CN117622114B

CN117622114B - Parking path planning method and device, computer equipment and storage medium

Info

Publication number: CN117622114B
Application number: CN202311360406.6A
Authority: CN
Inventors: 赵远东; 郭晓丹
Original assignee: Mgjia Beijing Technology Co ltd
Current assignee: Mgjia Beijing Technology Co ltd
Priority date: 2023-10-19
Filing date: 2023-10-19
Publication date: 2024-08-09
Anticipated expiration: 2043-10-19
Also published as: CN117622114A

Abstract

The invention relates to the technical field of intelligent driving, and discloses a parking path planning method, a device, computer equipment and a storage medium. The method comprises the following steps: determining a target parking space; acquiring size information of a vehicle and lane obstacle position information of one side of a target parking space far away from the vehicle; determining a parking path planning type of the vehicle based on the target parking space, the size information of the vehicle and a lane obstacle on one side of the target parking space away from the vehicle; selecting each candidate point based on the planning type of the parking path and respectively performing collision detection to determine an intermediate point from the candidate points; and planning a path from the current position of the vehicle to the middle point and a path from the middle point to the target point to obtain a parking path planning result. By the aid of the scheme, the flexibility of parking path planning can be improved.

Description

Parking path planning method and device, computer equipment and storage medium

Technical Field

The invention relates to the technical field of intelligent driving, in particular to a parking path planning method, a device, computer equipment and a storage medium.

Background

At present, the driving travel is becoming popular, the parking space is becoming lack, and how to park better becomes a problem to be solved urgently.

In the traditional method, a parking path is selected based on the judgment of a driver on the parking environment, and the influence on the parking path is greatly judged by personal experience of the driver. In the related art, a parking path is planned based on HybridA (Hybrid a) and RS (Reeds-Shepp) curve splicing methods, the Hybrid a algorithm is a graph searching algorithm, heuristic searching is performed under a continuous coordinate system, the planned path considers the kinematic constraint of the vehicle, namely, the maximum curvature constraint of the vehicle is met, and the RS curve can splice a plurality of sections of arcs and straight lines into the path and support reverse motion planning.

However, the above method is susceptible to scene environmental factors to misjudge the parkable space as unbuckable.

Disclosure of Invention

In view of the above, the present invention provides a parking path planning method, apparatus, computer device and storage medium, so as to solve the problem that the parkable space is misjudged as being unbuckled due to the influence of scene environment factors.

In a first aspect, the present invention provides a parking path planning method, including:

determining a target parking space, wherein the target parking space comprises a target point for referring to the pose of a vehicle after the vehicle is parked;

Acquiring size information of a vehicle and lane obstacle position information of one side of the target parking space far away from the vehicle;

Determining a parking path planning type of the vehicle based on the target parking space, the size information of the vehicle and a lane obstacle on one side of the target parking space away from the vehicle, wherein the parking path planning type is divided based on the position of the parking space and the surrounding environment, and each parking path planning type corresponds to one parking path;

selecting each candidate point based on the parking path planning type and respectively performing collision detection to determine an intermediate point from the candidate points; the collision detection is used for detecting whether the vehicle can keep a safe distance with the obstacle in the process of parking based on the corresponding candidate point, and the middle point is a starting point which can park the vehicle to a target point and keeps the safe distance with the obstacle in the process;

And planning a path from the current position of the vehicle to the middle point and a path from the middle point to the target point to obtain a parking path planning result.

According to the scheme, the parking path is divided into the path from the current position of the vehicle to the middle point and the path from the middle point to the target point and is respectively planned by selecting the proper middle point, so that the situation that the parkable position is judged to be unbuckled due to the influence of scene environment factors can be planned mistakenly, the planning flexibility of the parking path can be improved, and the application range is enlarged.

In an alternative embodiment, after determining the target parking space, the method further includes:

and determining a lane center line, wherein the lane center line is the center line of a lane which is outside the target parking space and is perpendicular to the length direction of the target parking space.

In an alternative embodiment, the determining the parking path planning type of the vehicle based on the target parking space, the size information of the vehicle, and the lane obstacle on the side of the target parking space away from the vehicle includes:

Establishing a parking environment map based on the target parking space, the size information of the vehicle and a lane barrier on one side of the target parking space away from the vehicle;

Judging whether the distance between a vehicle body and a lane barrier on one side of a target parking space far away from the vehicle is a safe distance or not when the vehicle exits from the target parking space with the minimum turning radius based on a parking environment map; the minimum turning radius is the minimum radius which can be reached when the vehicle turns;

And if the vehicle is at the safe distance, determining the planning type of the parking path of the vehicle for parking to be a narrow lane.

By the scheme, the parking path planning type is further limited to be a narrow lane under what scene, and the scheme is refined.

In an alternative embodiment, the selecting each candidate point based on the parking path planning type and performing collision detection respectively to determine an intermediate point from the candidate points includes:

Selecting an initial point on a lane center line; the transverse distance between the initial point and the target point is the sum of half of the lane width, the distance between the target point and the target parking space opening and the minimum safety distance, and the longitudinal distance between the initial point and the target point is the difference between the length of the vehicle and the rear suspension length of the vehicle;

performing collision detection based on the initial point;

If the collision detection is passed, taking the initial point as a middle point;

If the collision detection does not pass, performing transverse adjustment or longitudinal adjustment on the lane central line by taking the initial point as a reference, selecting other candidate points and respectively performing the collision detection until the candidate points passing the collision detection are selected as intermediate points.

By the scheme, when the parking path planning type is a narrow lane, the method further limits how to select the middle point, and the scheme is refined.

Judging whether the distance between a lane barrier on one side of the target parking space far away from the vehicle and the side of the target parking space exceeds the sum of the length of the vehicle and the minimum safety distance or not based on a parking environment map;

if the vehicle is not in excess, determining that the planning type of the parking path for parking the vehicle is a broken road.

By the scheme, the situation that the parking path planning type is a broken road in which scene is further defined, and the scheme is refined.

Turning the target point to the opposite side of the lane by taking the center line of the lane as an axis;

taking the current pose of the vehicle as a starting endpoint, taking the central line of the vehicle as a tangent line, and taking the radius as the minimum turning radius and the arc line with the arc center angle pi/3 as the arc lines on both sides of the central line of the vehicle to obtain a first arc line and a second arc line;

Respectively carrying out collision detection on two endpoints of the first arc line and two endpoints of the second arc line;

if an endpoint passing collision detection exists, taking the endpoint as an intermediate point;

If the end point passing through the collision detection does not exist, gradually expanding the radius of the arc line and adjusting the corresponding arc center angle, and performing the collision detection on the end point of the arc line until the end point passing through the collision detection is selected as a middle point.

By the scheme, when the planning type of the parking path is a broken road, the method further limits how to select the intermediate point, and the scheme is refined.

In an alternative embodiment, the planning the path from the current position of the vehicle to the intermediate point and the path from the intermediate point to the target point to obtain a parking path planning result includes:

planning a path from the current position of the vehicle to the intermediate point by using an automatic path planning algorithm to obtain a first result linked list; the automatic path planning algorithm is a pre-written program for automatic path planning;

Taking the target point as a starting point, taking the intermediate point as an end point, and planning a path from the target point to the intermediate point by using an automatic path planning algorithm to obtain a second result linked list;

Turning over the second result linked list, and setting the movement direction of the vehicle corresponding to the second result linked list to be the opposite direction when the vehicle runs, so as to obtain a third result linked list;

And linking the first result linked list with the third result linked list to obtain a parking path planning result.

According to the scheme, how to plan the path from the current position of the vehicle to the middle point and the path from the middle point to the target point respectively is further limited, and the two paths are combined into the whole parking path, so that the scheme is refined.

In a second aspect, the present invention provides a parking path planning apparatus, the apparatus comprising:

the parking space determining module is used for determining a target parking space, wherein the target parking space comprises a target point for referring to the pose of the vehicle after the vehicle is parked;

The information acquisition module is used for acquiring the size information of the vehicle and the position information of the lane obstacle on the side, far away from the vehicle, of the target parking space;

The type determining module is used for determining a parking path planning type of the vehicle based on the target parking space, the size information of the vehicle and a lane obstacle on one side of the target parking space away from the vehicle, wherein the parking path planning type is divided based on the position of the parking space and the surrounding environment, and each parking path planning type corresponds to one parking path;

The intermediate point selection module is used for selecting each candidate point based on the parking path planning type and respectively performing collision detection so as to determine an intermediate point from the candidate points; the collision detection is used for detecting whether the vehicle can keep a safe distance with the obstacle in the process of parking based on the corresponding candidate point, and the middle point is a starting point which can park the vehicle to a target point and keeps the safe distance with the obstacle in the process;

And the path planning module is used for planning a path from the current position of the vehicle to the middle point and a path from the middle point to the target point to obtain a parking path planning result.

In a third aspect, the present invention provides a computer device comprising: the parking path planning system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the parking path planning method according to the first aspect or any implementation mode corresponding to the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the parking path planning method of the first aspect or any one of the embodiments corresponding thereto.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method of parking path planning in accordance with an embodiment of the present invention;

FIG. 2 is a flow chart of another method of parking path planning in accordance with an embodiment of the present invention;

FIG. 3 illustrates a schematic diagram of a target parking spot and lane according to an embodiment of the present application;

FIG. 4 illustrates a schematic view of a parking path plan in a narrow lane scenario in accordance with an embodiment of the present application;

FIG. 5 shows a schematic diagram of the geometric relationship in a narrow lane scenario according to an embodiment of the present application;

fig. 6 shows a schematic diagram of a broken-end scenario according to an embodiment of the present application;

Fig. 7 shows a schematic diagram of a parking path planning in a broken road scenario according to an embodiment of the present application;

FIG. 8 is a block diagram of a parking path planning apparatus according to an embodiment of the present invention;

fig. 9 is a schematic diagram of a hardware structure of a computer device (for a computer device having an input device and an output device) according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The related art parking assist planning scheme plans a path based on the principle of vehicle body kinematics rather than a state space when searching based on HybridA and RS curve stitching method hybridA, so that when some parking spaces are located at special positions, the related art parking assist planning scheme can iterate over time to search out a path meeting the requirements when planning the path to the parking space, and determine the parking spaces located at the special positions as non-parkable, but in reality, the parking spaces located at the special positions are likely to be target parking spaces that the driver wants to select.

Therefore, the embodiment of the invention provides a parking path planning method, which performs parking path planning by searching for the middle point of a parking path so as to perform parking path planning on the situation that the vehicle cannot be parked originally.

According to an embodiment of the present invention, a parking path planning method embodiment is provided, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order other than that shown or described herein.

In this embodiment, a parking path planning method is provided, which may be used in the above mobile terminal, such as a mobile phone, a tablet pc, etc., fig. 1 is a flowchart of a parking path planning method according to an embodiment of the present invention, and as shown in fig. 1, the flowchart includes the following steps:

step S101, determining a target parking space.

The target parking space comprises a target point for referring to the pose of the vehicle after the vehicle is parked.

Firstly, determining a target parking space to be parked, setting a target point in the target parking space for conveniently planning a parking path, and completing parking when the relative pose of the vehicle and the target point reaches a preset target.

Optionally, the vertical position where the midpoint of the rear axle should be when the vehicle is parked in the target parking space is set as the target point, that is, when the parking path planning is performed, the vehicle is parked in the target parking space, and the midpoint of the rear axle of the vehicle and the target point are at the same vertical position as the target point.

Further, a threshold value relative to the target point is set, and the parking path planning target is set by taking the vehicle into the target parking space and the distance between the midpoint of the rear wheel axle of the vehicle and the target point in the vertical direction does not exceed the threshold value.

Step S102, size information of a vehicle and lane obstacle position information of one side of the target parking space far away from the vehicle are obtained.

The scheme is suitable for the situation that the target parking space is located on one side of the lane and is a vertical parking space, and the vehicle runs towards one side of the target parking space away from the vehicle. Because the target parking space is a vertical parking space, the vehicle needs to drive through the target parking space and go back into storage, however, because the barrier exists on one side of the target parking space away from the vehicle, the side of the target parking space away from the vehicle has insufficient space, so that the vehicle cannot drive through the target parking space to finish the go back into storage, and the situation is judged as being unable to park in the related art.

Therefore, the size information of the vehicle and the position information of the lane obstacle on the side, far away from the vehicle, of the target parking space need to be acquired firstly, so as to judge whether the parking path planning on the target parking space belongs to the application condition of the scheme, and if so, the parking path planning is carried out according to the scheme.

Step S103, determining the parking path planning type of the vehicle based on the target parking space, the size information of the vehicle and the lane barrier on the side of the target parking space away from the vehicle.

The parking path planning types are divided based on the positions of parking spaces and surrounding environments, and each parking path planning type corresponds to one parking path.

After the parking path planning type of the vehicle to the target parking space is determined, a corresponding mode can be selected according to the parking path planning type to carry out parking path planning.

Step S104, selecting each candidate point based on the parking path planning type and respectively performing collision detection to determine an intermediate point from the candidate points.

The collision detection is used for detecting whether the vehicle can keep a safe distance with the obstacle in the process of parking based on the corresponding candidate point, and the middle point is a starting point of the vehicle which can park to the target point and keeps the safe distance with the obstacle in the process.

According to different parking path planning types, different candidate points can be selected, and each parking path planning type corresponds to a plurality of candidate points. After the type of the parking path planning is determined, the candidate point with the highest possibility can be firstly selected according to practical experience, whether the candidate point passes the collision detection is verified, and other candidate points are continuously selected until the intermediate point passing the collision detection is selected and used as a reference point of the parking path planning.

Step S105, a path from the current position of the vehicle to the middle point and a path from the middle point to the target point are planned, and a parking path planning result is obtained.

The path from the middle point to the target point of the vehicle is the path for reversing and warehousing, so that the path from the current position of the vehicle to the middle point and the path from the middle point to the target point can be respectively planned, and then the two paths are combined to be used as a planning result of the parking path.

According to the parking path planning method provided by the embodiment, the parking path is divided into the path from the current position of the vehicle to the middle point and the path from the middle point to the target point through selecting the proper middle point and planning respectively, so that the situation that the parkable position is judged to be unbuckled due to the influence of scene environment factors can be planned mistakenly, the flexibility of parking path planning can be improved, and the application range is enlarged.

In this embodiment, a parking path planning method is provided, which may be used in the above mobile terminal, such as a mobile phone, a tablet pc, etc., fig. 2 is a flowchart of a parking path planning method according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:

Step S201, determining a target parking space.

Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.

Step S202, determining a lane center line.

The central line of the lane is the central line of the lane which is outside the target parking space and is perpendicular to the length direction of the target parking space.

Fig. 3 shows a schematic diagram of a target parking space and a lane according to an embodiment of the present application. As shown in fig. 3, the gray part is the side of the target parking space far away from the vehicle, the vehicle runs to the side of the target parking space far away from the vehicle, the target parking space is the vertical parking space, and the point a is the vertex of the parking space opening of the target parking space far away from the vehicle.

Step S203, acquiring size information of the vehicle and lane obstacle position information of the target parking space on a side far away from the vehicle.

Please refer to step S102 in the embodiment shown in fig. 1 in detail, which is not described herein.

Step S204, determining the parking path planning type of the vehicle based on the target parking space, the size information of the vehicle and the lane barrier on the side of the target parking space away from the vehicle.

Specifically, the step S204 includes:

in step S2041, a parking environment map is created based on the target parking space, the size information of the vehicle, and a lane obstacle on a side of the target parking space away from the vehicle.

The corresponding scene map can be established by software with a map establishing function in the related technology, and is converted into a distance map, a grid map or a Veno map and the like which can be used by the scheme to serve as a parking environment map.

Optionally, the area of the parking environment map is no more than 50 square meters.

Step S2042, based on the parking environment map, determines whether the distance between the vehicle body and the lane obstacle on the side of the target parking space away from the vehicle is a safe distance when the vehicle exits from the target parking space with the minimum turning radius.

The minimum turning radius is the minimum radius which can be achieved when the vehicle turns, and can be adjusted according to the actual condition of the vehicle.

Fig. 4 shows a schematic diagram of a parking path plan in a narrow lane scenario according to an embodiment of the present application. As shown in fig. 4, when the parking path planning type is a narrow lane (steps S2041 to 2043), lane obstacles on the side of the target parking space away from the vehicle are distributed on both sides of the lane (the side of the lane close to the target parking space and the side of the lane away from the parking space), so that the passable width of the lane is narrowed. It should be noted that the obstacle may be a physical object or an area where the vehicle cannot enter.

In step S2043, if the vehicle is at the safe distance, it is determined that the parking path planning type of the vehicle for parking is a narrow lane.

Fig. 5 shows a schematic diagram of the geometrical relationship in a narrow lane scenario according to an embodiment of the present application. As shown in fig. 5, where R is the minimum turning radius of the vehicle, O is the center of R, R is the distance from the end point of one side of the lane opening to the center O, goal _to_edge is the distance from the target point to the side of the parking space, w is the vehicle width, safe_dis is the safe distance, length is the vehicle length, real is the rear overhang distance, r_f is the distance between the center O and the midpoint of the front side of the vehicle when the vehicle arrives at the obstacle, length-real is the connection line between R and the end point of r_f, α is the angle between R and r_f, β is the angle between length-real and the horizontal direction when the vehicle arrives at the obstacle, and turn_f is the distance between R and the parking space opening, satisfying the following formula:

β＝π/2-α

Through the geometric relationship, the critical distance between the obstacle on the side of the lane far from the target parking space and the parking space opening can be obtained from the lane obstacle on the side of the target parking space far from the vehicle, and the critical distance is used as a standard for judging whether the planning type of the parking path is a narrow lane.

It should be noted that, in this scheme, the safe distance refers to a distance that the vehicle can park and accords with the scene of this scheme, and in fact, when the distance between the vehicle body and the lane obstacle on the side of the target parking space away from the vehicle exceeds the safe distance, the space for the vehicle to park is more abundant, so that the lane is a normal lane, and the parking path planning method in the related art can be adopted to plan the parking path. And when the distance between the vehicle body and the lane barrier on the side of the target parking space away from the vehicle is smaller than the safety distance, sufficient space cannot be provided for parking the vehicle, and the scheme is not suitable for the scheme.

If the safety distance in the actual application scene is set to be a fixed value, the applicable conditions are too few, so that the safety distance is set to be a threshold range, and the maximum safety distance and the minimum safety distance can be set according to actual requirements.

Step S2044, based on the parking environment map, judges whether the distance between the lane obstacle on the side of the target parking space far from the vehicle and the side of the target parking space exceeds the sum of the vehicle length and the minimum safety distance.

Fig. 6 shows a schematic diagram of a broken-end scenario according to an embodiment of the present application. As shown in fig. 6, when the parking path planning type is a break (step S2041, step S2044 to step 2045), the target parking space is far from the lane obstacle on the vehicle side so that the vehicle cannot continue to travel forward along the lane after reaching the obstacle when traveling toward the target parking space far from the vehicle side. It should be noted that the obstacle may be a physical object or an area where the vehicle cannot enter.

Optionally, as shown in fig. 6, the two sides of the target parking space are AB and CD respectively, the CE is used as a reference, the CE is translated along a direction parallel to the lane toward the vehicle running direction, the CE is translated by a distance of half a vehicle length (maximum translation distance), in the translation process, whether the contacted obstacle has enough clearance for the vehicle to pass through (i.e. whether the distance between the lane obstacle on the side of the target parking space away from the vehicle and the side of the target parking space exceeds the sum of the vehicle length and the minimum safety distance) is judged, if the clearance for allowing the vehicle to pass through exists, the CE is translated until the obstacle without a passage allowing the vehicle to pass through is touched or the maximum translation distance is reached. If the final translation distance is smaller than the sum of the vehicle length and the minimum safety distance, judging that the vehicle is broken, otherwise, judging that the vehicle is a normal lane.

Step S2045, if not, determining that the type of parking path planning for parking the vehicle is a broken road.

If the distance between the lane barrier on the side of the target parking space, which is far away from the vehicle, and the side distance of the target parking space exceeds the sum of the vehicle length and the minimum safety distance, the space for the vehicle to park is indicated to exist between the target parking space and the barrier, the lane is a normal lane, and the parking path planning method in the related technology can be adopted for parking path planning.

Step S205, selecting each candidate point based on the parking path planning type and performing collision detection respectively, so as to determine an intermediate point from the candidate points.

Specifically, the step S205 includes:

Step S2051, selecting an initial point on the lane center line.

The transverse distance between the initial point and the target point is the sum of half of the lane width, the distance between the target point and the target parking space opening and the minimum safety distance, and the longitudinal distance between the initial point and the target point is the difference between the length of the vehicle and the rear suspension length of the vehicle.

Steps S2051 to S2054 are applicable to a scene in which the parking path planning type is a narrow lane.

As shown in fig. 4, first, an initial candidate point (initial point) is selected, which may be selected from the lane center line, so as to facilitate subsequent adjustment. The initial point can be selected empirically, for example, according to the test result of the real vehicle, the position where the vehicle is most easy to park in a reverse warehouse (the transverse distance between the initial point and the target point is half of the width of the vehicle, the distance between the target point and the target parking space opening and the minimum safety distance are the sum of the transverse distance between the initial point and the target point, and the longitudinal distance between the initial point and the target point is the difference between the length of the vehicle and the rear suspension length of the vehicle) is selected as the initial point. Wherein mid_node is the middle point, goal _to_door is the distance from the target point to the parking space, start_dis_ goal is the lateral distance between the initial point and the target point, start_dis_start is the longitudinal distance between the initial point and the target point, and the following formula is satisfied:

start_dis_goal＝goal_to_door+road_width/2+safe_dis

start_dis_stall＝car_length-rear

The road_width is the lane width, safe_dis is the minimum safety distance, car_length is the vehicle length, and rear is the vehicle rear overhang length.

Step S2052, based on the initial point, collision detection is performed.

The collision detection can simulate whether the vehicle can keep a safe distance with the obstacle when taking the selected candidate point as the intermediate point and respectively planning the path from the current position of the vehicle to the intermediate point and the path from the intermediate point to the target point.

In step S2053, if the collision detection is passed, the initial point is set as the intermediate point.

And according to the collision detection, the selected candidate points meet the requirements, and the candidate points are used as intermediate points for planning the parking path.

In step S2054, if the collision detection is not passed, the lane is transversely or longitudinally adjusted based on the initial point, and other candidate points are selected and collision detection is performed respectively until the candidate points passing the collision detection are selected as intermediate points.

If the candidate points which are not selected by the collision detection instruction do not meet the requirement, other candidate points are required to be selected as intermediate points for collision detection, and the collision detection can be repeatedly performed by performing transverse adjustment or longitudinal adjustment based on the previously selected candidate points.

Optionally, taking the longitudinal line as a reference, firstly transversely separating from the target point adjustment candidate point, then transversely approaching to the target point adjustment candidate point, repeatedly performing collision detection, transversely adjusting the intermediate point which is longitudinally separated from the parking space opening direction without passing the collision detection, longitudinally adjusting the intermediate point without passing the collision detection, and repeatedly and alternately adjusting the transverse and longitudinal positions until a proper candidate point is selected as the intermediate point.

In step S2055, the target point is turned over to the opposite side of the lane with the lane center line as the axis.

Step S2055 to step S2059 are applicable to a scene in which the parking path planning type is a broken road.

Fig. 7 shows a schematic diagram of a parking path plan in a broken road scenario according to an embodiment of the present application. For a scene that the type of the parking path planning is a broken road, the main reason of the overtime searching when the hybridA is used for the parking path planning is that an expandable node capable of turning around the vehicle cannot be provided at a lane cut off by an obstacle, so the parking path planning can be split into two steps by selecting a middle point, and the problem that hybridA is used for finding the turning around position of the vehicle by adopting a general searching strategy can be solved by utilizing the middle point. Since the obstacle blocks the target parking space from the lane on the vehicle side, the intermediate point needs to be found from the target parking space on the vehicle side.

As shown in fig. 7, the vertex of the target parking space is ABCD, the target parking space is turned over to the opposite side of the lane with the lane center line as the axis, and a 'B' C 'D' is obtained (the same applies to turning over the target point to the opposite side of the lane, and the target point and the turned-over target point are actually taken as the end points of the parking path). Because the vehicle has the minimum turning radius and the vehicle head needs to turn 180 degrees when parking, if the number of gear shifting times of the vehicle is expected to be as small as possible according to a kinematics rule, the space of the lane is insufficient, so that the vehicle head can normally turn if the vehicle is expected, the number of gear shifting times is as small as possible, and enough space needs to be reserved in the areas on two sides of the lane.

Step S2056, taking the current pose of the vehicle as a starting endpoint, taking the central line of the vehicle as a tangent line, and taking the radius as the minimum turning radius and the arc line with the arc angle pi/3 at both sides of the central line of the vehicle to obtain a first arc line and a second arc line.

The arc center angle is determined to be pi/3, so that the vehicle can be turned 3 times by utilizing the space on two sides of the lane when turning, and the 180-degree rotation of the vehicle body can be completed 3 times each time by turning 60 degrees.

Step S2057, performing collision detection on the two endpoints of the first arc line and the two endpoints of the second arc line respectively.

As shown in fig. 7, two end points of the first arc line are point 1 and point 3, two end points of the second arc line are point 2 and point 4, and the selection sequence can be selected according to habit of a driver or distribution situation of obstacles at each place in an actual scene (for example, the other side is selected if an obstacle is present on one side of a lane), for example, the selection is performed according to the sequence of point 1, point 2, point 3 and point 4, and collision detection is performed after each selection.

In step S2058, if there is an end point passing the collision detection, the end point is set as the intermediate point.

If the selected end point passes the collision detection, it is checked whether the area of the end point far from the side of the center line of the road is an empty area, for example, if the point 1 passes the collision detection, it is checked whether the area where the point 2 is located has enough space (the space size is set in the range from the inscribed circle to the circumscribed circle when the vehicle runs), and if the opposite side has enough space for assisting the turning. The point is taken as the middle point.

Step S2059, if there is no end point passing through the collision detection, gradually expanding the radius of the arc and adjusting the corresponding arc center angle, and performing the collision detection on the end point of the arc until the end point passing through the collision detection is selected as the middle point.

If none of the four selected endpoints passes the collision detection, each endpoint is adjusted in sequence, the radius of the arc is gradually enlarged until reaching the boundary of the map of the parking environment, and the arc center angle is alternately adjusted (e.g., increased for odd times and decreased for even times) until finding a middle point meeting the requirements, for example, in fig. 7, point 1 is taken as an example, and the arc center angle is gradually adjusted to point 1', point 1″ and so on.

Step S206, a path from the current position of the vehicle to the middle point and a path from the middle point to the target point are planned, and a parking path planning result is obtained.

Specifically, the step S206 includes:

in step S2061, the path from the current position of the vehicle to the intermediate point is planned by using an automatic path planning algorithm, and a first result linked list is obtained.

The automatic path planning algorithm is a pre-written program for automatic path planning.

That is, after the intermediate point is found, the path from the current position of the vehicle to the intermediate point and the path from the intermediate point to the target point may be used for parking path planning by a parking path planning method (automatic path planning algorithm) in the related art, and specifically, the path is selected according to the actual requirement, for example, hybridA x is selected for parking path planning.

The linked list is a discontinuous and non-sequential storage structure on a physical storage structure, the logic sequence of the data elements is realized through the pointer link sequence in the linked list, and the path result obtained through an automatic path planning algorithm is stored through the linked list in the scheme.

In step S2062, the path from the target point to the intermediate point is planned by using the automatic path planning algorithm with the target point as the starting point and the intermediate point as the end point, so as to obtain a second result linked list.

The vehicle runs from the target point to the intermediate point and the vehicle performs reversing and warehousing from the intermediate point to the target point to perform reverse movement, and when the parking path planning is performed, the path from the target point to the intermediate point is planned first.

Step S2063, the second result linked list is turned over, and the movement direction of the vehicle corresponding to the second result linked list is set to be the opposite direction, so as to obtain a third result linked list.

Because the parking is performed from the current position of the vehicle to the middle point and then reversing from the middle point to the target point, the second result linked list is reversed with the start and end pose of the second result linked list obtained in step 2062, and the driving direction of the vehicle is adjusted to be the opposite direction, so as to obtain the third result linked list.

Step S2064, the first result linked list and the third result linked list are linked to obtain a parking path planning result.

The first result linked list from the current position of the vehicle to the intermediate point and the third result linked list from the intermediate point to the target point are combined to obtain the planning result of the parking path from the current position of the vehicle to the target point, and the planning result of the parking path can be further subjected to smoothing treatment and the like.

The embodiment also provides a parking path planning device, which is used for implementing the above embodiment and the preferred implementation manner, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

The present embodiment provides a parking path planning apparatus, as shown in fig. 8, including:

The parking space determining module 801 is configured to determine a target parking space, where the target parking space includes a target point for referencing a pose of a vehicle after the vehicle is parked;

An information obtaining module 802, configured to obtain size information of a vehicle and lane obstacle position information of a side of the target parking space away from the vehicle;

a type determining module 803, configured to determine a parking path planning type of the vehicle based on the target parking space, size information of the vehicle, and a lane obstacle on a side of the target parking space away from the vehicle, where the parking path planning types are divided based on a location of the parking space and a surrounding environment, and each parking path planning type corresponds to a parking path;

The intermediate point selection module 804 is configured to select each candidate point based on the parking path planning type and perform collision detection respectively, so as to determine an intermediate point from the candidate points; the collision detection is used for detecting whether the vehicle can keep a safe distance with the obstacle in the process of parking based on the corresponding candidate point, and the middle point is a starting point which can park the vehicle to a target point and keeps the safe distance with the obstacle in the process;

The path planning module 805 is configured to plan a path from the current position of the vehicle to the intermediate point and a path from the intermediate point to the target point, so as to obtain a parking path planning result.

In one possible implementation manner, after determining the target parking space, the method further includes:

In one possible implementation manner, the determining the parking path planning type of the vehicle based on the target parking space, the size information of the vehicle, and the lane obstacle on the side of the target parking space away from the vehicle includes:

Judging whether the distance between a vehicle body and a lane barrier on one side of the target parking space, which is far away from the vehicle, is a safe distance or not when the vehicle exits from the target parking space with the minimum turning radius based on the parking environment map; the minimum turning radius is the minimum radius which can be reached when the vehicle turns;

If the vehicle is at the safe distance, determining the planning type of the parking path of the vehicle for parking to be a narrow lane.

In one possible implementation manner, the selecting each candidate point based on the parking path planning type and performing collision detection respectively to determine an intermediate point from the candidate points includes:

Performing collision detection based on the initial point;

if the collision detection passes, taking the initial point as a middle point;

if the collision detection does not pass, performing transverse adjustment or longitudinal adjustment on the lane central line by taking the initial point as a reference, selecting other candidate points and performing the collision detection respectively until the candidate points passing the collision detection are selected as intermediate points.

Judging whether the distance between a lane barrier on one side of the target parking space far away from the vehicle and the side of the target parking space exceeds the sum of the length of the vehicle and the minimum safety distance or not based on the parking environment map;

if the vehicle is not in excess, determining that the planning type of the parking path of the vehicle for parking is a broken road.

In one possible implementation manner, the planning the path from the current position of the vehicle to the intermediate point and the path from the intermediate point to the target point, to obtain a parking path planning result, includes:

Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.

The parking path planning apparatus in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application SPECIFIC INTEGRATED Circuit) Circuit, a processor and a memory that execute one or more software or firmware programs, and/or other devices that can provide the above functions.

The embodiment of the invention also provides a computer device which is provided with the parking path planning device shown in the figure 9.

Referring to fig. 9, fig. 9 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 9, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 9.

The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.

Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods shown in implementing the above embodiments.

The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.

The computer device further comprises input means 30 and output means 40. The processor 10, memory 20, input device 30, and output device 40 may be connected by a bus or other means, for example by a bus connection in fig. 9.

The input device 30 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointer stick, one or more mouse buttons, a trackball, a joystick, and the like. The output means 40 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. Such display devices include, but are not limited to, liquid crystal displays, light emitting diodes, displays and plasma displays. In some alternative implementations, the display device may be a touch screen.

The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.

Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.

Claims

1. A method of parking path planning, the method comprising:

Planning a path from the current position of the vehicle to the middle point and a path from the middle point to the target point to obtain a parking path planning result;

The determining a parking path planning type of the vehicle based on the target parking space, the size information of the vehicle and a lane obstacle on one side of the target parking space away from the vehicle comprises the following steps:

Judging whether the distance between a vehicle body and a lane barrier on one side of a target parking space far away from the vehicle is a safe distance or not when the vehicle exits from the target parking space with the minimum turning radius based on a parking environment map; the minimum turning radius is the minimum radius which can be reached when the vehicle turns; if the vehicle is at the safe distance, determining that the planning type of the parking path for parking the vehicle is a narrow lane;

Judging whether the distance between a lane barrier on one side of the target parking space far away from the vehicle and the side of the target parking space exceeds the sum of the length of the vehicle and the minimum safety distance or not based on a parking environment map; if the vehicle is not in excess, determining that the planning type of the parking path for parking the vehicle is a broken road.

2. The method of claim 1, further comprising, after determining the target parking space:

3. The method of claim 1, wherein the selecting each candidate point based on the parking path planning type and performing collision detection respectively to determine an intermediate point from the candidate points includes:

performing collision detection based on the initial point;

4. The method of claim 1, wherein the selecting each candidate point based on the parking path planning type and performing collision detection respectively to determine an intermediate point from the candidate points includes:

5. The method of claim 1, wherein the planning the path of the current position of the vehicle to the intermediate point and the path of the intermediate point to the target point to obtain a parking path planning result comprises:

6. A parking path planning apparatus, the apparatus comprising:

The path planning module is used for planning a path from the current position of the vehicle to the middle point and a path from the middle point to the target point to obtain a parking path planning result;

The type determination module is further configured to:

7. A computer device, comprising:

a memory and a processor in communication with each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the parking path planning method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the parking path planning method according to any one of claims 1 to 5.