably, the obtaining of the coordinates of the plurality of groups of Bezier curve control points according to the current vehicle coordinates, the vehicle speed, the coordinates of the surrounding obstacles, the speed of the surrounding obstacles and the target reference line comprises:

[0014] when the obstacle is located behind the vehicle, or the speed of the nearest obstacle in front of the vehicle is greater than or equal to the vehicle speed, determining the coordinates of an ending point according to the vehicle speed and a preset maximum lane-changing time;

[0015] when the speed of the nearest obstacle in front of the vehicle is less than the vehicle speed, obtaining the s coordinate s obstacle of the obstacle point on the nearest obstacle in front of the vehicle closest to the vehicle; uniformly sampling a plurality of lane-changing times within a preset lane-changing time interval [t min , t max ]; uniformly sampling a plurality of following distances within a preset following distance interval [d min , d max ]; and determining the coordinates of a plurality of ending points according to the s coordinate s obstacle of the obstacle point, the plurality of lane-changing times and the plurality of following distances.

[0016] Preferably, the obtaining of the coordinates of the plurality of groups of Bezier curve control points according to the current vehicle coordinates, the vehicle speed, the coordinates of the surrounding obstacles, the speed of the surrounding obstacles and the target reference line comprises:

[0017] when the intersection point of the extension line of the current direction of the vehicle and the target reference line is within a preset distance range, uniformly sampling the coordinates of a plurality of first intermediate points on the line between the starting point and the intersection point.

[0018] When the intersection of the extension line of the current heading of the vehicle head and the target reference line is out of the preset distance range or the intersection does not exist, a plurality of first intermediate point coordinates are obtained by equally and uniformly sampling the extension line of the current heading of the vehicle head within the range between the starting point and each end point.

[0019] Preferably, the obtaining of the coordinates of the plurality of sets of Bezier curve control points according to the coordinates of the host vehicle, the speed of the host vehicle, the coordinates of the obstacle, the speed of the obstacle and the target reference line comprises:

[0020] The coordinates of a plurality of second intermediate points are obtained by equally and uniformly sampling within the range between each first intermediate point and its corresponding one end point.

[0021] Preferably, the screening of the plurality of Bezier curves to obtain an optimal Bezier curve and the obtaining of the corresponding vehicle lane-changing path according to the optimal Bezier curve comprises:

[0022] The coordinates of a plurality of sampling points of each Bezier curve and its connected part of the target reference line are obtained by equally and uniformly sampling each Bezier curve and its connected part of the target reference line, and n-order curve fitting is performed according to the coordinates of the plurality of sampling points of each Bezier curve and its connected part of the target reference line to obtain an n-order curve corresponding to each Bezier curve; wherein the part of the target reference line connected by each Bezier curve refers to the part of the target reference line with an s coordinate greater than the s coordinate of the end point, and n>1.

[0023] The loss value of the n-order curve corresponding to each Bezier curve is calculated, and the Bezier curve corresponding to the n-order curve with the minimum loss value is selected as the optimal Bezier curve.

[0024] Preferably, the loss value of the n-order curve is a weighted sum of a zero-order and reference line offset loss, a first-order smoothness loss, a second-order smoothness loss, a third-order smoothness loss, an expected lane-changing time loss and an expected final state following distance loss.

[0025] The zero-order and reference line offset loss Cost0 is:

[0026] The first-order smoothness loss Cost1 is:

[0027] The second-order smoothness loss is Cost2:

[0028] The third-order smoothness loss Cost3 is:

[0029] The expected lane-changing time loss Cost t is: Costt = k · t;

[0030] the expected end state of the following distance loss Cost d Cost = k · t; d = 1 / (d + σ), σ = 1e-6;

[0031] wherein f(s) is a Bezier curve function, s0is the s coordinate of the starting point, s t is the s coordinate of the end point or the s coordinate slightly greater than the end point, k is a preset parameter value, t is the lane changing time, t ∈ [t min , t max ], d is the following distance, d ∈ [d min , d max ].

[0032] Preferably, the plurality of Bezier curves are screened to obtain an optimal Bezier curve, and a corresponding vehicle lane changing path is obtained according to the optimal Bezier curve, comprising:

[0033] obtaining the coordinates of a plurality of sampling points corresponding to the optimal Bezier curve and the partial target reference line connected thereto, converting the coordinates of the plurality of sampling points from the Frenet coordinate system to the Cartesian coordinate system to obtain the coordinates of the plurality of sampling points based on the Cartesian coordinate system, and using an m-degree polynomial curve to connect any two adjacent sampling points according to the coordinates of the plurality of sampling points based on the Cartesian coordinate system to obtain a segmented function of the vehicle lane changing path; wherein m > 1.

[0034] Preferably, the plurality of Bezier curves are screened to obtain an optimal Bezier curve, and a corresponding vehicle lane changing path is obtained according to the optimal Bezier curve, comprising:

[0035] sampling the vehicle lane changing path at a preset step length to obtain a plurality of position points, and obtaining the curvatures, the orientations of the vehicle, the lane changing times, and the following distances corresponding to the plurality of position points.

[0036] According to a second aspect of the present application, a vehicle lane changing path planning device is provided, the device comprising:

[0037] a coordinate acquisition unit configured to acquire the coordinates of the vehicle and the coordinates of the obstacles around the vehicle based on the Frenet coordinate system at the current time;

[0038] a speed acquisition unit configured to acquire the speed of the vehicle and the speed of the obstacles around the vehicle at the current time;

[0039] a reference line acquisition unit configured to acquire a target reference line; the target reference line is the center line of the target lane on which the vehicle is to travel;

[0040] The control point acquisition unit is used to acquire the coordinates of multiple sets of Bézier curve control points based on the current vehicle coordinates, vehicle speed, coordinates of obstacles around the vehicle, speed of obstacles around the vehicle, and the target reference line.

[0041] The Bézier curve generation unit is used to generate multiple corresponding Bézier curves based on the coordinates of the multiple sets of Bézier curve control points.

[0042] The path generation unit is used to filter the multiple Bézier curves to obtain an optimal Bézier curve, and to obtain the corresponding vehicle lane-changing path based on the optimal Bézier curve.

[0043] Preferably, the coordinates of each set of Bézier curve control points include the coordinates of four control points; the four control points include a start point, an end point, a first intermediate point, and a second intermediate point; the start point is the current position of the vehicle; the end point is the position where the vehicle merges into the target reference line; the first intermediate point is obtained by sampling within the range between the start point and the end point; the second intermediate point is obtained by sampling within the range between the first intermediate point and the end point, and the second intermediate point falls on the target reference line.

[0044] Preferably, the control point acquisition unit is specifically used for:

[0045] When an obstacle is located behind the vehicle, or when the speed of the nearest obstacle in front of the vehicle is greater than or equal to the speed of the vehicle, the coordinates of a destination are determined based on the vehicle's speed and the preset maximum lane-changing time.

[0046] When the speed of the nearest obstacle in front of the vehicle is less than the speed of the vehicle, obtain the s-coordinate s of the point on the nearest obstacle that is closest to the vehicle. obstacle ; within the preset lane change time interval [t min ,t max Multiple lane-changing times were sampled evenly at equal intervals within the [d] range; within the preset following distance range [d] min ,d max Multiple following distances were sampled evenly at equal intervals within the obstacle; based on the s-coordinates of the obstacle points... obstacle The multiple lane change times and the multiple following distances determine the coordinates of multiple destinations.

[0047] Preferably, the control point acquisition unit is specifically used for:

[0048] When the intersection of the extended line of the vehicle's current orientation and the target reference line is within a preset distance range, the coordinates of multiple first intermediate points are obtained by uniformly sampling at equal distances between the starting point and the intersection point.

[0049] When the intersection of the extension line of the current heading of the vehicle head and the target reference line is out of the preset distance range or the intersection does not exist, a plurality of first intermediate point coordinates are obtained by equally and uniformly sampling the extension line of the current heading of the vehicle head within the range between the starting point and each end point.

[0050] Preferably, the control point acquisition unit is specifically configured to:

[0051] A plurality of second intermediate point coordinates are obtained by equally and uniformly sampling within the range between each first intermediate point and its corresponding one end point.

[0052] Preferably, the path generation unit is specifically configured to:

[0053] The coordinates of a plurality of sampling points of each Bezier curve and the connected part of the target reference line are obtained by equally and uniformly sampling each Bezier curve and the connected part of the target reference line, and n-order curve fitting is performed according to the coordinates of the plurality of sampling points of each Bezier curve and the connected part of the target reference line, to obtain an n-order curve corresponding to each Bezier curve; wherein the part of the target reference line connected by each Bezier curve refers to the part of the target reference line with an s coordinate greater than the s coordinate of the end point, and n>1.

[0054] The loss value of the n-order curve corresponding to each Bezier curve is calculated, and the Bezier curve corresponding to the n-order curve with the minimum loss value is selected as the optimal Bezier curve.

[0055] Preferably, the path generation unit is specifically configured to:

[0056] The coordinates of a plurality of sampling points corresponding to the optimal Bezier curve and the connected part of the target reference line are obtained, the coordinates of the plurality of sampling points are converted from the Frenet coordinate system to the Cartesian coordinate system to obtain coordinates of the plurality of sampling points based on the Cartesian coordinate system, and a segmented function of the vehicle lane-changing path is obtained by connecting any two adjacent sampling points using an m-order polynomial curve according to the coordinates of the plurality of sampling points based on the Cartesian coordinate system; wherein m>1.

[0057] Preferably, the path generation unit is specifically configured to:

[0058] A plurality of position points are obtained by sampling the vehicle lane-changing path at a preset step length, and the curvatures, the orientations of the vehicle, the lane-changing times and the following distances corresponding to the plurality of position points are obtained.

[0059] According to a third aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the vehicle lane-changing path planning method as described above.

[0060] According to a fourth aspect of the present application, there is provided an electronic device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor implementing the vehicle lane-changing path planning method as described above when executing the program.

[0061] The present application has at least the following beneficial effects:

[0062] The present application simultaneously considers static obstacles and dynamic obstacles around the vehicle, obtains coordinates of a plurality of groups of Bezier curve control points according to the coordinates of the vehicle, the speed of the vehicle, the coordinates of obstacles around the vehicle, the speed of obstacles around the vehicle, and a target reference line at the current time, generates a plurality of corresponding Bezier curves based on the coordinates of the plurality of groups of Bezier curve control points, selects an optimal Bezier curve from the plurality of Bezier curves, and obtains a corresponding vehicle lane-changing path according to the optimal Bezier curve, thereby generating a lane-changing path closer to an actual optimal solution.

[0063] Other features and advantages of the present application will be described in the following description. BRIEF DESCRIPTION OF DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0065] Figure 1 A flowchart of a vehicle lane-changing path planning method in an embodiment of the present application.

[0066] Figure 2 A schematic diagram of a Frenet coordinate system.

[0067] Figure 3 A schematic diagram of selecting a plurality of groups of Bezier curve control points in an embodiment of the present application.

[0068] Figure 4 A specific flowchart of a vehicle lane-changing path planning method in a specific embodiment of the present application.

[0069] Figure 5 A schematic diagram of a frame structure of a vehicle lane-changing path planning device in an embodiment of the present application. DETAILED DESCRIPTION

[0070] The detailed description of the accompanying drawings is intended to illustrate the presently preferred embodiments of the invention and is not intended to represent only the forms in which the invention can be implemented. It should be understood that the same or equivalent functions can be accomplished by different embodiments intended to be included within the spirit and scope of the invention.

[0071] One embodiment of the present invention provides a vehicle lane-changing path planning method, such as... Figure 1 As shown, the method in this embodiment includes the following steps:

[0072] Step S1: Obtain the current vehicle coordinates and the coordinates of obstacles around the vehicle based on the Frenet coordinate system;

[0073] Specifically, such as Figure 2 As shown, the Frenet coordinate system is a curvilinear coordinate system with the target reference line as the horizontal axis and the normal distance from the vehicle to the target reference line as the vertical axis. Using the Frenet coordinate system helps to simplify the unnecessary complexity caused by the road shape. In this embodiment, the initially obtained coordinates of the vehicle and the coordinates of the obstacles around the vehicle are coordinates in the vehicle coordinate system, which is constructed based on the Cartesian coordinate system. Therefore, in the steps, it is necessary to first obtain the coordinates of the vehicle and the coordinates of the obstacles around the vehicle in the Cartesian coordinate system and convert them to the Frenet coordinate system. Among them, the obstacles around the vehicle include dynamic obstacles and static obstacles.

[0074] Step S2: Obtain the current speed of the vehicle and the speeds of obstacles around the vehicle;

[0075] Specifically, the vehicle's speed and the speeds of obstacles around the vehicle can be obtained from the output of the vehicle's sensing unit;

[0076] Step S3: Obtain the target reference line; the target reference line is the center line of the target lane for this vehicle to change lanes.

[0077] Specifically, assuming the vehicle is traveling in the first lane and needs to change lanes to the adjacent second lane, then the second lane is the target lane;

[0078] Step S4: Obtain the coordinates of multiple sets of Bézier curve control points based on the current vehicle coordinates, vehicle speed, coordinates of obstacles around the vehicle, speed of obstacles around the vehicle, and the target reference line;

[0079] Specifically, in the embodiment, a second-order Bezier curve, a third-order Bezier curve or a fourth-order Bezier curve can be used, and the generation of the Bezier curve needs a set of Bezier curve control points to define the shape of the curve, and the set of Bezier curve control points includes a plurality of control points; in the embodiment, both the static obstacles and the dynamic obstacles around the vehicle are considered, and a plurality of sets of coordinates of the Bezier curve control points are obtained according to the coordinates of the vehicle, the speed of the vehicle, the coordinates of the obstacles around the vehicle, the speed of the obstacles around the vehicle and the target reference line;

[0080] In step S5, a plurality of Bezier curves corresponding to the plurality of sets of coordinates of the Bezier curve control points are generated.

[0081] In step S6, an optimal Bezier curve is obtained by screening the plurality of Bezier curves, and a vehicle lane-changing path corresponding to the optimal Bezier curve is obtained.

[0082] Specifically, in the embodiment, a plurality of Bezier curves corresponding to the plurality of sets of coordinates of the Bezier curve control points are generated, an optimal Bezier curve is obtained by screening the plurality of Bezier curves, and a vehicle lane-changing path corresponding to the optimal Bezier curve is obtained, so that a lane-changing path closer to an actual optimal solution is generated.

[0083] In some embodiments, a third-order Bezier curve is preferably used, and correspondingly, the coordinates of each set of Bezier curve control points include the coordinates of four control points to define the shape of the Bezier curve; the four control points include a starting point, an ending point, a first intermediate point and a second intermediate point; the starting point is the position of the vehicle at the current time, which is selected fixedly, while the ending point, the first intermediate point and the second intermediate point need to be selected according to actual conditions; the ending point is the position of the vehicle merging into the target reference line, which determines the position at which the curve merges into the target reference line; the first intermediate point is obtained by sampling within the range between the starting point and the ending point, that is, one ending point corresponds to a plurality of first intermediate points; the second intermediate point is obtained by sampling within the range between the first intermediate point and the ending point, and the second intermediate point falls on the target reference line, that is, one intermediate point and one ending point correspond to a plurality of second intermediate points; in the embodiment, the starting point, the ending point, the first intermediate point and the second intermediate point are determined in sequence, and finally, a plurality of sets of Bezier curve control points can be obtained according to the corresponding relationship between the determined starting point, ending point, first intermediate point and second intermediate point.

[0084] In some embodiments, the step S4 includes the selection of the ending point, and the selection of the ending point preferably uses the following method:

[0085] When the obstacle is located behind the vehicle, or the speed V obstacle of the nearest obstacle in front of the vehicle is greater than or equal to the speed V egoWhen the situation is classified as having no low-speed obstacles ahead, it will be handled according to the preset maximum lane-changing time t. max and the current speed V of this vehicle. ego Calculate the coordinates of the endpoint where the vehicle merges into the target reference line. In this case, there is only one endpoint, and this endpoint is used as the fourth control point of the Bézier curve, i.e., the coordinates of this fourth control point are (s,l) = (t). max *V ego ,0);

[0086] When the speed of the nearest obstacle in front of this vehicle is V obstacle Less than the vehicle's speed V ego When this situation occurs, it is classified as a low-speed obstacle ahead and processed accordingly. The coordinates s of the nearest obstacle point to the vehicle are obtained. obstacle ; within the preset lane change time interval [t min ,t max Multiple lane-changing times were sampled evenly at equal intervals within the [internal area], t min and t max These are the preset minimum lane-changing time and maximum lane-changing time; within the preset following distance range [d] min ,d max Multiple following distances were sampled evenly at equal intervals within the [inner] area, d min and d max These are the preset minimum lane change time and maximum lane change time; based on the s-coordinates of the obstacle point. obstacle The multiple lane-changing times and multiple following distances determine the coordinates of multiple endpoints. The coordinates of these multiple endpoints correspond to multiple sets of Bézier curve control points. The formula for calculating the s-coordinate of these multiple endpoints is: s = s obstacle +V obstacle *td, where t is the lane change time obtained from the sampling, t∈[t min ,t max ], where d is the following distance obtained from sampling, d∈[d min ,d max ].

[0087] In some embodiments, see Figure 3 Step S4 includes selecting a first intermediate point. The selection of the first intermediate point takes into account the influence of the vehicle's heading on the trend of the target reference line, and preferably adopts the following method:

[0088] When the intersection of the extended line of the vehicle's current orientation and the target reference line is within a preset distance range, the coordinates of multiple first intermediate points are obtained by uniformly sampling at equal intervals between the starting point and the intersection point, and the first intermediate points are within the range between the starting point and the ending point.

[0089] When the intersection of the extension of the current heading of the vehicle and the target reference line is out of the preset distance range or the intersection does not exist, a virtual intersection at a distance far enough, for example, 400 meters, is artificially set, and then a plurality of coordinates of first intermediate points are obtained by equidistant and uniform sampling on the extension of the current heading of the vehicle within the range between the starting point and each ending point.

[0090] It should be noted that in the selection of the first intermediate points, the relationship between the heading of the vehicle and the target reference line is fully considered, so that the vehicle can naturally merge into the target lane along the trend at the current moment, and the merging is more in line with human intuition.

[0091] In some embodiments, the step S4 comprises:

[0092] A plurality of coordinates of second intermediate points are obtained by equidistant and uniform sampling between each first intermediate point and the corresponding ending point thereof;

[0093] Specifically, in order to smooth the curve when merging into the target reference line, the second intermediate points always fall on the target reference line, that is, the l coordinate of the second intermediate point is always zero, and the s coordinate of the second intermediate point is uniformly distributed and sampled within the range between a first intermediate point and the corresponding ending point thereof, that is, the combination of a first intermediate point and the corresponding ending point thereof corresponds to a plurality of second intermediate points.

[0094] As described above, in the process of determining the control points, the number of the determined second intermediate points is the largest, and each second intermediate point, the corresponding first intermediate point, the ending point and the fixed starting point form a group of Bezier curve control points, so that a plurality of groups of Bezier curve control points can be obtained by the embodiments of the present application, and each group of Bezier curve control points comprises a starting point, a first intermediate point, a second intermediate point and an ending point.

[0095] In some embodiments, in step S5, the Bezier curve B(t) follows the following general parametric equation:

[0096]

[0097] wherein P i is the coordinate of the i th control point, t i is a control parameter between 0 and 1, n is the number of control points, and n = 4 in the embodiments of the present application; the value of t i can be adjusted to control the position and number of sampling points on the generated Bezier curve, and the content of the sampling points is embodied in step S6.

[0098] It should be noted that in the sampling selection of the four control points, the speed of the dynamic obstacle, the estimated lane changing time and the estimated following distance are fully considered, so as to refine the sampling of the position points of the trajectory and realize the partially coupled planning. Compared with the existing completely decoupled method, a more optimal lane changing path can be searched.

[0099] In some embodiments, the step S6 comprises:

[0100] The coordinates of the plurality of sampling points of each Bezier curve and the connected partial target reference line are obtained by equidistant uniform sampling of each Bezier curve and the connected partial target reference line, and n-order curve fitting is performed according to the coordinates of the plurality of sampling points of each Bezier curve and the connected partial target reference line, to obtain an n-order curve corresponding to each Bezier curve; wherein the partial target reference line connected by each Bezier curve refers to the partial target reference line with an s coordinate greater than the terminal point s coordinate, and n>1;

[0101] The loss value of the n-order curve corresponding to each Bezier curve is calculated, and the Bezier curve corresponding to the n-order curve with the minimum loss value is selected as the optimal Bezier curve.

[0102] Specifically, the partial target reference line connected by each Bezier curve refers to the partial target reference line with an s coordinate greater than the Bezier curve, which can be understood as the route part to be traveled by the host vehicle after merging into the target lane, because the host vehicle needs to travel in the middle of the target lane after merging into the target lane;

[0103] For example, the n-order curve in the present embodiment preferably adopts a quintic curve, and the general equation of the quintic polynomial is:

[0104] f(s)=a0+a1s+a2s 2 +a3s 3 +a4s 4 +a5s 5

[0105] There are six unknowns a0-a5 to be solved, so at least six sampling points are needed for least squares regression, that is, equidistant uniform sampling of each Bezier curve and the connected partial target reference line is performed to obtain the coordinates of six sampling points of each Bezier curve and the connected partial target reference line;

[0106] It should be noted that the calculation of the loss value of the n-order curve can be set according to actual considerations.

[0107] In some embodiments, the loss value Cost of the n-th curve is preferably but not limited to a value of a weighted sum of a zero-order reference line offset loss, a first-order smoothness loss, a second-order smoothness loss, a third-order smoothness loss, an expected lane-changing time loss, and an expected end-state car-following distance loss;

[0108] wherein the zero-order reference line offset loss Cost0 is:

[0109] wherein the first-order smoothness loss Cost1 is:

[0110] wherein the second-order smoothness loss Cost2 is:

[0111] wherein the third-order smoothness loss Cost3 is:

[0112] wherein the expected lane-changing time loss Cost t is: t = k·t;

[0113] wherein the expected end-state car-following distance loss Cost d is: d = 1 / (d+σ), σ = 1e-6;

[0114] wherein f(s) is a Bezier curve function, s0 is the s coordinate of the starting point, s t is the s coordinate of the end point or the s coordinate slightly greater than the s coordinate of the end point, k is a preset parameter value, t is the lane-changing time, t ∈ [t min , t max ], d is the car-following distance, d ∈ [d min , d max ];

[0115] It should be noted that for any Bezier curve function f(s), the corresponding starting point, end point, first intermediate point, and second intermediate point are determined, and s0, s t , t, and d are also determined correspondingly; when the speed V obstacle of the nearest obstacle in front of the host vehicle is less than the speed V ego of the host vehicle, it is classified as a case with a low-speed obstacle in front and is processed, then t is the sampled lane-changing time, t ∈ [t min , t max ], and d is the sampled car-following distance, d ∈ [d min , d max ]; when the obstacle is located behind the host vehicle, or the speed V obstacle of the nearest obstacle in front of the host vehicle is greater than or equal to the speed V egoWhen the low-speed front obstacle is not present, t is the preset maximum lane-changing time t max The following is the loss of the zero-order offset from the reference line, the first-order smoothness loss, the second-order smoothness loss, the third-order smoothness loss, the expected lane-changing time loss, and the expected final state following distance loss:

[0116] The following is the loss of the zero-order offset from the reference line, the first-order smoothness loss, the second-order smoothness loss, the third-order smoothness loss, the expected lane-changing time loss, and the expected final state following distance loss:

[0117] Cost = w0·Cost0 + w1·Cost1 + w2·Cost2 + w3·Cost3 + w t ·Cost t +w d ·Cost d

[0118] ω0, ω1, ω2, ω3, ω t , ω d are preset weight parameters;

[0119] It should be noted that in the calculation of the loss value, in addition to the general smoothness and offset indicators, the zero-order to third-order losses are also considered in combination with the sampling strategy of time and distance, and the loss value calculation for the incorporated maneuvering time and the expected following distance is added, so that the overall path can be completed in a reasonable time and provide a reference for the speed planning.

[0120] In some embodiments, the step S6 comprises:

[0121] obtaining the coordinates of the plurality of sampling points corresponding to the optimal Bezier curve and the connected partial target reference line, converting the coordinates of the plurality of sampling points from the Frenet coordinate system to the Cartesian coordinate system to obtain the coordinates of the plurality of sampling points based on the Cartesian coordinate system, and using an m-degree polynomial curve to connect any two adjacent sampling points based on the coordinates of the plurality of sampling points based on the Cartesian coordinate system to obtain a segmented function of the vehicle lane-changing path; wherein m>1;

[0122] Specifically, in this embodiment, a cubic spline curve difference is preferably used, i.e., m is 3, and the segmented function of the vehicle lane-changing path obtained by using an m-degree polynomial curve to connect any two adjacent sampling points is as follows:

[0123] y(x) = g0+ g1x + g2x 2 +g3x 3

[0124] By limiting the first and second smoothness of the end points and the connecting points of each segment, a complete segmented function can be obtained.

[0125] It should be noted that in the Bezier curve sampling stage of the embodiment, by considering the expected maneuvering time of the vehicle, combining the speed of the obstacle, and using a first-order model to calculate the approximate position of the obstacle at the corresponding state at the end of the path, and combining the configured expected final state of the following distance, the merging point position of the curve into the target reference line is obtained, the time factor is introduced into the path planning, the space can be more finely sampled, the operation speed is further improved, and the optimal path result obtained is further closer to the actual optimal path in the time and space domain.

[0126] In some embodiments, the step S6 comprises:

[0127] The vehicle lane changing path is sampled at a preset step length to obtain a plurality of position points, and the curvatures corresponding to the plurality of position points, the orientations of the vehicle, the lane changing times, and the following distances are obtained.

[0128] Specifically, the curvatures corresponding to the plurality of position points of the lane changing path output by the embodiment ultimately, the orientations of the vehicle, the lane changing times, and the following distances are provided to downstream speed planning, which can provide better references for downstream speed planning.

[0129] Figure 4 For a specific flowchart of a vehicle lane changing path planning in one specific embodiment of the application, reference can be made to 4 to understand the content of the above-mentioned embodiments.

[0130] Another embodiment of the application provides a vehicle lane changing path planning device, the device of the embodiment corresponds to the method of the above-mentioned embodiments, and can be used to implement the steps of the method of the above-mentioned embodiments, reference can be made to Figure 5 The device of the embodiment comprises the following units:

[0131] The coordinate acquisition unit 1 is used to acquire the coordinates of the vehicle and the coordinates of the obstacles around the vehicle based on the Frenet coordinate system at the current time;

[0132] The speed acquisition unit 2 is used to acquire the speed of the vehicle and the speed of the obstacles around the vehicle at the current time;

[0133] The reference line acquisition unit 3 is used to acquire the target reference line; the target reference line is the center line of the target lane where the vehicle changes lanes;

[0134] The control point acquisition unit 4 is used to acquire the coordinates of a plurality of groups of Bezier curve control points according to the coordinates of the vehicle, the speed of the vehicle, the coordinates of the obstacles around the vehicle, the speed of the obstacles around the vehicle, and the target reference line at the current time;

[0135] The Bezier curve generation unit 5 is used to generate a plurality of corresponding Bezier curves according to the coordinates of the plurality of groups of Bezier curve control points;

[0136] The path generation unit 6 is used to filter the multiple Bézier curves to obtain an optimal Bézier curve, and to obtain the corresponding vehicle lane-changing path based on the optimal Bézier curve.

[0137] In some embodiments, the coordinates of each set of Bézier curve control points include the coordinates of four control points; the four control points include a start point, an end point, a first intermediate point, and a second intermediate point; the start point is the current position of the vehicle; the end point is the position where the vehicle merges into the target reference line; the first intermediate point is obtained by sampling within the range between the start point and the end point; the second intermediate point is obtained by sampling within the range between the first intermediate point and the end point, and the second intermediate point falls on the target reference line.

[0138] In some embodiments, the control point acquisition unit 4 is specifically used for:

[0139] When an obstacle is located behind the vehicle, or when the speed of the nearest obstacle in front of the vehicle is greater than or equal to the speed of the vehicle, the coordinates of a destination are determined based on the vehicle's speed and the preset maximum lane-changing time.

[0140] When the speed of the nearest obstacle in front of the vehicle is less than the speed of the vehicle, obtain the s-coordinate s of the point on the nearest obstacle that is closest to the vehicle. obstacle ; within the preset lane change time interval [t min ,t max Multiple lane-changing times were sampled evenly at equal intervals within the [d] range; within the preset following distance range [d] min ,d max Multiple following distances were sampled evenly at equal intervals within the obstacle; based on the s-coordinates of the obstacle points... obstacle The multiple lane change times and the multiple following distances determine the coordinates of multiple destinations.

[0141] In some embodiments, the control point acquisition unit 4 is specifically used for:

[0142] When the intersection of the extended line of the vehicle's current orientation and the target reference line is within a preset distance range, the coordinates of multiple first intermediate points are obtained by uniformly sampling at equal distances between the starting point and the intersection point.

[0143] When the intersection of the extension line of the current orientation of the vehicle head and the target reference line is outside the preset distance range or there is no intersection, the coordinates of multiple first intermediate points are obtained by uniformly sampling at equal distances along the extension line of the current orientation of the vehicle head within the range between the starting point and each ending point.

[0144] In some embodiments, the control point acquisition unit 4 is specifically used for:

[0145] Respectively, the equal distance uniform sampling is performed in each first intermediate point and its corresponding one end point to obtain the coordinates of a plurality of second intermediate points.

[0146] In some embodiments, the path generation unit 5 is specifically configured to:

[0147] Respectively, the equal distance uniform sampling is performed on each Bezier curve and its connected partial target reference line to obtain the coordinates of a plurality of sampling points of each Bezier curve and its connected partial target reference line, and n-order curve fitting is performed according to the coordinates of the plurality of sampling points of each Bezier curve and its connected partial target reference line to obtain an n-order curve corresponding to each Bezier curve; wherein the partial target reference line connected by each Bezier curve refers to the partial target reference line with a s coordinate greater than the s coordinate of the end point, and n>1.

[0148] The loss value of the n-order curve corresponding to each Bezier curve is calculated, and the Bezier curve corresponding to the n-order curve with the minimum loss value is selected as the optimal Bezier curve.

[0149] In some embodiments, the path generation unit 5 is specifically configured to:

[0150] The coordinates of a plurality of sampling points corresponding to the optimal Bezier curve and its connected partial target reference line are obtained, the coordinates of the plurality of sampling points are converted from the Frenet coordinate system to the Cartesian coordinate system to obtain coordinates of the plurality of sampling points based on the Cartesian coordinate system, and the segmented function of the vehicle lane-changing path is obtained by connecting any two adjacent sampling points using an m-order polynomial curve according to the coordinates of the plurality of sampling points based on the Cartesian coordinate system; wherein m>1.

[0151] In some embodiments, the path generation unit 5 is specifically configured to:

[0152] A plurality of position points are obtained by sampling the vehicle lane-changing path at a preset step length, and the curvatures, vehicle orientations, lane-changing times, and following distances corresponding to the plurality of position points are obtained.

[0153] It should be noted that the device described in the embodiment corresponds to the method described in the above embodiment, and therefore, the parts of the device described in the embodiment that are not described in detail can be obtained by referring to the content of the method described in the above embodiment, and therefore, the parts are not described here.

[0154] In addition, when the device of the above embodiment is realized in the form of a software function module and sold or used as an independent product, it can be stored in a computer readable storage medium.

[0155] Another embodiment of the present application provides a computer readable storage medium storing a computer program, which, when executed by a processor, implements the vehicle lane-changing path planning method according to any one of the above embodiments.

[0156] In particular, the computer readable storage medium can include any entity or recording medium that can carry the computer program instructions, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, and the like.

[0157] Another embodiment of the present application provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the vehicle lane-changing path planning method according to any one of the above embodiments when executing the program.

[0158] The electronic device can further include a bus connecting different components (including the memory and the processor). The memory can include a computer readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The memory can also include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the present application. The electronic device can also communicate with one or more external devices (such as a keyboard, a pointing device, a display, etc.) and can communicate with one or more devices that enable a user to interact with the electronic device, and / or with any devices (such as a network card) that enable the electronic device to communicate with one or more other computing devices. Such communication can be carried out through an input / output (I / O) interface, and the electronic device can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) through a network adapter.

[0159] From the above description of the embodiments, it can be seen that the embodiments of the present application have the following advantages:

[0160] The embodiments of the present application differ from the conventional path planning based on Bezier curve, specifically, the embodiments of the present application simultaneously consider static obstacles and dynamic obstacles around the vehicle, take the vehicle coordinate at the current time, the vehicle speed, the obstacle coordinate around the vehicle, the obstacle speed around the vehicle, the target reference line, the lane changing time, the following distance after lane changing as the planning constraints to obtain the coordinates of multiple groups of Bezier curve control points, generate corresponding multiple Bezier curves based on the coordinates of the multiple groups of Bezier curve control points, screen the multiple Bezier curves to obtain an optimal Bezier curve, and obtain a corresponding vehicle lane changing path according to the optimal Bezier curve, the vehicle lane changing path considers the static obstacles, the dynamic obstacles, the lane changing time, the following distance after lane changing and other factors around the vehicle, so that the generated vehicle lane changing path is closer to the actual optimal solution; meanwhile, the embodiments of the present application directly select a specific sampling space, so that the sampling is more refined and the overall calculation loss function time is shortened, and the path planning speed is optimized.

[0161] The above has described the embodiments of the present application, the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles, practical application or technical improvement in the market of the embodiments, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A vehicle lane-changing path planning method, characterized by, The method comprises: acquiring the current time's car coordinate based on Frenet coordinate system, car surrounding obstacle coordinate; acquiring the current time's car speed, car surrounding obstacle speed; acquiring target reference line; the target reference line is the center line of the target lane of the car's lane changing driving; acquiring the coordinates of multiple groups of Bezier curve control points according to the current time's car coordinate, car speed, car surrounding obstacle coordinate, car surrounding obstacle speed and the target reference line; generating corresponding multiple Bezier curves according to the coordinates of the multiple groups of Bezier curve control points; screening the multiple Bezier curves to obtain an optimal Bezier curve, and obtaining corresponding vehicle lane changing path according to the optimal Bezier curve.

2. The vehicle lane-changing path planning method according to claim 1, wherein The coordinates of each group of Bezier curve control points comprise the coordinates of four control points; the four control points comprise a starting point, an ending point, a first intermediate point and a second intermediate point; the starting point is the current time's car position; the ending point is the position of the car's merging into the target reference line; the first intermediate point is obtained by sampling in the range between the starting point and the ending point; the second intermediate point is obtained by sampling in the range between the first intermediate point and the ending point, and the second intermediate point falls on the target reference line.

3. The vehicle lane-changing path planning method according to claim 2, wherein The acquiring the coordinates of multiple groups of Bezier curve control points according to the current time's car coordinate, car speed, car surrounding obstacle coordinate, car surrounding obstacle speed and the target reference line comprises: when the obstacle is located behind the car, or the speed of the nearest obstacle in front of the car is greater than or equal to the car speed, determining the coordinate of an ending point according to the car speed and a preset maximum lane changing time; When the speed of the nearest obstacle in front of the vehicle is less than the speed of the vehicle, obtain the s-coordinate s of the point on the nearest obstacle that is closest to the vehicle. obstacle ; within the preset lane change time interval [t min ,t max Multiple lane-changing times were sampled evenly at equal intervals within the [d] range; within the preset following distance range [d] min ,d max Multiple following distances were sampled evenly at equal intervals within the obstacle; based on the s-coordinates of the obstacle points... obstacle The multiple lane change times and the multiple following distances determine the coordinates of multiple destinations.

4. The vehicle lane-changing path planning method according to claim 2 or 3, characterized in that, The acquiring the coordinates of multiple groups of Bezier curve control points according to the car coordinate, the car speed, the obstacle coordinate, the obstacle speed and the target reference line comprises: when the intersection of the extension line of the current direction of the car and the target reference line is within the preset distance range, obtaining the coordinates of multiple first intermediate points by equidistance uniform sampling on the line between the starting point and the intersection; when the intersection of the extension line of the current direction of the car and the target reference line is outside the preset distance range or does not exist, obtaining the coordinates of multiple first intermediate points by equidistance uniform sampling on the extension line of the current direction of the car in the range between the starting point and each ending point.

5. The vehicle lane-changing path planning method according to claim 4, wherein The acquiring the coordinates of multiple groups of Bezier curve control points according to the car coordinate, the car speed, the obstacle coordinate, the obstacle speed and the target reference line comprises: respectively equidistance uniform sampling in the range between each first intermediate point and its corresponding one ending point to obtain the coordinates of multiple second intermediate points.

6. The vehicle lane-changing path planning method according to claim 1, wherein The screening the multiple Bezier curves to obtain an optimal Bezier curve, and obtaining corresponding vehicle lane changing path according to the optimal Bezier curve comprises: The coordinates of the sampling points of each Bezier curve and the partial target reference line connected therewith are obtained by equidistantly and uniformly sampling each Bezier curve and the partial target reference line connected therewith, and n-order curve fitting is performed according to the coordinates of the sampling points of each Bezier curve and the partial target reference line connected therewith, to obtain an n-order curve corresponding to each Bezier curve; wherein the partial target reference line connected with each Bezier curve refers to the partial target reference line with a s coordinate greater than the s coordinate of the end point, and n>1; The loss value of the n-order curve corresponding to each Bezier curve is calculated, and the Bezier curve corresponding to the n-order curve with the minimum loss value is selected as the optimal Bezier curve.

7. The vehicle lane-changing path planning method according to claim 6, wherein The loss value of the n-order curve is the weighted sum of the zero-order reference line offset loss, the first-order smoothness loss, the second-order smoothness loss, the third-order smoothness loss, the expected lane changing time loss, and the expected following distance loss of the final state; The zero-order and reference line offset loss Cost0 is: The first-order smoothness loss Cost1 is: The second order smoothness loss is Cost2: The third-order smoothness loss Cost3 is: the expected lane change time loss Cost t is: Cost t = k · t; The desired final state of the following distance loss cost d is: Cost d = 1 / (d + σ), σ = 1e-6; Wherein, f(s) is a Bezier curve function, s0 is the s coordinate of the starting point, s t is the s coordinate of the end point or the s coordinate slightly greater than the end point, k is a preset parameter value, t is the lane changing time, t ∈ [t min ,t max ], d is the following distance, d ∈ [d min ,d max ].

8. The vehicle lane-changing path planning method according to claim 6, wherein The optimal Bezier curve is obtained by screening the plurality of Bezier curves, and a vehicle lane changing path corresponding to the optimal Bezier curve is obtained, comprising: The coordinates of the sampling points corresponding to the optimal Bezier curve and the partial target reference line connected therewith are obtained, the coordinates of the sampling points are converted from the Frenet coordinate system to the Cartesian coordinate system to obtain the coordinates of the sampling points based on the Cartesian coordinate system, and the coordinates of the sampling points based on the Cartesian coordinate system are used to connect any two adjacent sampling points using an m-order polynomial curve to obtain a segmented function of the vehicle lane changing path; wherein m>1.

9. The vehicle lane-changing path planning method according to claim 8, wherein The optimal Bezier curve is obtained by screening the plurality of Bezier curves, and a vehicle lane changing path corresponding to the optimal Bezier curve is obtained, comprising: The vehicle lane changing path is sampled at a preset step size to obtain a plurality of position points, and the curvatures, orientations, lane changing times, and following distances corresponding to the plurality of position points are obtained.

10. A vehicle lane-changing path planning device characterized by comprising: The device comprises: A coordinate acquisition unit for acquiring the coordinates of the host vehicle and the coordinates of the obstacles around the host vehicle based on the Frenet coordinate system at the current time; A speed acquisition unit for acquiring the speed of the host vehicle and the speed of the obstacles around the host vehicle at the current time; A reference line acquisition unit for acquiring a target reference line; the target reference line is the center line of the target lane for the host vehicle to change lanes; A control point acquisition unit for acquiring the coordinates of a plurality of sets of Bezier curve control points based on the coordinates of the host vehicle, the speed of the host vehicle, the coordinates of the obstacles around the host vehicle, the speed of the obstacles around the host vehicle, and the target reference line at the current time; A Bezier curve generation unit for generating a plurality of corresponding Bezier curves based on the coordinates of the plurality of sets of Bezier curve control points; A path generation unit for screening the plurality of Bezier curves to obtain an optimal Bezier curve, and obtaining a vehicle lane changing path corresponding to the optimal Bezier curve.

11. The vehicle lane-changing path planning device according to claim 10, characterized by The coordinates of each group of Bezier curve control points include coordinates of four control points; the four control points include a start point, an end point, a first intermediate point and a second intermediate point; the start point is a current vehicle position; the end point is a position where the vehicle is to be on the target reference line; The first intermediate point is obtained by sampling in a range between the start point and the end point; The second intermediate point is obtained by sampling in a range between the first intermediate point and the end point, and the second intermediate point is on the target reference line.

12. The vehicle lane-changing path planning device according to claim 11, wherein The control point acquisition unit is specifically configured to: When the obstacle is located behind the vehicle, or the speed of the nearest obstacle in front of the vehicle is greater than or equal to the vehicle speed, determine the coordinates of an end point according to the vehicle speed and a preset maximum lane changing time; When the speed of the nearest obstacle in front of the vehicle is less than the speed of the vehicle, obtain the s-coordinate s of the point on the nearest obstacle that is closest to the vehicle. obstacle ; within the preset lane change time interval [t min ,t max Multiple lane-changing times were sampled evenly at equal intervals within the [d] range; within the preset following distance range [d] min ,d max Multiple following distances were sampled evenly at equal intervals within the obstacle; based on the s-coordinates of the obstacle points... obstacle The multiple lane change times and the multiple following distances determine the coordinates of multiple destinations.

13. The vehicle lane-changing path planning device according to claim 11 or 12, characterized by, The control point acquisition unit is specifically configured to: When the intersection of the extension line of the current heading of the vehicle and the target reference line is within a preset distance range, obtain the coordinates of a plurality of first intermediate points by equidistant uniform sampling on the line between the start point and the intersection; When the intersection of the extension line of the current heading of the vehicle and the target reference line is outside the preset distance range or does not exist, obtain the coordinates of a plurality of first intermediate points by equidistant uniform sampling on the extension line of the current heading of the vehicle in the range between the start point and each end point.

14. The vehicle lane-changing path planning device according to claim 13, wherein The control point acquisition unit is specifically configured to: Respectively, equidistant uniform sampling in the range between each first intermediate point and its corresponding end point obtains the coordinates of a plurality of second intermediate points.

15. The vehicle lane-changing path planning apparatus according to claim 10, wherein The path generation unit is specifically configured to: Respectively, equidistant uniform sampling on each Bezier curve and the part of the target reference line connected thereto obtains the coordinates of a plurality of sampling points of each Bezier curve and the part of the target reference line connected thereto, and performs n times curve fitting according to the coordinates of the plurality of sampling points of each Bezier curve and the part of the target reference line connected thereto, to obtain an n-th curve corresponding to each Bezier curve; wherein, the part of the target reference line connected to each Bezier curve refers to the part of the target reference line with an s coordinate greater than the s coordinate of the end point, and n>1; Calculate the loss value of the n-th curve corresponding to each Bezier curve, and select the Bezier curve corresponding to the n-th curve with the smallest loss value as the optimal Bezier curve.

16. The vehicle lane-changing path planning device according to claim 15, wherein The path generation unit is specifically configured to: Obtain the coordinates of a plurality of sampling points corresponding to the optimal Bezier curve and the part of the target reference line connected thereto, convert the coordinates of the plurality of sampling points from the Frenet coordinate system to the Cartesian coordinate system to obtain coordinates of the plurality of sampling points based on the Cartesian coordinate system, and use an m-th polynomial curve to connect any two adjacent sampling points according to the coordinates of the plurality of sampling points based on the Cartesian coordinate system to obtain a segmented function of the vehicle lane changing path; wherein, m>1.

17. The vehicle lane-changing path planning device according to claim 16, wherein The path generation unit is specifically configured to: Sample the vehicle lane changing path at a preset step length to obtain a plurality of position points, and obtain the corresponding curvature, vehicle heading, lane changing time and following distance of the plurality of position points.

18. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the vehicle lane-changing path planning method in any one of claims 1-9.

19. An electronic device, comprising: A computer program product comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor implements the vehicle lane-changing path planning method in any one of claims 1-9 when executing the program.

Images