CN116373851A - Automatic parking path planning method, automatic parking method and related device - Google Patents

Abstract

The present application discloses a path planning method for automatic parking, an automatic parking method, and related devices. The path planning method includes obtaining parking space information of a target parking space, and determining a parking segment and an adjustment segment based on the parking space information; The hybrid A* algorithm determines the first planned path corresponding to the parking section; the straight-line driving method is used to determine the second planned path corresponding to the adjustment section; the first planned path is connected to the second planned path to Form an automatic parking path. This application divides the parking path into a parking section and an adjustment section, uses a hybrid A* algorithm for path planning in the parking section, and uses a straight-line driving method for path planning in the adjustment section. The generated vehicle attitude error is adjusted, which reduces the requirements for control accuracy when the vehicle is parked, and can well guarantee the final attitude of the vehicle.

Description

A path planning method for automatic parking, an automatic parking method, and related devices

technical field

The present application relates to the technical field of automatic parking, in particular to a path planning method for automatic parking, an automatic parking method and related devices.

Background technique

In recent years, with the rapid development of the domestic automobile industry, automatic parking technology has become an indispensable function of vehicles. Automatic parking technology plans a feasible parking path based on vehicle pose and parking position, and then automatically controls the vehicle Follow the parking path to complete the park. Among them, parking path planning is the key link of automatic parking, and its basic requirement is that the planned path is feasible and safe without collision.

Existing parking path planning methods generally adopt the planning method of geometric curve splicing and the planning method of graph search (for example, hybrid A* search method), wherein, the planning method of using geometric curve splicing has a great impact on the working accuracy of sensors and actuators. The requirements are very high, and it is difficult to compensate the dynamic error of the system operation; using the graph search planning method, in the narrow and tortuous search space, it is difficult to guarantee the search efficiency and the optimality of the path.

Thereby prior art still needs to improve and improve.

Contents of the invention

The technical problem to be solved in the present application is to provide a route planning method for automatic parking, an automatic parking method and related devices in view of the deficiencies in the prior art.

In order to solve the above technical problems, the first aspect of the embodiment of the present application provides a path planning method for automatic parking, the method comprising:

Acquiring the parking space information of the target parking space, and determining the parking segment and the adjustment segment based on the parking space information;

Determining the first planned path corresponding to the parking segment by using a hybrid A* algorithm;

Determining the second planned path corresponding to the adjustment section by using a straight-line approach;

Connecting the first planned route and the second planned route to form an automatic parking route.

The path planning method for automatic parking, wherein the determining the first planned path corresponding to the parking segment through the hybrid A* algorithm specifically includes:

Use the starting position of the vehicle as the initial waypoint;

Obtaining the distance between the initial waypoint and the target parking space, and determining the heuristic function weight corresponding to the initial waypoint according to the distance;

Based on the weight of the heuristic function, search for the next path node of the initial path point in the search area corresponding to the vehicle through a hybrid A* algorithm;

Taking the next path node as an initial path point, and continuing to perform the step of obtaining the distance between the initial path point and the target parking space until the end point of the parking section to form a first planned path.

The path planning method for automatic parking, wherein the process of determining the search area specifically includes:

Determine an initial obstacle area and an initial parking space area corresponding to the target vehicle based on the parking space information, and expand the initial obstacle area outward to obtain a target obstacle area, and expand the initial parking space area inward to obtain a target parking space area;

A search area is determined based on the target obstacle area and the target parking space area.

The path planning method for automatic parking, wherein the determining the weight of the heuristic function corresponding to the initial path point according to the distance specifically includes:

comparing the distance with a first distance threshold and a second distance threshold, respectively;

If the distance is greater than a first distance threshold, setting the first preset weight as the heuristic function weight corresponding to the initial path point;

If the distance is less than or equal to the first distance threshold and greater than or equal to the second distance threshold, setting the second preset weight as the heuristic function weight corresponding to the initial path point;

If the distance is smaller than the second distance threshold, setting a third preset weight as the heuristic function weight corresponding to the initial path point, wherein the first preset weight is greater than the second preset weight, The second preset weight is greater than the third preset weight.

The path planning method for automatic parking, wherein the determining the parking segment and the adjustment segment based on the parking space information specifically includes:

Determine the parking point of the target parking space based on the parking space information, and select a target point before the parking point as a dividing point, wherein the dividing point and the parking point are located on the same straight line, and from The direction from the parking point to the dividing point is the front direction of the vehicle;

The road section between the starting point of the vehicle and the dividing point is used as a parking section, and the road section between the dividing point and the parking point is used as an adjustment section.

The second aspect of the embodiment of the present application provides an automatic parking method, using the parking path determined by the above-mentioned automatic parking path planning method; the method includes:

Taking the initial waypoint of the parking path as the previous driving moment, and controlling the vehicle to travel to the current driving moment of the previous driving moment;

Obtain the position of the candidate obstacle at the current driving time and the position of the newly added obstacle relative to the previous driving time;

Predicting the extended obstacle position corresponding to each newly added obstacle position, and determining the obstacle position corresponding to the current driving moment based on the candidate obstacle position and the extended obstacle position;

Adjusting the parking path based on the position of the obstacle, and continuing to execute the step of controlling the vehicle to travel to the current travel time at the previous travel time until the vehicle completes automatic parking.

The automatic parking method, wherein the adjusting the parking path based on the obstacle position specifically includes:

Detecting whether a collision occurs in the parking path based on the position of the obstacle;

If the parking path collides, replan the parking path to adjust the parking path;

If the parking path does not collide, the parking path remains unchanged.

The automatic parking method, wherein the acquisition of the position of the candidate obstacle at the current driving moment specifically includes:

Detect the location of suspicious obstacles corresponding to the current driving moment through the sensors configured on the vehicle;

For each suspicious obstacle position, obtain the observation probability corresponding to the suspicious obstacle position and the prior probability corresponding to the suspicious obstacle position when the vehicle is in the previous driving moment;

calculating a posterior probability corresponding to the position of the suspicious obstacle based on the observation probability and the prior probability;

If the posterior probability is greater than a preset probability threshold, the suspicious obstacle position is used as a candidate obstacle position.

In the automatic parking method, the predicting the position of the extended obstacle corresponding to the position of each newly added obstacle specifically includes:

Acquiring the center position of the previous obstacle corresponding to the previous driving time and the current center position of the obstacle corresponding to the current driving time, and using the direction from the center position of the previous obstacle to the center position of the current obstacle as the extension direction;

For each newly added obstacle position, the estimated extension probability of each extended position within the preset range is predicted along the extended direction, and the extended position with the estimated extended probability greater than the preset probability value is used as the extended obstacle position.

The third aspect of the embodiment of the present application provides a path planning device for automatic parking, and the path planning device includes:

An acquisition module, configured to acquire the parking space information of the target parking space, and determine the parking segment and the adjustment segment based on the parking space information;

A first determination module, configured to determine the first planned path corresponding to the parking segment through a hybrid A* algorithm;

The second determination module is used to determine the second planned path corresponding to the adjustment section by adopting a straight-line approach;

A forming module, configured to connect the first planned route with the second planned route to form an automatic parking route.

The fourth aspect of the embodiment of the present application provides an automatic parking device, using the parking path determined by the above-mentioned automatic parking path planning device; the device includes:

A control module, controlling the vehicle to drive according to the parking route, and obtaining the position of the candidate obstacle at the current driving time and the position of the newly added obstacle at the current driving time relative to the previous driving time;

A prediction module, configured to predict the extended obstacle position corresponding to each newly added obstacle position, and determine the obstacle position corresponding to the current driving moment based on the candidate obstacle position and the extended obstacle position;

An adjustment module, configured to adjust the parking path based on the position of the obstacle, and continue to execute the step of controlling the vehicle to travel along the parking path until the vehicle completes automatic parking. The fifth aspect of the embodiment of the present application provides a computer-readable storage medium, which is characterized in that the computer-readable storage medium stores one or more programs, and the one or more programs can be processed by one or more The controller is executed to realize the steps in the above-mentioned automatic parking route planning method, and/or to realize the above-mentioned steps in the automatic parking method.

The third aspect of the embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to Realize the steps in the path planning method and automatic parking method for automatic parking as described above.

The sixth aspect of the embodiment of the present application provides a terminal device, including: a processor, a memory, and a communication bus; a computer-readable program executable by the processor is stored in the memory;

The communication bus realizes connection and communication between the processor and the memory;

When the processor executes the computer-readable program, the steps in the path planning method for automatic parking according to any one of claims 1-5 are realized, and/or the steps in any one of claims 6-9 are realized. The steps in the automatic parking method described above.

Beneficial effects: Compared with the prior art, the present application provides a path planning method for automatic parking, an automatic parking method and related devices. The path planning method includes obtaining the parking space information of the target parking space, and based on the parking space information to determine the parking section and the adjustment section; determine the first planned path corresponding to the parking section by a hybrid A* algorithm; determine the second planned path corresponding to the adjustment section by using a straight-line driving method; The path is connected with the second planned path to form an automatic parking path. This application divides the parking path into a parking section and an adjustment section, uses a hybrid A* algorithm for path planning in the parking section, and uses a straight-line driving method for path planning in the adjustment section. The generated vehicle attitude error is adjusted, which reduces the requirements for control accuracy when the vehicle is parked, and can well guarantee the final attitude of the vehicle.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can also be obtained based on these drawings under the premise of not conforming to creative work.

FIG. 1 is a flow chart of the route planning method for automatic parking provided by the present application.

Figure 2 is a schematic diagram of the parking space.

Fig. 3 is the curve of the parking attitude change of the lateral parking space.

Fig. 4 is a curve of the attitude change of the parking space in the rear direction.

Fig. 5 is a schematic diagram of the parking section.

FIG. 6 is a schematic diagram of a parking path.

Fig. 7 is a schematic diagram of an initial obstacle area.

Fig. 8 is a polygonal schematic diagram of the feasible region of the parking lane.

FIG. 9 is a schematic diagram of a target obstacle area.

FIG. 10 is a schematic flowchart of a path planning method for automatic parking.

Fig. 11 is a flow chart of the automatic parking method provided by the present application.

Fig. 12 is a schematic flowchart of the automatic parking method provided by the present application.

Fig. 13 is a schematic diagram of the parameters of the ultrasonic sensor.

Fig. 14 is a schematic diagram of obstacle distribution at the previous driving moment.

Fig. 15 is a schematic diagram of the distribution of candidate obstacles at the current driving moment.

Fig. 16 is a schematic diagram of obstacle distribution at the current driving moment.

FIG. 17 is a structural schematic diagram of a path planning device for automatic parking provided by the present application.

FIG. 18 is a structural schematic diagram of the automatic parking device provided by the present application.

FIG. 19 is a structural schematic diagram of a terminal device provided by the present application.

Detailed ways

This application provides a path planning method for automatic parking, an automatic parking method and related devices. In order to make the purpose, technical solution and effect of this application clearer and clearer, the application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

Those skilled in the art will understand that unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the word "comprising" used in the specification of the present application refers to the presence of said features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Additionally, "connected" or "coupled" as used herein may include wireless connection or wireless coupling. The expression "and/or" used herein includes all or any elements and all combinations of one or more associated listed items.

Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have meanings consistent with their meaning in the context of the prior art, and unless specifically defined as herein, are not intended to be idealized or overly Formal meaning to explain.

It should be understood that the sequence numbers and sizes of the steps in this embodiment do not imply the order of execution, and the execution order of each process is determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

After research, it is found that in recent years, with the rapid development of the domestic automobile industry, automatic parking technology has become an indispensable function of vehicles. Then the vehicle is automatically controlled to follow the parking path to complete parking. Among them, parking path planning is the key link of automatic parking, and its basic requirement is that the planned path is feasible and safe without collision.

Existing parking path planning methods generally adopt the planning method of geometric curve splicing and the planning method of graph search (for example, hybrid A* search method), wherein, the planning method of adopting geometric curve splicing is to adopt the method of multi-segment curve splicing to solve When planning the path, if the posture at the storage point is not ideal, there are errors in the vehicle storage control process, and obstacles appear, the solution for the storage section route may not have an analytical solution and the route is not optimal, and it is difficult to guarantee the final vehicle body. attitude. The hybrid A* search method is used to determine the optimal planning path based on the starting point, ending point and obstacle position information. However, due to the left and right restrictions on vertical parking spaces and the front and rear restrictions on side parking spaces, the parking end point is in a narrow search space closed in three directions. , the search efficiency and the optimality of the path are difficult to guarantee, and when obstacles appear, the search algorithm may not be able to find a feasible path. And because the search domain and the detection domain are the same, frequent re-planning occurs in dynamic obstacle scenarios.

In addition, in the process of using the hybrid A* search method, part of the path planning method divides the route into two sections: forward driving and reverse parking. The two sections use different heuristic function weights during the hybrid A* search, but the parking section uses The hybrid A* search requires high control accuracy when the vehicle is parked, and it is difficult to guarantee the final attitude.

In order to solve the above problems, in the embodiment of the present application, the parking space information of the target parking space is obtained, and the parking segment and the adjustment segment are determined based on the parking space information; the first planned path corresponding to the parking segment is determined by a hybrid A* algorithm ; Determine the second planned route corresponding to the adjustment section by using a straight-line approach; connect the first planned route with the second planned route to form an automatic parking route. This application divides the parking path into a parking section and an adjustment section, uses a hybrid A* algorithm for path planning in the parking section, and uses a straight-line driving method for path planning in the adjustment section. The generated vehicle attitude error is adjusted, which reduces the requirements for control accuracy when the vehicle is parked, and can well guarantee the final attitude of the vehicle.

The content of the application will be further explained by describing the embodiments below in conjunction with the accompanying drawings.

This embodiment provides a path planning method for automatic parking, as shown in Figure 1, the method includes:

S10. Acquire parking space information of a target parking space, and determine a parking segment and an adjustment segment based on the parking space information.

Specifically, the parking space information includes vehicle information, parking space geometric information, and obstacle information, wherein the vehicle information may include vehicle model and vehicle location, and the parking space geometric information may include parking space length, parking space width, parking space slope, safety distance, and lane width, The obstacle information may include front and rear car position information, left and right car position information, and obstacle information inside the parking space (for example, car stoppers, guardrails, etc.). Wherein, the vehicle information can be determined according to the positioning device carried by the vehicle itself, the geometric information of the parking space can be obtained through an ultrasonic sensor or an image acquisition device, and the obstacle information can also be obtained through an ultrasonic sensor or an image acquisition device. In addition, when the obstacle information inside the parking space is not obtained, the parking lot design specification standard information can be used.

The parking section and the adjustment section are two components of the parking path. The parking section and the adjustment section are connected, wherein the adjustment section is used to adjust the vehicle passing through the parking section to maintain the final attitude of the vehicle. It can be understood that when planning the parking path, the parking path is divided into a parking section and an adjustment section. When the vehicle is automatically parked according to the parking path, it first passes through the parking section and then passes through the adjustment section to complete Automatic parking.

In an implementation manner, determining the parking segment and the adjustment segment based on the parking space information specifically includes:

S11. Determine the parking point of the target parking space based on the parking space information, and select a target point before the parking point as a dividing point;

S12. Use the road section between the starting point of the vehicle and the dividing point as a parking section, and use the road section between the dividing point and the parking point as an adjustment section.

Specifically, as shown in FIG. 2 , the dividing point and the parking point are located on the same straight line, and the direction from the parking point to the dividing point is the front direction of the vehicle. That is to say, a division point is set at a predetermined distance forward in the direction of the front of the vehicle, the road section between the starting point of the vehicle and the division point is used as the parking section, and the road section between the division point and the parking point is used as the adjustment section, that is, the division point is The split point between the parking segment and the adjustment segment.

As shown in FIG. 2 , the parking spaces include side parking spaces, vertical parking spaces and inclined parking spaces, wherein different parking spaces can reserve different positions with the front facing forward. Thus, when determining the parking point of the target parking space based on the parking space information, the parking space type can be determined based on the parking space information, and the adjustment distance corresponding to the parking space type can be selected; the division point is determined based on the adjustment distance, so that the division point The distance to the parking point is equal to the adjustment distance, so that the adjustment section can be determined, and the vehicle can avoid collisions when the vehicle passes the parking section and travels to the dividing point or cannot plan the first planned path corresponding to the parking section. Wherein, the types of parking spaces include lateral parking spaces and backward parking spaces, side parking spaces may include side parking spaces, and rear parking spaces may include vertical parking spaces and inclined parking spaces.

Further, the adjustment distances corresponding to different types of parking spaces may be different. For lateral parking spaces, as shown in Figure 3, the larger the adjustment distance, the better the parking posture. However, as the adjustment distance increases, the parking space becomes smaller. , thus affecting the planning of the first planning path and may even result in the inability to solve the first planning path. Therefore, for lateral parking spaces, the adjustment distance is determined based on a first preset condition, wherein the first preset condition is preset, for example, the first preset condition is that the adjustment distance is less than a preset distance threshold, wherein the preset The distance threshold is determined based on the length of the parking space, for example, the preset distance threshold is equal to one-fifth of the length of the parking space. In addition, in practical applications, in order to increase the path planning speed, the adjusted distance can be a preset value, for example, the adjusted distance is 0.4m.

For the rear-facing parking spaces, as shown in Figure 4, the larger the adjustment distance, the better the parking posture. Increased requirements on lane domains and inability to solve planned paths when lanes are not wide enough. Thus, for a rearward parking space, the adjustment distance can be determined based on a second preset condition, wherein the second preset condition is preset, for example, the second preset condition is that the adjustment distance is less than the first distance threshold and greater than The second distance threshold, wherein the first distance threshold is greater than the second distance threshold, and both the first distance threshold and the second distance threshold are determined based on the length of the parking space, such as, the first distance is equal to the length of the parking space, and the second distance threshold is five times the length of the parking space One-third and so on. In practical applications, in order to increase the path planning speed, the adjusted distance may be a preset value, for example, the adjusted distance is 4m.

S20. Determine a first planned path corresponding to the parking segment by using a hybrid A* algorithm.

Specifically, the hybrid A* algorithm is used to solve the path search problem under the constraint of the movement of the parking space. The hybrid A* algorithm can be used to solve the first planned path of the parking section, wherein, as shown in Figure 5, the first planned path is a curve For the path, the starting point of the vehicle is the starting point of the first planned route, and the division point is the ending point of the first planned route. Summarized in the search process of the hybrid A* algorithm, the sum of the moving cost and the heuristic function is used as the search basis, and the search domain is searched based on the search basis to form the first planned path.

Because the heuristic function in the hybrid A* algorithm generally uses the RS curve to measure the distance from the current point to the target point, and the heuristic function plays the same role regardless of the distance between the current point and the target point, which will affect the path planning efficiency. Based on this, in an implementation manner, the determining the first planned path corresponding to the parking segment through the hybrid A* algorithm specifically includes:

S21. Taking the starting position of the vehicle as the initial waypoint;

S22. Obtain the distance between the initial waypoint and the target parking space, and determine the heuristic function weight corresponding to the initial waypoint according to the distance;

S23. Based on the weight of the heuristic function, search for the next path node of the initial path point in the search area corresponding to the vehicle through the hybrid A* algorithm;

S24. Use the next path node as an initial path point, and continue to execute the step of obtaining the distance between the initial path point and the target parking space until the end point of the parking section to form a first planned path.

Specifically, the distance between the initial waypoint and the target parking space refers to the distance between the initial waypoint and the parking point of the target parking space, which is used to reflect the relative distance between the vehicle and the target parking space. The farther the distance from the target parking space is, on the contrary, the smaller the distance is, the closer the vehicle is to the target parking space. Among them, when the distance between the vehicle and the target parking space is large, a large heuristic function weight can be set to increase the proportion of the heuristic function to improve the search speed; when the distance between the vehicle and the target parking space is small, a small heuristic function weight can be set to reduce the search speed. The proportion of the function is used to determine the optimal path. Although the optimal route to the front-end path can be sacrificed, the front-end path of parking is generally based on fast passing, so the impact of the optimal path can be ignored, and the reduction in the rear pass The proportion of the heuristic function can obtain the optimal path. By driving according to the optimal path in the later stage and adjusting the vehicle attitude in the adjustment stage, a good posture can be ensured when the vehicle parks in the target parking space, which can improve the automatic parking The speed of the vehicle can also make the vehicle maintain a good final attitude.

In an implementation manner, the determining the weight of the heuristic function corresponding to the initial path point according to the distance specifically includes:

comparing the distance with a first distance threshold and a second distance threshold, respectively;

If the distance is greater than a first distance threshold, setting the first preset weight as the heuristic function weight corresponding to the initial path point;

If the distance is less than or equal to the first distance threshold and greater than or equal to the second distance threshold, setting the second preset weight as the heuristic function weight corresponding to the initial path point;

If the distance is smaller than the second distance threshold, a third preset weight is set as the heuristic function weight corresponding to the initial path point.

Specifically, both the first distance threshold and the second distance threshold are preset, and as a basis for determining the weight of the heuristic function, the first distance threshold is smaller than the second distance threshold. The first preset weight, the second preset weight and the third preset weight are all preset, the first preset weight is greater than the second preset weight, and the second preset weight is greater than the first preset weight Three preset weights, so that when the distance is greater than the first distance threshold, the largest heuristic function weight is used to achieve the purpose of fast search; when the distance is less than or equal to the first distance threshold and greater than the second distance threshold, the middle one is used Heuristic function weight, to seek the optimal path while ensuring the search speed; when the distance is less than or equal to the second distance threshold, use the smallest heuristic function weight, increase the attention to the movement cost, and ensure that the end of the parking segment can be searched to the end Parking path, so as to ensure the vehicle attitude after the parking segment is completed.

Based on this, the search objective function of the hybrid A* algorithm can be expressed as:

Among them, f(N) represents the search objective function, g(N) represents the moving cost, h(N) represents the heuristic function, w ₁ , w ₂ , and w ₃ represent the weight of the heuristic function, N represents the search position, and M represents the parking Position, D ₁ , D ₂ , D ₃ all represent distance thresholds.

Further, the process of determining the search area specifically includes:

Determine an initial obstacle area and an initial parking space area corresponding to the target vehicle based on the parking space information, and expand the initial obstacle area outward to obtain a target obstacle area, and expand the initial parking space area inward to obtain a target parking space area;

A search area is determined based on the target obstacle area and the target parking space area.

Specifically, the initial obstacle area is an area formed by obstacles corresponding to the target parking space, which can be obtained when collecting the parking space information, for example, through an ultrasonic sensor or an image acquisition device of the vehicle device. The target obstacle area is obtained by expanding the initial obstacle area outward, and the target obstacle area includes the initial obstacle area. The expansion refers to expanding the initial obstacle area, for example, the initial obstacle area as shown in FIG. 6 is expanded to obtain the target obstacle area as shown in FIG. 7 . The expansion can be realized by expanding the initial obstacle area outward by a preset distance, or by expanding the area range of the initial obstacle area by a preset multiple, etc.

After the target obstacle area is obtained, the geometric information of the parking space included in the parking space information is converted into a polygonal area of the feasible area of the parking space lane, wherein the polygonal area includes the initial parking space area and the lane area, for example, the parking space lane as described in Figure 8 Feasible domain. After the initial parking space area, the parking space area expands inward to narrow the parking space area to obtain the target parking space area, and then removes the overlapping part of the target multi-deformation area formed by the target parking space area and the lane area and the target obstacle area to obtain the search area. This implementation method reserves the movement area for obstacles by expanding the obstacle area outward and the parking area inward, which can avoid frequent re-planning caused by obstacle movement, detection blind area and obstacle position error The problem of the path improves the parking efficiency of automatic parking.

S30. Determine the second planned route corresponding to the adjustment section by using a straight-line approach.

Specifically, the starting point of the adjustment section is located directly in front of the end point of the adjustment section, as shown in Figure 9, the second planning path can be planned directly by using a straight-line driving method, and the speed gradient descent method is adopted in the adjustment section to The approaching movement of the terminal line can eliminate attitude errors and reduce the attitude accuracy requirements for the parking entry point.

S40. Connect the first planned route with the second planned route to form an automatic parking route.

Specifically, after the first planned path and the second planned path are obtained, the first planned path and the second planned path are connected, that is, the end point of the first planned path is merged with the starting point of the second planned path to obtain an automatic parking path. In addition, as shown in Figure 10, after the parking path is obtained, it can also be detected whether the parking path will collide with obstacles. If there is a collision, the path will be re-planned. The gradient is smoothed and the parking path is published.

In summary, this embodiment is a path planning method for automatic parking, the path planning method includes obtaining the parking space information of the target parking space, and determining the parking segment and the adjustment segment based on the parking space information; through the hybrid A* algorithm Determining the first planned path corresponding to the parking section; determining the second planned path corresponding to the adjustment section by using a straight-line driving method; connecting the first planned path with the second planned path to form automatic parking path. This application divides the parking path into a parking section and an adjustment section, uses a hybrid A* algorithm for path planning in the parking section, and uses a straight-line driving method for path planning in the adjustment section. The generated vehicle attitude error is adjusted, which reduces the requirements for control accuracy when the vehicle is parked, and can well guarantee the final attitude of the vehicle.

Based on the above-mentioned path planning method for automatic parking, this embodiment provides an automatic parking method, which applies the parking path determined by the above-mentioned path planning method for automatic parking; as shown in Figures 11 and 12, the method includes :

H10. Control the vehicle to drive according to the parking route, and obtain the position of the candidate obstacle at the current driving time and the position of the newly added obstacle at the current driving time relative to the previous driving time.

Specifically, the position of the candidate obstacle is detected when the vehicle is driving to the current driving moment, and the newly added obstacle position is the position of the candidate obstacle detected by the vehicle at the current driving moment relative to the previous position detected by the vehicle at the previous driving moment. The newly added obstacle position, that is, the newly added obstacle position is included in the candidate obstacle position, but not included in the previous obstacle position.

In an implementation manner, the obtaining the position of the obstacle candidate at the current driving moment specifically includes:

H21. Detect the position of the suspicious obstacle corresponding to the current driving time through the sensor configured in the vehicle;

H22. For each suspicious obstacle position, obtain the observation probability corresponding to the suspicious obstacle position and the prior probability corresponding to the suspicious obstacle position when the vehicle is in the previous driving moment;

H23. Calculate the posterior probability corresponding to the position of the suspicious obstacle based on the observation probability and the prior probability;

H24. If the posterior probability is greater than a preset probability threshold, use the suspicious obstacle position as a candidate obstacle position.

Specifically, the vehicle is equipped with several ultrasonic sensors, each of which is independent of each other, and can detect the position of a suspicious obstacle according to the beam angle and obstacle distance. That is to say, the transmitter of each ultrasonic sensor emits ultrasonic waves, and records the emission time of the emitted waves, so that the ultrasonic waves will be reflected when they meet obstacles, so that the receiver of the ultrasonic sensor receives the reflected waves, through the time of receiving the reflected waves, The emission time of the transmitted wave and the transmission rate of the light wave are used as the ultrasonic distance data, and the vehicle terminal can obtain the position of the obstacle relative to the vehicle according to the ultrasonic distance data, the driving speed of the vehicle, and the like.

The vehicle is equipped with several ultrasonic sensors, and each ultrasonic sensor can detect several suspicious obstacle positions, so that the suspicious obstacle positions corresponding to the current driving time include the suspicious obstacle positions collected by the sensors configured in the vehicle, for example, the vehicle includes ultrasonic sensor 1 , ultrasonic sensor 2 , .

Further, after obtaining the position of the suspicious obstacle corresponding to the current driving time, the positions of each suspicious obstacle can be combined and transformed into the map coordinate system to form an obstacle probability map, wherein the obstacle probability map includes the current driving time at All suspicious obstacle locations and probabilities in the map coordinate system. After merging and transforming the positions of each suspicious obstacle into the map coordinate system, under the detection parameters of the ultrasonic sensor as shown in Figure 13, the calculation formula of the observation probability can be:

Among them, a represents the distance between the position of the suspicious obstacle and the ultrasonic sensor, b represents the deflection angle between the position of the suspicious obstacle and the central axis of the ultrasonic sensor, s represents the measured value of the distance returned by the ultrasonic sensor, w represents the beam angle of the ultrasonic sensor, ds=0.2 ×s represents the credible half-width of the ultrasonic sensor model. When the point k(x, y) is not within the credible half-width range of the model, the probability of an obstacle is regarded as 0.

Based on the Bayesian principle, the posterior probability of a suspicious obstacle location can be determined based on the observation probability of the suspicious obstacle location and the prior probability of the previous driving moment, that is, when a suspicious obstacle location appears in the ultrasonic obstacle possible area , it will not be judged as an obstacle immediately, but will be regarded as the obstacle position when the position of the suspicious obstacle is continuously judged as an obstacle for a continuous period of time. In this way, using the probability to represent the occurrence event of an obstacle can be Improve the accuracy of obstacle detection and avoid the measurement error of traditional ultrasonic sensors, for example, avoid the problem that the vehicle has no way to go due to using all possible areas within the beam angle range as the obstacle position, or avoid the problem of using Two ultrasonic data in adjacent positions are used to determine the location of the obstacle. The judgment logic is that when both ultrasonic sensors detect an obstacle, it is considered that the obstacle appears in the overlapping area of the detection range of the two ultrasonic sensors. Two smaller obstacles, obstacle 1 appears in the left half of the detection range of the left ultrasonic sensor, obstacle 2 appears in the right half of the detection range of the right ultrasonic sensor, and it is wrongly judged that only one obstacle appears in the left and right ultrasonic sensors Problems with overlapping areas of sensors.

In an implementation, the calculation process of the posterior probability of the location of the suspicious obstacle may be:

基于此，超声传感器i测量下点k(x,y)在t时刻存在障碍物，且被正确检测到的后验概率T_i(t,k)，其中，T_i(t,k)的计算公式可以为：Let k(x, y) be the event that actually has an obstacle as A, and the event that k(x, y) is detected as having an obstacle at this moment is B, then according to the conditional probability, P(B|A)= P(A|B)P(B)/P(A), can be obtained from the total probability formula

Based on this, ultrasonic sensor i measures the posterior probability T i (t, k) that there is an obstacle at point k (x, y) at time t and is correctly detected, where the calculation of _{T i (} t, k) The formula can be:

P(O)=P(t,k)×T(t-1,k)

Among them, T _i (t, k) represents the posterior probability, T(T-1, k) represents the prior probability, and P(t, k) represents the observation probability.

Further, after obtaining the posterior probability T _i (t, k) of each ultrasonic sensor, the maximum value of each posterior probability T _i (t, k) is used as the posterior probability of the suspicious obstacle position, where the posterior The formula for calculating the test probability can be:

Among them, N represents the number of ultrasonic sensors.

H20. Predict the position of the extended obstacle corresponding to each newly added obstacle position, and determine the position of the obstacle corresponding to the current driving moment based on the position of the candidate obstacle and the position of the extended obstacle.

Specifically, the extended obstacle position is the position determined by the extension of the new obstacle position according to the preset direction, where the preset direction can be preset, or it can be based on the obstacle information corresponding to the previous driving time and the current driving time. The obstacle information corresponding to the time is determined. In this embodiment, by obtaining the extended obstacle position of each newly added obstacle position, it can solve the phenomenon that large obstacles appear, the sensor cannot see the whole picture at a certain moment, and as the vehicle continues to move, obstacles will appear continuously.

In an implementation manner, the predicting the position of the extended obstacle corresponding to the position of each newly added obstacle specifically includes:

Acquiring the center position of the previous obstacle corresponding to the previous driving time and the current center position of the obstacle corresponding to the current driving time, and using the direction from the center position of the previous obstacle to the center position of the current obstacle as the extension direction;

For each newly added obstacle position, the estimated extension probability of each extended position within the preset range is predicted along the extended direction, and the extended position with the estimated extended probability greater than the preset probability value is used as the extended obstacle position.

Specifically, the obstacle distribution map obtained by Bayesian estimation at the previous driving moment can be shown in Figure 14, where the darker the color, the higher the probability, and the cross arrow indicates the center position of the obstacle at time t-1. The obstacle distribution diagram obtained through Bayesian estimation at the current driving moment can be shown in FIG. 15 , where the center position of the obstacle indicated by the circular cross moves to the right. Thus, the extending direction is the direction of the line connecting the cross arrow at the previous driving time to the circular cross at the current driving time. In other words, the extension direction is a direction from the center position of the previous obstacle to the center position of the current obstacle.

After the extension direction is obtained, the extension estimation probability of each extension position within the preset range is predicted along the extension direction, wherein the extension estimation probability can be expressed as:

Among them, g represents the probability calculation formula of the predicted point j, the posterior probability T(t,k) of the newly added obstacle position k, the distance d between the newly added obstacle position k and the predicted point j, and ds represents the preset distance threshold.

After the candidate obstacle position and the extended obstacle position are obtained, the obstacle area formed by the candidate obstacle position and the extended obstacle position is used as the obstacle position corresponding to the current driving moment, as shown in FIG. 16 .

H30. Adjust the parking path based on the position of the obstacle, and continue to execute the step of controlling the vehicle to travel along the parking path until the vehicle completes automatic parking.

Specifically, after obtaining the position of the obstacle, it may be detected based on the position of the obstacle whether a collision occurs in the parking path, so as to avoid a collision during automatic parking. Wherein, when detecting whether the parking path collides based on the position of the obstacle, if the parking path collides, replan the parking path to adjust the parking path; if the parking path does not If a collision occurs, the parking path remains unchanged. In addition, when re-planning the parking route, the route planning method for automatic parking provided in the above-mentioned embodiments can be used for re-routing planning, or other existing methods can be used for route planning, for example, directly using the hybrid A* algorithm Perform path planning, etc.

In this embodiment, when Bayesian estimation is used to predict obstacles, the original ultrasonic data and prior experience at the previous moment are used to estimate obstacles, which can improve the accuracy of obstacle estimation. At the same time, when estimating the obstacle, the possible position of the obstacle is predicted in its growth direction according to the change of the obstacle position at the previous moment as the prediction basis. In this way, on the one hand, when the vehicle is gradually approaching the obstacle during the moving process, the real obstacle position is finally determined to be an obstacle rather than the obstacle position after continuous estimation iterations. During the iteration process, the estimation threshold cannot be satisfied, although a certain These moments are contained within the detection range of ultrasonic waves, but will not be considered as obstacles. The estimation accuracy of the obstacle position is improved, which in turn allows the vehicle to have more driving space in autonomous parking. On the other hand, the change of obstacles at adjacent moments is used as the prediction basis. Compared with the existing method of predicting obstacles in the entire ultrasonic detection area, the prediction is made in the direction of the growth of the obstacle, and the basis of the prediction is the previous step. The more realistic obstacle distribution probability obtained by Bayesian calculation makes the prediction result more reasonable and can reduce the estimated blind area caused by the obstacle size exceeding the detection range.

Based on the above path planning method for automatic parking, this embodiment adopts a path planning device for automatic parking, as shown in Figure 17, the path planning device includes:

An acquisition module 101, configured to acquire parking space information of a target parking space, and determine a parking segment and an adjustment segment based on the parking space information;

The first determination module 102 is configured to determine the first planned path corresponding to the parking segment through a hybrid A* algorithm;

The second determination module 103 is configured to determine the second planned path corresponding to the adjustment section in a straight-line approach;

The forming module 104 is configured to connect the first planned route and the second planned route to form an automatic parking route.

Based on the above automatic parking method, this embodiment provides an automatic parking device, as shown in Figure 18, the device includes:

The control module 201 controls the vehicle to drive according to the parking route, and obtains the position of the candidate obstacle at the current driving time and the position of the newly added obstacle at the current driving time relative to the previous driving time;

A prediction module 202, configured to predict the extended obstacle position corresponding to each newly added obstacle position, and determine the obstacle position corresponding to the current driving moment based on the candidate obstacle position and the extended obstacle position;

The adjustment module 203 is configured to adjust the parking path based on the position of the obstacle, and continue to execute the step of controlling the vehicle to follow the parking path until the vehicle completes automatic parking.

This embodiment provides a computer-readable storage medium, where one or more programs are stored in the computer-readable storage medium, and the one or more programs can be executed by one or more processors to implement the above-mentioned implementation The path planning method for automatic parking described in the example and/or the steps in the automatic parking method.

The present application also provides a terminal device, as shown in FIG. 19 , which includes at least one processor (processor) 20; a display screen 21; and a memory (memory) 22, and may also include a communication interface (Communications Interface) 23 and a bus twenty four. Wherein, the processor 20 , the display screen 21 , the memory 22 and the communication interface 23 can communicate with each other through the bus 24 . The display screen 21 is configured to display the preset user guidance interface in the initial setting mode. The communication interface 23 can transmit information. The processor 20 can invoke logic instructions in the memory 22 to execute the methods in the above-mentioned embodiments.

In addition, the above-mentioned logic instructions in the memory 22 may be implemented in the form of software functional units and when sold or used as an independent product, may be stored in a computer-readable storage medium.

As a computer-readable storage medium, the memory 22 can be configured to store software programs and computer-executable programs, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 20 runs software programs, instructions or modules stored in the memory 22 to execute functional applications and data processing, ie to implement the methods in the above-mentioned embodiments.

The memory 22 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required by a function; the data storage area may store data created according to the use of the terminal device, and the like. In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory. For example, U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes can also be temporary state storage medium.

In addition, the specific process of loading and executing multiple instruction processors in the storage medium and the terminal device has been described in detail in the above method, and will not be described here one by one.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims (13)

1. A method for path planning for automatic parking, the method comprising:

acquiring parking space information of a target parking space, and determining a parking section and an adjusting section based on the parking space information;

determining a first planning path corresponding to the parking section through a mixed A-algorithm;

determining a second planning path corresponding to the adjusting section in a straight-line driving-in mode;

and connecting the first planned path and the second planned path to form an automatic parking path.

2. The method for planning a path for automatic parking according to claim 1, wherein the determining, by using a hybrid a-x algorithm, the first planned path corresponding to the parking segment specifically includes:

taking the starting position of the vehicle as an initial path point;

acquiring the distance between the initial path point and the target parking space, and determining heuristic function weights corresponding to the initial path point according to the distance;

searching a next path node of an initial path point in a search area corresponding to the vehicle through a mixed A algorithm based on the heuristic function weight;

and taking the next path node as an initial path point, and continuously executing the step of acquiring the distance between the initial path point and the target parking space until the end point of the parking section is reached to form a first planning path.

3. The automatic parking path planning method according to claim 2, wherein the determining process of the search area specifically includes:

determining an initial obstacle area and an initial parking space area corresponding to a target vehicle based on the parking space information, expanding the initial obstacle area outwards to obtain a target obstacle area, and expanding the initial parking space area inwards to obtain a target parking space area;

And determining a search area based on the target obstacle area and the target parking space area.

4. The method for planning a path for automatic parking according to claim 2, wherein determining the heuristic function weight corresponding to the initial path point according to the distance specifically comprises:

comparing the distance with a first distance threshold and a second distance threshold, respectively;

if the distance is greater than a first distance threshold, setting a first preset weight as a heuristic function weight corresponding to the initial path point;

if the distance is smaller than or equal to a first distance threshold and larger than or equal to a second distance threshold, setting a second preset weight as a heuristic function weight corresponding to the initial path point;

and if the distance is smaller than the second distance threshold, setting a third preset weight as a heuristic function weight corresponding to the initial path point, wherein the first preset weight is larger than the second preset weight, and the second preset weight is larger than the third preset weight.

5. The method for planning a path for automatic parking according to claim 1, wherein the determining the parking section and the adjustment section based on the parking space information specifically includes:

Determining a parking point of the target parking space based on the parking space information, and selecting a target point in front of the parking point as a dividing point, wherein the dividing point and the parking point are on the same straight line, and the direction from the parking point to the dividing point is the head direction of a vehicle;

taking a road section between a vehicle starting point and the dividing point as a parking section, and taking a road section between the dividing point and the parking point as an adjusting section.

6. An automatic parking method, characterized by applying the parking path determined by the path planning method for automatic parking according to any one of claims 1 to 5; the method comprises the following steps:

controlling the vehicle to run according to the parking path, and acquiring candidate obstacle positions at the current running time and newly-increased obstacle positions at the current running time relative to the previous running time;

predicting extended obstacle positions corresponding to the newly added obstacle positions, and determining the obstacle positions corresponding to the current running time based on the candidate obstacle positions and the extended obstacle positions;

and adjusting the parking path based on the obstacle position, and continuously executing the step of controlling the vehicle to run according to the parking path until the vehicle finishes automatic parking.

7. The automatic parking method of claim 6, wherein the adjusting the parking path based on the obstacle location specifically comprises:

detecting whether a collision of the parking path occurs based on the obstacle position;

if the parking path collides, re-planning the parking path to adjust the parking path;

and if the parking path is not collided, keeping the parking path unchanged.

8. The automatic parking method according to claim 6, wherein the obtaining the candidate obstacle position at the current driving time specifically includes:

detecting the position of a suspicious obstacle corresponding to the current running time through a sensor configured by the vehicle;

for each suspicious obstacle position, obtaining an observation probability corresponding to the suspicious obstacle position and a priori probability corresponding to the suspicious obstacle position when the vehicle is at a previous driving moment;

calculating posterior probability corresponding to the suspicious obstacle position based on the observation probability and the prior probability;

and if the posterior probability is greater than a preset probability threshold, taking the suspicious obstacle position as a candidate obstacle position.

9. The automatic parking method according to claim 6, wherein predicting the extended obstacle position corresponding to each newly added obstacle position specifically includes:

Acquiring a preamble obstacle center position corresponding to a previous driving moment and a current obstacle center position corresponding to a current driving moment, and taking a direction from the preamble obstacle center position to the current obstacle center position as an extension direction;

for each newly added obstacle position, predicting the extension estimation probability of each extension position within a preset range along the extension direction, and taking the extension position with the extension estimation probability larger than a preset probability value as the extension obstacle position.

10. A path planning apparatus for automatic parking, the path planning apparatus comprising:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring parking space information of a target parking space and determining a parking section and an adjustment section based on the parking space information;

the first determining module is used for determining a first planning path corresponding to the parking section through a mixed A-algorithm;

the second determining module is used for determining a second planning path corresponding to the adjusting section in a straight-line driving-in mode;

and the forming module is used for connecting the first planning path and the second planning path to form an automatic parking path.

11. An automatic parking apparatus, characterized by applying the parking path determined by the path planning apparatus for automatic parking according to claim 10; the device comprises:

The control module is used for controlling the vehicle to run according to the parking path and acquiring candidate obstacle positions at the current running time and newly-increased obstacle positions at the current running time relative to the previous running time;

the prediction module is used for predicting extended obstacle positions corresponding to the newly-added obstacle positions and determining the obstacle positions corresponding to the current running time based on the candidate obstacle positions and the extended obstacle positions;

and the adjusting module is used for adjusting the parking path based on the obstacle position and continuously executing the step of controlling the vehicle to run according to the parking path until the vehicle finishes automatic parking.

12. A computer-readable storage medium storing one or more programs executable by one or more processors to perform the steps of the method of path planning for automatic parking according to any one of claims 1-5 and/or to perform the steps of the method of automatic parking according to any one of claims 6-9.

13. A terminal device, comprising: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;

The communication bus realizes connection communication between the processor and the memory;

the processor, when executing the computer readable program, implements the steps of the path planning method of automatic parking according to any one of claims 1-5 and/or the steps of the automatic parking method according to any one of claims 6-9.

Images