A site automatic parking method, device, medium and electronic equipment

Abstract

The present disclosure provides a kind of automatic parking method of site, comprising: obtaining the current position of vehicle;According to the current position of the vehicle, it is judged whether the distance between the vehicle and navigation terminal point is less than preset value;If less than preset value, obtain the road obstacle information near the navigation terminal point, and update road drivable area according to the road obstacle information;Obtain search parameter, search parking point according to the search parameter;It is judged whether the parking point is located in front of the navigation terminal point;If located in front, solve first path based on the current position of the vehicle and the position of the parking point, smooth the first path to generate first smooth trajectory, and control the vehicle to travel to the parking point according to the first smooth trajectory.The method provided by the present disclosure can realize the parking on the selected position of public road.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and more specifically, to a method, apparatus, medium, and electronic device for automatic parking at a station. Background Technology

[0002] In the field of autonomous driving, automatic parking systems are generally installed in mid-to-high-end vehicles. These systems utilize numerous high-cost sensors and function primarily as a driver assistance feature to help novice drivers park. Their application is typically limited to parking lots. However, in Level 4 autonomous driving scenarios, road conditions are complex, and there are no fixed parking spaces. Existing automatic parking methods struggle to achieve parallel parking at any chosen location on the road. Summary of the Invention

[0003] The purpose of this disclosure is to provide a method, apparatus, medium, and electronic device for automatic parking at a station, the specific solutions of which are as follows:

[0004] According to a specific embodiment of this disclosure, in a first aspect, this disclosure provides an automatic parking method at a station, comprising:

[0005] Get the vehicle's current location;

[0006] Determine whether the distance between the vehicle and the navigation destination is less than a preset value based on the vehicle's current location;

[0007] If the value is less than a preset value, obtain road obstacle information near the navigation endpoint and update the drivable area of ​​the road based on the road obstacle information;

[0008] Obtain search parameters and search for parking locations based on the search parameters;

[0009] Determine whether the parking spot is located ahead of the navigation destination; and

[0010] If the vehicle is located ahead, a first path is solved based on the vehicle's current position and the location of the parking spot. The first path is then smoothed to generate a first smooth trajectory. The vehicle is then controlled to drive to the parking spot based on the first smooth trajectory.

[0011] Optionally, solving the first path based on the vehicle's current location and the parking spot's location includes:

[0012] The first path is solved using a nonlinear programming algorithm.

[0013] Optionally, before the step of determining whether the parking point is located ahead of the navigation destination, the method further includes:

[0014] Determine whether a parking spot is found before the front of the vehicle reaches the navigation destination. If a parking spot is found, determine whether the parking spot is located in front of the navigation destination. If no parking spot is found, end the parking process.

[0015] Optionally, after the step of controlling the vehicle to travel to the parking point according to the first smooth trajectory, the method further includes:

[0016] Determine if parking was successful;

[0017] If parking fails, determine whether an RS curve exists based on the vehicle's current position, the parking spot's position, and obstacle information; and

[0018] If an RS curve exists, the vehicle is controlled to travel to the parking point based on the RS curve.

[0019] Optionally, determining whether parking was successful includes: judging whether parking was successful by checking the parking position of the vehicle.

[0020] Optionally, if not located ahead, the presence of an RS curve is determined based on the vehicle's current position, the parking point's position, and obstacle information; and

[0021] If an RS curve exists, the vehicle is controlled to travel to the parking point based on the RS curve.

[0022] Optionally, controlling the vehicle to travel to the parking point based on the RS curve includes:

[0023] Select the shortest RS curve as the second path, and segment the second path according to whether there is reverse traffic, to obtain the segmented second path; and

[0024] For each segment of the second segmented path, a segmented trajectory is generated using a Durbin curve. The segmented trajectory is then smoothed to obtain a smoothed segmented trajectory. The vehicle is then controlled to travel to the parking point based on the smoothed segmented trajectory.

[0025] According to a specific embodiment of this disclosure, in another aspect, this disclosure provides an automatic parking device for bus stops, comprising:

[0026] The acquisition unit is used to acquire the vehicle's current location;

[0027] The first judgment unit is used to determine whether the distance between the vehicle and the navigation destination is less than a preset value based on the current position of the vehicle.

[0028] An update unit is used to obtain road obstacle information near the navigation endpoint if the value is less than a preset value, and update the drivable area of ​​the road based on the road obstacle information;

[0029] The search unit is used to acquire search parameters and search for parking spots based on the search parameters.

[0030] The second determination unit is used to determine whether the parking point is located ahead of the navigation destination; and

[0031] The control unit is configured to, if located ahead, solve a first path based on the vehicle's current position and the location of the parking point, smooth the first path to generate a first smooth trajectory, and control the vehicle to travel to the parking point according to the first smooth trajectory.

[0032] According to specific embodiments of the present disclosure, in another aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0033] According to a specific embodiment of this disclosure, in another aspect, this disclosure provides an electronic device, including:

[0034] One or more processors;

[0035] A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to perform the methods described above.

[0036] The automatic parking method, device, medium, and electronic equipment disclosed herein can solve the parking problem of driverless vehicles at delivery stations on public roads, enabling them to park at any selected location on public roads (provided that they comply with traffic rules). Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0038] Figure 1 A schematic diagram of the structure of an automatic driving system applicable to the automatic parking method at stations provided in this embodiment is given;

[0039] Figure 2 A flowchart illustrating the automatic parking method at a station provided in an embodiment of this disclosure is given schematically.

[0040] Figure 3 A flowchart illustrating the automatic parking method at a station provided in an embodiment of this disclosure is given schematically.

[0041] Figure 4 A schematic diagram of the structure of the automatic parking device at the station provided in the embodiments of this disclosure is given;

[0042] Figure 5 A schematic diagram of the connection structure of an electronic device according to an embodiment of the present disclosure is shown.

[0043] Figure 6 A schematic diagram illustrating the derivation of the nonlinear programming algorithm involved in the embodiments of this disclosure is provided.

[0044] The reference numerals in the attached figures are as follows:

[0045] 11. High-precision map; 12. Sensor; 13. Planner; 14. Controller. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this disclosure clearer, the disclosure will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0047] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure. The singular forms “a,” “the,” and “the” as used in the embodiments of this disclosure and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0048] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0049] It should be understood that although the terms first, second, third, etc., may be used to describe embodiments of this disclosure, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of embodiments of this disclosure, and similarly, second may also be referred to as first.

[0050] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0051] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0052] The optional embodiments of this disclosure are described in detail below with reference to the accompanying drawings.

[0053] Example 1

[0054] This embodiment provides an automatic parking method for delivery stations. This method can be applied to various types of vehicles equipped with automatic driving systems, such as various unmanned delivery vehicles that can drive on public roads. These unmanned delivery vehicles typically carry a variety of delivery goods and need to stop at the delivery stations corresponding to each delivery good in order to deliver the goods to the designated recipient.

[0055] Figure 1 A schematic diagram of the structure of an automatic driving system applicable to the automatic parking method at stations provided in this embodiment is given. For example... Figure 1 As shown, the autonomous driving system may include: a high-precision map 11, a sensor 12, a planner 13, and a controller 14.

[0056] The high-precision map 11 is used to store map information of the vehicle's operating area. This map information includes at least: lane information, traffic light locations, and traffic signs. The lane information may further include: lane type, number of lanes, lane number, and lane width. The high-precision map 11 can also be used to generate navigation routes, such as the navigation route for an unmanned delivery vehicle to a user's residential area. The high-precision map 11 can also help the planner 13 generate real-time planned paths.

[0057] The sensor 12 is used to sense the road conditions in front of and behind the vehicle and generate obstacle information near the vehicle. The obstacle information may include: obstacle type, the projection of the obstacle boundary on the map, the predicted obstacle trajectory, etc. The sensor 12 can also be used to locate the vehicle's position in the high-precision map 11. The sensor 12 can also be used to communicate with the planner 13 to provide processed perception data to update the drivable road area.

[0058] The planner 13 receives the perception data from the sensor 12 and makes a path decision within the currently drivable area. The path decision, after smoothing, yields the vehicle's trajectory. The planner 13 can also communicate with the controller 14 to convert the obtained vehicle trajectory into control commands.

[0059] The controller 14 communicates with the vehicle chassis, translating control commands into actual maneuvering actions. These actions include at least: acceleration, braking, turning the left steering wheel, and turning the right steering wheel.

[0060] Please see also Figure 2 and Figure 3 This embodiment provides an automatic parking method at a station, including the following steps:

[0061] S101, Obtain the current location of the vehicle.

[0062] In this step, the vehicle's current position can be obtained through a position sensor installed on the vehicle. The position sensor can obtain the vehicle's current coordinates while in motion, thereby pinpointing the vehicle's location on a high-precision map. In some embodiments, when the vehicle is in operation, the position sensor on the vehicle automatically starts working, thus enabling real-time acquisition of the vehicle's current position during operation.

[0063] S102, determine whether the distance between the vehicle and the navigation destination is less than a preset value based on the vehicle's current position. If yes, proceed to step S103; otherwise, return to step S101.

[0064] In this step, the vehicle's current location can be obtained using onboard location sensors, and the navigation destination is a specific location pre-set on a map, such as a delivery station corresponding to the goods being delivered. In real-world applications, the delivery station can be a logistics warehouse, a commercial shop, or a residential community. In reality, the delivery station may be located on public roads, such as a commercial shop adjacent to a city highway, or in open spaces, such as a residential building within a walled community with gates and walls.

[0065] The distance between the vehicle and the navigation destination can be the straight-line distance between the vehicle and the navigation destination. In some embodiments, the preset distance value is set to a range of 10 meters to 100 meters. It is understood that the preset distance value can be set according to the actual situation. For example, in some areas with limited parking spaces, the preset distance value can be set to a range of 100 meters to 1000 meters.

[0066] S103, obtain road obstacle information near the navigation destination, and update the drivable area of ​​the road based on the road obstacle information.

[0067] In this step, when the distance between the vehicle and the navigation destination is less than a preset value, the vehicle enters a sidewalk parking scenario, and the vehicle begins to update the drivable road area. During vehicle operation, various types of obstacles, such as vehicles ahead, medians, and loose debris, can affect the vehicle's drivable area. After entering the sidewalk parking scenario, it is necessary to acquire road obstacle information near the navigation destination to avoid collisions. This road obstacle information includes: obstacle type, the projection of the obstacle boundary on the map, and the predicted obstacle trajectory. In some embodiments, this road obstacle information can be obtained through onboard sensors.

[0068] S104, Obtain search parameters, and search for parking spots according to the search parameters.

[0069] In this step, when the distance between the vehicle and the navigation destination is less than a preset value, the vehicle enters the side-by-side parking scenario and begins searching for nearby parking spots.

[0070] The search parameters can be parking-related parameters, such as the number of parking spaces, the distance between the parking space and the navigation destination, the distance between the parking space and a moving vehicle, whether the parking is free, and the permitted parking duration. These parameters can be preset; for example, parking spaces can be preset to be free or have more than 5 parking spaces. These parameters can also be dynamically updated according to certain rules. For example, in the first time period, the distance between the parking space and the navigation destination may be less than 10 meters, while in the second time period, the distance may be less than 20 meters.

[0071] In some embodiments, the search range for parking spots can be dynamically adjusted based on the vehicle's current location, i.e., parking spots are searched within the dynamically adjusted range. For example, when the vehicle is traveling on a public road, the search parameters for parking spots are set to a first parameter; when the vehicle is traveling in an open space, the search parameters for parking spots are set to a second parameter. By dynamically adjusting the search parameters based on the vehicle's current location, more optimal parking spots can be found, improving the success rate of automatic parking under actual road conditions.

[0072] In some embodiments, the search parameters for parking spots can be dynamically adjusted based on the city / district where the vehicle is located. For example, when the vehicle is located in Guangzhou, the search parameter for parking spots is set as the third parameter; when the vehicle is located in Shenzhen, the search parameter for parking spots is set as the fourth parameter. By dynamically adjusting the search parameters based on the city / district where the vehicle is located, it is possible to quickly adapt to different cities / districts, facilitating the application and promotion of the vehicle in various regions.

[0073] S105, determine whether a parking point has been found before the front of the vehicle reaches the navigation destination. If yes, proceed to step S106; otherwise, end the parking process.

[0074] In this step, if the vehicle has reached the navigation destination but has not yet found a suitable parking spot, it may be that the parking spot does not exist at all, or that although a parking spot exists, it is not suitable for parking at this time. In this case, the vehicle cannot automatically park at the station and needs to terminate the automatic parking process immediately. In some embodiments, the vehicle terminates the automatic parking process and also sends a parking error message to prompt the user to intervene manually. In some embodiments, this step can be omitted.

[0075] S106, determine whether the parking point is located in front of the navigation destination; if so, proceed to step S107.

[0076] In this step, if the parking spot is located ahead of the navigation destination, the vehicle only needs to proceed normally as prompted during the parking process. If the parking spot is not located ahead of the navigation destination, the vehicle may need to perform actions such as steering or reversing during the parking process.

[0077] If the parking spot is not located ahead of the navigation destination, in some embodiments, such as Figure 2 As shown, automatic parking will be terminated; in other embodiments, such as Figure 3 As shown, step S108 will be executed.

[0078] S107, based on the current position of the vehicle and the position of the parking point, solve for a first path, smooth the first path to generate a first smooth trajectory, and control the vehicle to drive to the parking point according to the first smooth trajectory.

[0079] In this step, the vehicle's current position can be obtained using an onboard position sensor. Based on the vehicle's current position and the location of the parking spot, a first path from the vehicle's current position to the parking spot can be calculated. A smoothing algorithm can then be used to smooth this first path, thereby generating a first smooth trajectory.

[0080] In some embodiments, the first path can be obtained using a nonlinear programming algorithm. This nonlinear programming algorithm adds nonlinear constraints to a quadratic programming (QP) algorithm. In a quadratic programming algorithm, the objective function contains squared terms, and all constraints are linear. Since the quadratic programming algorithm only constrains the position of the vehicle's rear axle center and not the positions of the four corner points, it may lead to corner collisions in the optimized trajectory. The nonlinear programming algorithm used in this embodiment can solve the collision problem at the vehicle's corner points in path planning. Specifically, collision avoidance at the vehicle's corner points can be achieved by adding several constraints on the vehicle's corner points. Furthermore, since half the vehicle width and a safety buffer distance have already been subtracted when generating the path boundary, collision avoidance at the vehicle's corner points can also be achieved by only constraining the position of the center point of the front bumper.

[0081] In some embodiments, the following constraints are added to the quadratic programming path:

[0082] Lower boundary constraints at front corners (total N) f indivual):

[0083]

[0084] Front corner point upper boundary constraints (Nf in total):

[0085]

[0086] Where, Δl nonped Δl is the expected distance between the vehicle and the non-pedestrian obstacle. ped The values ​​represent the desired distance between the vehicle and pedestrian obstacles, and are all preset parameters. NONCURB represents lane boundary lines without curbs, CURB represents lane boundary lines with curbs, and OBS... NONPED OBS_PED represents obstacle boundaries that are not pedestrian types, while ε represents obstacle boundaries that are pedestrian types. n For the slack variable with respect to the NONCURB type boundary, ε o For the slack variables of the obstacle type boundary, and Let o be the upper and lower boundaries of a series of ADC reference points o sampled at equal intervals Δs within a certain distance s in Frenet coordinates.

[0087] Regarding the calculation l f Or, in other words, how to make l f There are three ways to represent the optimization variables and known parameters as a function:

[0088] Method (1) assumes the curvature of the reference line is 0 (i.e., assumes it is a straight line), and assumes θ << 1:

[0089] l f =l+Ll′

[0090] Where L is the distance from the front bumper to the center of the vehicle. This formula assumes sinθ = l′.

[0091] Method (2) assumes the curvature of the reference line is 0 (i.e., assumes it is a straight line), and assumes κ r l << 1):

[0092]

[0093] The assumptions of this formula, compared to those of method (1), are that the assumption θ << 1 is removed.

[0094] Method (3) definition:

[0095]

[0096] have

[0097]

[0098] The derivation of this formula can be found by referring to... Figure 6 The diagram assumes that the reference line near the vehicle can be considered as an arc with a radius of curvature (considering κ at this point). r <0)

[0099]

[0100] a=Lsinθ

[0101] b=Lcosθ

[0102]

[0103]

[0104] The above substitutions

[0105]

[0106] Then you can get

[0107]

[0108] When k r When >0, a similar derivation can be obtained.

[0109]

[0110] And k r When the value is 0, it is simplified to version 2.

[0111] Method (1) remains a QP optimization problem; methods (2) and (3) become nonlinear programming (NLP) problems.

[0112] After controlling the vehicle to travel to the parking point according to the first smooth trajectory, in some embodiments, such as Figure 2 As shown, automatic parking will be terminated; in other embodiments, such as Figure 3 As shown, step S107a will then be executed.

[0113] S107a, determine whether parking was successful. If successful, end parking; otherwise, proceed to step S108.

[0114] In this step, the success of parking can be determined by checking the vehicle's parking position. This parking position can be obtained using sensors on the vehicle itself, or it can be obtained using sensors located at the parking spot.

[0115] S108. Based on the current position of the vehicle, the position of the parking point, and obstacle information, determine whether an RS curve exists. If yes, proceed to step S109; otherwise, proceed to step S120 and send a parking abnormality prompt.

[0116] In this step, the vehicle's current position and obstacle information can be obtained from onboard sensors. The Reeds-Shepp Curves (RS curves) consist of a series of circular and straight-line paths, allowing the vehicle to reverse and better meeting parking needs.

[0117] In some embodiments, the method for determining whether an RS curve exists is to sequentially hit the vehicle's starting point and stopping point with each RS curve. If a curve is considered to be usable after considering obstacles, then the curve is considered usable.

[0118] S109, Select the shortest RS curve as the second path, and divide the second path into segments according to whether there is reversing, to obtain the segmented second path.

[0119] In this step, if a reversing path exists in the RS curve, each reversing path is separated into a separate sub-path. Through the above division, the second path can be decomposed into multiple sequentially connected sub-paths, for example, sub-path 1 (reversing path), sub-path 2 (non-reversing path), sub-path 3 (reversing path), and sub-path 4 (non-reversing path). All the sub-paths are connected sequentially to form the segmented second path.

[0120] S110, generate segmented trajectories for each segment of the segmented second path using Durbin curves, smooth the segmented trajectories to obtain segmented smooth trajectories, and control the vehicle to drive to the parking point according to the segmented smooth trajectories.

[0121] In this step, the Dubin curves are the shortest paths connecting two two-dimensional planes, satisfying curvature constraints and specified tangents (entry directions) at the beginning and end. Like RS curves, Dubin curves consist of a series of circles and straight lines. The difference between Dubin curves and RS curves is that Dubin curves cannot change direction midway (i.e., the vehicle can only move forward continuously). Each segment of the segmented second path can be generated using Dubin curves. These segmented trajectories can then be smoothed using a smoothing algorithm, resulting in a smoothed segmented trajectory.

[0122] After the vehicle is guided to the parking point according to the segmented smooth trajectory, in some embodiments, automatic parking will be terminated; in other embodiments, such as Figure 3 As shown, step S110a will then be executed.

[0123] S110a, determine whether parking was successful. If successful, end parking. If unsuccessful, execute step S120 to send a parking error message.

[0124] In this step, the success of parking can be determined by checking the vehicle's parking position. This parking position can be obtained using sensors on the vehicle itself, or it can be obtained using sensors located at the parking spot.

[0125] Example 2

[0126] like Figure 4 As shown, according to a specific embodiment of this disclosure, in a second aspect, this disclosure provides an automatic parking device for bus stops. The device includes an acquisition unit 301, a first judgment unit 302, an update unit 303, a search unit 304, a second judgment unit 305, and a control unit 306, etc., as detailed below:

[0127] The acquisition unit 301 is used to acquire the current position of the vehicle.

[0128] The vehicle's current position can be obtained through position sensors installed on the vehicle. These position sensors can obtain the vehicle's current coordinates while in motion, thereby pinpointing the vehicle's location on a high-precision map. In some embodiments, when the vehicle is in operation, the position sensors on the vehicle automatically activate, enabling real-time acquisition of the vehicle's current position during operation.

[0129] The first judgment unit 302 is used to determine whether the distance between the vehicle and the navigation destination is less than a preset value based on the current position of the vehicle.

[0130] The vehicle's current location can be obtained using onboard location sensors, and the navigation destination is a specific location pre-set on a map, such as a delivery station corresponding to the goods being delivered. In practical applications, the delivery station can be a logistics warehouse, a commercial shop, or a residential community. In reality, the delivery station may be located on public roads, such as commercial shops adjacent to city highways, or in open spaces, such as residential buildings within a walled community with gates.

[0131] The distance between the vehicle and the navigation destination can be the straight-line distance between the vehicle and the navigation destination. In some embodiments, the preset distance value is set to a range of 10 meters to 100 meters. It is understood that the preset distance value can be set according to the actual situation. For example, in some areas with limited parking spaces, the preset distance value can be set to a range of 100 meters to 1000 meters.

[0132] The update unit 303 is used to obtain road obstacle information near the navigation endpoint if the value is less than a preset value, and update the drivable area of ​​the road based on the road obstacle information.

[0133] When the distance between the vehicle and the navigation destination is less than a preset value, the vehicle enters a sidewalk parking scenario, and the vehicle begins updating the drivable road area. During vehicle operation, various types of obstacles, such as vehicles ahead, medians, and loose debris, can affect the vehicle's drivable area. After entering the sidewalk parking scenario, it is necessary to obtain road obstacle information near the navigation destination to avoid collisions. This road obstacle information includes: obstacle type, the projection of the obstacle boundary on the map, and the predicted obstacle trajectory. In some embodiments, this road obstacle information can be obtained through onboard sensors.

[0134] The search unit 304 is used to obtain search parameters and search for parking spots according to the search parameters.

[0135] When the distance between the vehicle and the navigation destination is less than a preset value, the vehicle enters the side-by-side parking scenario and begins searching for nearby parking spots.

[0136] The search parameters can be parking-related parameters, such as the number of parking spaces, the distance between the parking space and the navigation destination, the distance between the parking space and a moving vehicle, whether the parking is free, and the permitted parking duration. These parameters can be preset; for example, parking spaces can be preset to be free or have more than 5 parking spaces. These parameters can also be dynamically updated according to certain rules. For example, in the first time period, the distance between the parking space and the navigation destination may be less than 10 meters, while in the second time period, the distance may be less than 20 meters.

[0137] In some embodiments, the search range for parking spots can be dynamically adjusted based on the vehicle's current location, i.e., parking spots are searched within the dynamically adjusted range. For example, when the vehicle is traveling on a public road, the search parameters for parking spots are set to a first parameter; when the vehicle is traveling in an open space, the search parameters for parking spots are set to a second parameter. By dynamically adjusting the search parameters based on the vehicle's current location, more optimal parking spots can be found, improving the success rate of automatic parking under actual road conditions.

[0138] In some embodiments, the search parameters for parking spots can be dynamically adjusted based on the city / district where the vehicle is located. For example, when the vehicle is located in Guangzhou, the search parameter for parking spots is set as the third parameter; when the vehicle is located in Shenzhen, the search parameter for parking spots is set as the fourth parameter. By dynamically adjusting the search parameters based on the city / district where the vehicle is located, it is possible to quickly adapt to different cities / districts, facilitating the application and promotion of the vehicle in various regions.

[0139] The second judgment unit 305 is used to determine whether the parking point is located in front of the navigation destination.

[0140] If the parking spot is located ahead of the navigation destination, the vehicle only needs to proceed normally as prompted during the parking process. If the parking spot is not located ahead of the navigation destination, the vehicle may need to perform actions such as steering or reversing during the parking process.

[0141] The control unit 306 is configured to, if located ahead, solve a first path based on the current position of the vehicle and the position of the parking point, smooth the first path to generate a first smooth trajectory, and control the vehicle to drive to the parking point according to the first smooth trajectory.

[0142] The vehicle's current position can be obtained from an onboard position sensor. Based on the vehicle's current position and the location of the parking spot, a first path from the vehicle's current position to the parking spot can be calculated. In some embodiments, the first path can be calculated using a nonlinear quadratic programming algorithm. A smoothing algorithm can be used to smooth the first path, thereby generating a first smooth trajectory.

[0143] This disclosure provides an automatic parking method, device, medium, and electronic equipment that can solve the parking problem of driverless vehicles at delivery stations on public roads, enabling parallel parking at any selected location on public roads (provided that traffic rules are followed).

[0144] Example 3

[0145] like Figure 5 As shown, this embodiment provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the method steps described in the above embodiment.

[0146] Example 4

[0147] This disclosure provides a non-volatile computer storage medium storing computer-executable instructions that can perform the steps described in the above embodiments.

[0148] Example 5

[0149] The following is for reference. Figure 5 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0150] like Figure 5 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the electronic device. The processing unit 401, ROM 402, and RAM 403 are interconnected via a bus 405. An input / output (I / O) interface 405 is also connected to the bus 405.

[0151] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 405 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 405. Communication device 405 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.

[0152] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 405, or installed from a storage device 408, or installed from a ROM 402. When the computer program is executed by the processing device 401, it performs the functions defined in the methods of embodiments of this disclosure.

[0153] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0154] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0155] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0157] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

Claims

1. An automatic parking method for unmanned vehicles at a station, characterized in that, Includes the following steps: Get the vehicle's current location; Determine whether the distance between the vehicle and the navigation destination is less than a preset value based on the vehicle's current location; If the value is less than a preset value, obtain road obstacle information near the navigation endpoint and update the drivable area of ​​the road based on the road obstacle information; Obtain search parameters and search for parking locations based on the search parameters; Determine whether the parking spot is located ahead of the navigation destination; as well as If the vehicle is located ahead, based on its current position and the location of the parking spot, a first path is solved using a nonlinear programming algorithm. This first path is then smoothed to generate a first smooth trajectory, and the vehicle is controlled to travel to the parking spot based on the first smooth trajectory. The nonlinear programming algorithm adds nonlinear constraints on the lower and upper boundaries of the vehicle's front corner point to the quadratic programming algorithm. The nonlinear programming algorithm calculates the lateral coordinate l of the vehicle's front corner point. f At that time, l f Represented as or in, l is the lateral displacement of the vehicle's center of mass, l′ is the first derivative of l with respect to the arc length s, and κ r The curvature is used as a reference line.

2. The unmanned vehicle station parking method as described in claim 1, characterized in that, Before the step of determining whether the parking point is located ahead of the navigation destination, the method further includes: Determine whether a parking spot is found before the front of the vehicle reaches the navigation destination. If a parking spot is found, determine whether the parking spot is located in front of the navigation destination. If no parking spot is found, end the parking process.

3. The unmanned vehicle station parking method as described in claim 1, characterized in that, After the step of controlling the vehicle to drive to the parking point according to the first smooth trajectory, the method further includes: Determine if parking was successful; If parking fails, determine whether an RS curve exists based on the vehicle's current position, the parking spot's position, and obstacle information; and If an RS curve exists, the vehicle is controlled to travel to the parking point based on the RS curve.

4. The unmanned vehicle station parking method as described in claim 3, characterized in that, The determination of whether parking was successful includes: The success of parking is determined by checking the vehicle's parking position.

5. The unmanned vehicle parking method at a station as described in claim 1, characterized in that, Also includes: If not located ahead, determine whether an RS curve exists based on the vehicle's current position, the parking point's position, and obstacle information; as well as If an RS curve exists, the vehicle is controlled to travel to the parking point based on the RS curve.

6. The unmanned vehicle parking method at a station as described in any one of claims 3-5, characterized in that, The method of controlling the vehicle to the parking point based on the RS curve includes: Select the shortest RS curve as the second path, and segment the second path according to whether there is reverse traffic, to obtain the segmented second path; and For each segment of the second segmented path, a segmented trajectory is generated using a Durbin curve. The segmented trajectory is then smoothed to obtain a smoothed segmented trajectory. The vehicle is then controlled to travel to the parking point based on the smoothed segmented trajectory.

7. An automatic parking device for unmanned vehicle stations, characterized in that, include: The acquisition unit is used to acquire the vehicle's current location; The first judgment unit is used to determine whether the distance between the vehicle and the navigation destination is less than a preset value based on the current position of the vehicle. An update unit is used to obtain road obstacle information near the navigation endpoint if the value is less than a preset value, and update the drivable area of ​​the road based on the road obstacle information; The search unit is used to acquire search parameters and search for parking spots based on the search parameters. The second judgment unit is used to determine whether the parking point is located in front of the navigation destination; as well as A control unit, configured to, if located ahead, solve a first path based on the vehicle's current position and the location of the parking point using a nonlinear programming algorithm, smooth the first path to generate a first smooth trajectory, and control the vehicle to travel to the parking point according to the first smooth trajectory; wherein, the nonlinear programming algorithm adds nonlinear constraints of the lower and upper boundaries of the front corner of the vehicle to the quadratic programming algorithm, and the nonlinear programming algorithm calculates the lateral coordinate l of the front corner of the vehicle. f At that time, l f Represented as or in, l is the lateral displacement of the vehicle's center of mass, l′ is the first derivative of l with respect to the arc length s, and κ r The curvature is used as a reference line.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 6.

Images