Vehicle parking system, vehicle parking method, control device and storage medium
By establishing a three-dimensional coordinate system and a three-dimensional map, and generating parking paths based on three-dimensional point cloud data, the problem of difficulty in stability and accuracy control in automatic parking of towed RVs is solved, and efficient and safe automatic parking operations are achieved.
Patent Information
- Application Number
- CN202410956305.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-17
AI Technical Summary
The existing automatic parking technology for towed RVs or large objects has not yet been popularized, and there are problems of difficulty in controlling stability and accuracy during parking, especially in different parking lot environments.
The acquisition device is used to establish a three-dimensional coordinate system and a three-dimensional map, model it based on the three-dimensional point cloud data of the traction vehicle and the traction object, generate parking paths, and generate control instructions based on the environmental data through the control device to realize automatic parking of the traction object.
Improve the stability and accuracy of parking operations, ensure the safety and efficiency of the traction combination during parking, and adapt to different parking lot environments.
Smart Images

Figure CN118494465B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle parking system, a vehicle parking method, a control device and a storage medium. Background Art
[0002] With the improvement of living standards and the change of tourism concepts, self-driving tours and outdoor camping are becoming more and more popular. With its spacious space, complete facilities and high flexibility, trailer RVs can provide people with a home-like mobile experience and meet the needs of personalized and comfortable travel.
[0003] However, the automatic parking technology for trailers or large objects is still in the development stage and is not yet widely used in practice. Summary of the invention
[0004] The embodiments of the present application provide a vehicle parking system, a vehicle parking method, a control device and a storage medium, which improve the stability of a towed object during parking, so as to at least partially solve the above-mentioned technical problems.
[0005] In order to achieve the above object, according to a first aspect of the present application, a vehicle parking system is provided, the system comprising:
[0006] A collection device for collecting environmental data of a target parking area, wherein the collection device and the vehicle can be separated; the vehicle includes a tractor and a tractor object connected to each other;
[0007] A control device is communicatively connected to the acquisition device, and is used to generate a control instruction according to the environmental data, and control the vehicle to park according to the control instruction.
[0008] According to a second aspect of the present application, a vehicle parking method is provided, the method comprising:
[0009] Acquiring environmental data of a target parking area collected by a collection device, wherein the collection device and the vehicle are detachably arranged; the vehicle comprises a tractor and a tractor object connected to each other;
[0010] A control instruction is generated according to the environmental data, and the vehicle is controlled to park according to the control instruction so that the towing object is parked in the target parking area.
[0011] According to a third aspect of the present application, a vehicle parking device is provided, the device comprising:
[0012] An acquisition module, used to acquire environmental data of a target parking area acquired by an acquisition device, wherein the acquisition device and the vehicle can be separated; the vehicle includes a tractor and a tractor object connected to each other;
[0013] The control module is used to generate a control instruction according to the environmental data, and control the vehicle to park according to the control instruction, so that the towing object is parked in the target parking area.
[0014] According to a fourth aspect of the present application, a vehicle parking system is provided, comprising a control device, a tractor and a tractor object; wherein the control device is used to execute the steps of the vehicle parking method as described in the second aspect.
[0015] According to a fifth aspect of the present application, a control device is provided, comprising a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps of the vehicle parking method as described in the second aspect.
[0016] According to a sixth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for loading by a processor to execute the steps of the vehicle parking method as described in the second aspect.
[0017] According to a seventh aspect of the present application, a computer program product is provided, comprising a computer program or instructions, which implement the steps of the vehicle parking method as described in the second aspect when the computer program or instructions are executed by a processor.
[0018] In the vehicle parking method, apparatus, system, device and storage medium of the embodiments of the present application, environmental data of the target parking area is collected, and control instructions are generated according to the environmental data. The vehicle is controlled to park according to the control instructions, so that the towing object can be parked in the target parking area, thereby realizing automatic parking of the towing vehicle and the towing object, and improving the parking operation efficiency.
[0019] Other features and advantages of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work.
[0021] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same figure numbers represent the same parts in the following description.
[0022] Figure 1 is a schematic diagram of the architecture of a vehicle parking system provided in some embodiments of the present application;
[0023] Figure 2 is a schematic diagram of an application scenario of a vehicle parking method provided in some embodiments of the present application;
[0024] Figure 3 is a schematic flow chart of a vehicle parking method provided in some embodiments of the present application;
[0025] Figure 4 is a flowchart of a vehicle parking method provided in some other embodiments of the present application;
[0026] Figure 5 is a schematic diagram of a scene in which a towed object is parked in a target parking area provided in some embodiments of the present application;
[0027] Figure 6 is a schematic diagram of a scene of a swing angle of a traction object provided in some embodiments of the present application;
[0028] Figure 7 is a schematic diagram of a scene of top scanning of an aircraft provided in some embodiments of the present application;
[0029] Figure 8 is a schematic diagram of a scene of an aircraft circumferential scanning provided in some embodiments of the present application;
[0030] Fig. 9 is a flowchart of a vehicle parking method provided in some other embodiments of the present application;
[0031] Fig.10 is a flowchart of an aircraft scanning step provided in some embodiments of the present application;
[0032] Fig.11 is a flowchart of the spatial modeling and path planning steps provided in some embodiments of the present application;
[0033] Fig.12 is an overall flow chart of a vehicle parking method provided in yet other embodiments of the present application;
[0034] Fig.13 is an overall flow chart of a vehicle parking method provided in some further embodiments of the present application;
[0035] Fig.14 is a schematic diagram of the structure of a vehicle parking device provided in some embodiments of the present application;
[0036] Fig.15 It is a schematic diagram of the structure of a control device provided in some embodiments of the present application. DETAILED DESCRIPTION
[0037] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application. In the description of the present application, the terms "first" and "second" are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.
[0038] At present, automatic parking technology for trailer RVs or objects has not yet been popularized. When trailer RVs or objects are automatically parked, due to their large size and long length, they require a high parking space, and extremely high precision is required when docking with camp facilities. The automatic parking system needs to accurately calculate and control the movement of the vehicle to ensure safe and accurate parking in a limited space, which places extremely high demands on sensor accuracy, path planning algorithms, and control systems. In addition, there are also challenges in the stability of trailer RVs or objects during automatic parking. The environmental conditions of different parking lots or campsites vary, including but not limited to the size of parking spaces, ground conditions, surrounding obstacles, etc. The automatic parking system must have strong environmental perception capabilities and flexible scene adaptability, and be able to obtain and process a large amount of information in real time to cope with various complex parking scenarios.
[0039] In view of this, the embodiments of the present application provide a vehicle parking method, device, system, equipment and storage medium. Since the trailer caravan or object itself has no sensors, etc., and its shape may also be irregular, a three-dimensional coordinate system and a three-dimensional map are established by introducing a collection device, and modeling is performed based on the three-dimensional point cloud data of the towing vehicle and the towing object (such as the trailer caravan or object, etc.), and then path planning is performed based on the three-dimensional map and the model, thereby realizing automatic parking of the towing object and solving the problems of difficulty in scale and precision control, poor dynamic stability, and inaccurate environmental perception caused by the towing object blocking the vehicle sensor in the traditional towing process.
[0040] See also Figure 1, an embodiment of the present application provides a vehicle parking system, which includes a collection device 10 and a control device 30. Among them, the collection device 10 and the vehicle 20 can be separately arranged. The collection device 10 is communicatively connected to the control device 30. In some embodiments, the control device 30 can be mounted on the collection device 10, or on the vehicle 20, or the control device 30 can also be mounted on other devices and be communicatively connected to the collection device 10 and / or the vehicle 20. It should be noted that the vehicle referred to in the embodiment of the present application includes a tractor and a towing object, and the tractor and the towing object are connected to each other during parking. Among them, the towing object refers to the towed object, and the tractor refers to the vehicle used to tow the towing object. The towing object may have a driving capability or not. Exemplarily, the towing object includes but is not limited to a trailer caravan, an ordinary vehicle, or other objects.
[0041] The tractor can be connected to the towing object through a connecting device, so that the towing object is driven to move by the movement of the tractor. The connection type between the tractor and the towing object can be a rigid connection or a non-rigid connection. Among them, the connecting device includes but is not limited to a towing hook, a towing rod or a hinge. After the tractor and the towing object are connected, it is called a towing combination. The tractor and the towing object can be automatically connected by the tractor or manually connected by the user. The connection between the tractor and the towing object includes physical connection and circuit connection. Among them, the physical connection includes but is not limited to connection through mechanical connectors, towing rods or ropes, magnetic connectors and other connecting devices, such as hooks, pins, snap-on connectors, etc. The circuit connection includes but is not limited to cable connection, circuit connection, etc. For example, the connection of vehicle circuits, light signal circuits, etc., to control the synchronization of the brake light signal and turn signal of the tractor and the towing object, etc.
[0042] The collecting device is used to collect environmental data of the target parking area, and the control device generates a control instruction according to the environmental data and controls the vehicle to park according to the control instruction. The environmental data includes at least one of terrain data, obstacle data, and parking space size data.
[0043] Specifically, the acquisition device can perform an all-round scan of the target parking area through the onboard acquisition equipment, such as a camera, a lidar or a three-dimensional point cloud scanning device, so as to collect environmental data such as terrain, obstacles and parking space dimensions, and send the data to the control device, so that the control device can generate control instructions based on the environmental data, and control the vehicle to park according to the control instructions, so that the towing object can be parked in the target parking area.
[0044] In some embodiments, the control device includes a first data calculation module. When the vehicle performs parking, the collection device is used to collect the real-time driving data of the vehicle, and the first data calculation module is used to generate a parking correction instruction based on the real-time driving data. The real-time driving data includes one or more of the posture data of the tractor, the posture data of the towing object, and the obstacle data. According to the real-time driving data of the vehicle collected by the collection device, the control device can determine the real-time driving state of the tractor and / or the towing object, thereby judging the stability of the vehicle, and then determining whether correction is required. When the real-time driving state indicates that the vehicle does not meet the stability condition, the first data calculation module determines that correction is required, and generates a parking correction instruction based on the real-time driving data. The parking correction instruction is used to update the remaining parking path, such as replanning the remaining parking path.
[0045] In some embodiments, the control device includes a second data calculation module, which is used to generate a map model based on environmental data; and / or the second calculation module is used to generate a parking path for the vehicle based on environmental data. Specifically, the second data calculation module establishes a map model as a reference. The computer device constructs a map model by fusing data from a Global Positioning System (GPS) receiver, an Inertial Measurement Unit (IMU) and other positioning sensors, thereby ensuring that the acquisition device can accurately determine its absolute position and posture in the map model. The second calculation module can also be used to generate a parking path for the vehicle based on environmental data, that is, the parking path is a parking path starting from the current position and driving to the target parking area.
[0046] Compared with the parking process of a single vehicle, when the tractor and the towed object are connected for parking together, the towed object is driven by the tractor and may have lateral displacement or swing, and the connection brings instability factors; and when the tractor is driving the towed object, it is also affected by the relative force of the towed object, which will also affect the stability of the tractor. As a result, traditional path planning may cause the traction combination to have a collision risk during the movement. Therefore, more driving restrictions need to be considered to ensure the stability of the traction combination during driving.
[0047] To this end, in some embodiments, the second calculation module is further used to obtain the driving restriction conditions of the vehicle, and generate the parking path of the vehicle according to the environmental data under the constraints of the driving restriction conditions. The driving parameters defined by the driving restriction conditions at least include the turning radius, reversing angle, and safety distance of the traction combination.
[0048] The turning radius of a traction combination refers to the minimum distance from the outermost point of the traction combination to the center line of the turning path when the traction combination turns. For a combination of a tractor and a motorhome, due to the particularity of the body length and connection method, its turning radius is usually larger than that of a single vehicle. Using the 3D point cloud data of the traction combination, the turning radius of the traction combination at different angles can be accurately calculated. The reversing angle refers to the maximum reversing angle that can be achieved when the tractor and the towed object need to maintain relative positions through the connection device when reversing. When planning the parking route, this angle limitation must be taken into account to ensure that the tractor and the motorhome will not break the connection device or lose control of the vehicle due to excessive angles during the reversing process. The maximum reversing angle is a calibrable value. Through the 3D point cloud data of the traction combination, the relative position and angle change of the tractor and the motorhome when reversing can be simulated, so as to determine the safe reversing angle range. In order to prevent the tractor and the motorhome from colliding with other vehicles or obstacles during parking, a certain safety distance needs to be reserved when planning the route. When planning a parking route, it is necessary to ensure that the tractor and the RV can safely stop or avoid the tractor within this safe distance in any case. The actual size and shape of the tractor at different positions and angles can be accurately calculated through the 3D point cloud data of the tractor combination. This information is combined with the position information of other vehicles and obstacles to determine the safe distance that needs to be reserved.
[0049] Exemplarily, the acquisition device is an aircraft equipped with an acquisition device or a mobile robot equipped with an acquisition device. Exemplarily, the acquisition device is one or more of a camera, a radar, or a three-dimensional point cloud scanning device. The number of acquisition devices can be one or more.
[0050] In some embodiments, the towing object is equipped with an intelligent control module, which is used to control the connection or separation of the towing object with external equipment according to environmental data. The external equipment is, for example, a towing vehicle or other road facilities. For example, after the towing vehicle drives the towing object to park and makes the towing object park in the target parking area, the towing object controls itself to separate from the towing vehicle through the intelligent control module. For another example, the towing object controls itself to connect with road facilities (such as charging piles, water pipes, etc.) through the intelligent control module.
[0051] See also Figure 2 The embodiments of the present application can be applied to Figure 2In the application scenario shown. This scenario shows a vehicle parking system, which at least includes a collection device 10, a tractor 201, a tractor object 202 and a control device 30. The collection device 10 is, for example, an aircraft, and the control device 30 is, for example, a computer device. The tractor 201 and the tractor object 202 can be connected to form a traction combination, that is, the vehicle 20 referred to in the above embodiment. The aircraft can be equipped with one or more collection devices, such as ultrasonic radar, millimeter wave radar, laser radar, and surround view camera.
[0052] In some embodiments, the control device 30 is used to execute the vehicle parking method, and can be a terminal device or a server. The control device 30 is directly or indirectly connected to the tractor 201 through a wired or wireless communication method to control the movement of the tractor 201, thereby driving the traction object 202 to move. Exemplarily, the control device 30 can be a vehicle-mounted terminal on the tractor 201. For another example, the control device 30 can be a cloud server connected to the tractor 201. For another example, the control device 30 can also be a terminal device connected to the tractor 201. For another example, the control device 30 can also be a drone.
[0053] Among them, the terminal device includes but is not limited to one or more of mobile phones, computers, Internet of Things devices, vehicle-mounted terminals, and portable wearable devices. Among them, the Internet of Things device can be a smart vehicle-mounted device, etc. The portable wearable device can be one or more of a smart watch, a smart bracelet, smart glasses, and a head-mounted device. Among them, the server can be an independent server, or it can be a server network composed of multiple servers, a server cluster, or a distributed system. The server includes but is not limited to a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing.
[0054] The following is a detailed description of the embodiments in conjunction with the accompanying drawings. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments. Although the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different from that shown in the accompanying drawings.
[0055] See also Figure 3 , provides a vehicle parking method, which is applied to a control device. The control device can be an on-board terminal on a tractor, a computer device connected to the tractor for communication, a server connected to the tractor for communication, or a control module on an aircraft, etc. The tractor can be a fuel vehicle, a plug-in hybrid vehicle, or a new energy vehicle, etc., which is not specifically limited in this application. The method includes:
[0056] Step S101, obtaining environmental data of a target parking area collected by a collection device, wherein the collection device and the vehicle can be separated; the vehicle includes a tractor and a tractor object connected to each other.
[0057] The control device is connected to the acquisition device in communication, and acquires the environmental data of the target parking area collected by the acquisition device. The environmental data includes but is not limited to one or more of the size of the target parking area, the terrain, the distribution of obstacles in or around the target parking area, and the three-dimensional point cloud data of the obstacles. Exemplarily, the acquisition device can collect the environmental data of the target parking area by panoramic view, satellite map, point cloud scanning, etc.
[0058] Exemplarily, the collection device is an aircraft, and the control device controls the aircraft to take off first. The aircraft uses the onboard camera, lidar or three-dimensional point cloud scanning equipment to perform an all-round scan of the target parking area, thereby collecting environmental data such as terrain, obstacles and parking space dimensions, and sending it to the control device; the control device receives the environmental data transmitted by the aircraft.
[0059] Step S102: generating a control instruction according to the environmental data, and controlling the vehicle to park according to the control instruction, so that the towed object is parked in a target parking area.
[0060] The control device generates a control instruction based on the received environmental data, and controls the vehicle to park according to the control instruction. Controlling the vehicle to park may be to control the tractor to drive and drive the towed object to move, thereby parking. Alternatively, if the towed object has an intelligent control module, the control device controls the vehicle to park, and may also control the tractor and the towed object to drive together to park.
[0061] In some embodiments, generating a control instruction based on environmental data includes: generating a parking path for the vehicle based on the environmental data, and generating a control instruction carrying the parking path; accordingly, controlling the vehicle to park according to the control instruction includes: controlling the vehicle to park according to the parking path.
[0062] Exemplarily, the control device first establishes a global coordinate system as a reference. The control device constructs a global coordinate system by fusing data from a global positioning system receiver, an inertial measurement unit, and other positioning sensors, thereby ensuring that the aircraft can accurately determine its absolute position and attitude in the global coordinate system. In addition, the aircraft can also combine the real-time acquired position data with geomagnetic data, landmark information, etc. through flight scanning, thereby establishing a three-dimensional space in the global coordinate system. The three-dimensional space includes a target parking area. Thus, the control device plans a parking path from the current position to the target parking area in the three-dimensional space based on the global coordinate system. The control device generates a control instruction carrying a parking path, and controls the vehicle to park according to the parking path in the control instruction.
[0063] The vehicle parking method of the embodiment of the present application collects environmental data of the target parking area, generates control instructions based on the environmental data, and controls the vehicle to park according to the control instructions, so that the towing object can be parked in the target parking area, thereby realizing automatic parking under the combination of the towing vehicle and the towing object, and improving the parking operation efficiency.
[0064] In some embodiments, see Figure 4 , generating a parking path for the vehicle based on environmental data, including:
[0065] Step S201, obtaining three-dimensional point cloud data of the vehicle;
[0066] Step S202, determining a parking path to a target parking area under driving restriction conditions according to the environmental data and the three-dimensional point cloud data; wherein the driving restriction conditions are used to ensure the stability of the vehicle during driving.
[0067] Compared with the parking process of a single vehicle, when the tractor and the towed object are driving together to park the towed object, it is necessary to consider not only the stability of the individual vehicles, but also the stability of the combination formed by the tractor and the towed object. For the sake of convenience, the combination formed when the tractor and the towed object are connected is referred to as the traction combination below.
[0068] Since the traction combination is composed of a tractor and a towing object, the towing object may be laterally offset or swing when being driven by the tractor, and the connection brings instability factors; and when the tractor drives the towing object, it will also be affected by the relative force of the towing object, which will also affect the stability of the tractor. Therefore, traditional path planning may cause the traction combination to have a risk of collision during movement, so more driving restrictions need to be considered to ensure the stability of the traction combination during driving. Therefore, in order to generate a parking path more accurately, the control device obtains the three-dimensional point cloud data of the vehicle, including the three-dimensional point cloud data of the tractor and / or the towing object. The three-dimensional point cloud data of the tractor and / or the towing object can be extracted by the control device from a pre-stored file, or can be obtained by scanning on-site through an acquisition device.
[0069] Among them, the driving parameters defined by the driving restriction conditions at least include the turning radius, reversing angle, and safe distance of the traction combination. The turning radius of the traction combination refers to the minimum distance from the outermost point of the traction combination to the center line of the turning path when the traction combination turns. For the combination of a tractor and a motorhome, due to the particularity of the body length and the connection method, its turning radius is usually larger than that of a single vehicle. Using the three-dimensional point cloud data of the vehicle, the turning radius of the traction combination at different angles can be accurately calculated. The reversing angle refers to the maximum reversing angle that can be achieved when the tractor and the towed object need to maintain relative positions through the connection device when reversing. When planning the parking route, this angle restriction must be taken into account to ensure that the tractor and the motorhome will not break the connection device or the vehicle will not lose control due to excessive angles during the reversing process. The maximum reversing angle is a calibrable value. Through the three-dimensional point cloud data of the vehicle, the relative position and angle change of the tractor and the motorhome when reversing can be simulated, so as to determine the safe reversing angle range. In order to prevent the tractor and the motorhome from colliding with other vehicles or obstacles during parking, a certain safety distance needs to be reserved when planning the route. When planning a parking route, it is necessary to ensure that the tractor and the RV can safely stop or avoid the tractor within this safe distance in any case. The actual size and shape of the tractor combination at different positions and angles can be accurately calculated through the 3D point cloud data of the vehicle. This information is combined with the position information of other vehicles and obstacles to determine the safe distance that needs to be reserved.
[0070] Specifically, the control device determines the surrounding environment of the target parking area based on the environmental data, including the size of the parking area, the distribution of surrounding obstacles, the location and size of obstacles, etc., and then determines the area that can be used to plan the parking path, that is, the planning area. In the planning area, the control device plans the parking path for the traction combination to travel to the target parking area based on the three-dimensional point cloud data of the vehicle and under the driving restrictions of the traction combination. The control device can use a variety of path planning algorithms, including but not limited to one or more of the A / A* algorithm, the artificial potential field method, the Dijkstra algorithm, etc. Therefore, the control device can find an optimal parking path from the starting point to the end point in a complex environment and ensure the safety and feasibility of the parking path.
[0071] Exemplarily, the control device determines the three-dimensional coordinates of the outermost point of the traction combination based on the three-dimensional point cloud data of the vehicle, and ensures that the distance between the outermost point and the three-dimensional coordinates of each point on other vehicles or obstacles is at least not less than the safety distance when planning the path, thereby satisfying the restriction condition of the reserved safety distance. For another example, the control device calculates the distance from the outermost point of the traction combination to the center line of the turning path in the horizontal direction based on the three-dimensional point cloud data of the vehicle when turning, and ensures that the distance is greater than the preset minimum angle, thereby satisfying the restriction condition of the turning radius. For another example, the control device calculates the relative angle between the tractor and the traction object when the traction combination is reversing based on the three-dimensional point cloud data of the vehicle, and ensures that the relative angle is less than the maximum reversing angle, thereby satisfying the restriction condition of the reversing angle.
[0072] Thus, after planning the parking path, the control device can control the tractor and the towed object to travel along the parking path to the target parking area. The control device determines whether the tractor is connected to the towed object, including but not limited to physical connection and circuit connection, and when confirming that the tractor is connected to the towed object, controls the tractor to travel along the parking path according to predetermined control parameters, so that the towed object also travels along the parking path. Figure 5 As shown, the control device controls the towing vehicle 201 to park the towing object 202 in the target parking area.
[0073] Among them, the control parameters refer to the parameters of the tractor's control drive system for driving. Since it is necessary to take into account factors such as the size, mass, center of mass, suspension system, and tire friction coefficient of the traction combination, the control device needs to simulate the control parameters during driving to ensure that the traction combination is safe and stable and the parking operation is completed efficiently. The control parameters include but are not limited to the control parameters under straight-line conditions and turning conditions. Straight-line conditions refer to the scenario in which the tractor outputs power to drag the traction object until it moves to a specified position in a straight-line driving scenario. Turning conditions refer to the tractor turning and driving the traction object to turn. Exemplarily, the control parameters include but are not limited to one or more of speed, acceleration, and steering angle. In addition, since the tractor is also affected by the resistance of the traction object, the control parameters may also include output torque to adjust the resistance caused by different traction objects.
[0074] In the above-mentioned vehicle parking method, by collecting environmental data of the target parking area and obtaining the three-dimensional point cloud data of the vehicle, the traction combination and the surrounding environment can be accurately perceived; according to the environmental data and the three-dimensional point cloud data, under the driving restriction conditions of the traction combination, a parking path to the target parking area is determined, and the physical characteristics of the tractor after being connected to the traction object, such as size characteristics, kinematic characteristics, etc., can be taken into account, thereby ensuring the accuracy of planning the parking path and ensuring the stability and safety of the traction combination; further, when it is confirmed that the tractor is connected to the traction object, the tractor is used to tow the traction object to travel along the parking path, so that the traction object is parked in the target parking area, thereby achieving safe parking of the traction combination and improving the parking operation efficiency.
[0075] While the tractor is towing the towing object along the parking path, the control device can also monitor the towing combination and the surrounding environment in real time, so as to ensure the stability and safety of the towing combination. To this end, in some embodiments, the method further includes: acquiring real-time driving data collected by the collection device; determining the real-time driving state of the vehicle according to the real-time driving data; and updating the remaining parking paths in the parking path when the real-time driving state does not meet the stability condition.
[0076] Taking the acquisition device as an aircraft as an example, specifically, the control device can use the aircraft to collect real-time data on the tractor, the towing object and the surrounding environment, for example, by flying the aircraft above the towing combination to collect real-time driving data. Real-time driving data includes but is not limited to the posture data of the tractor, the posture data of the towing object, and obstacle data. Among them, the posture data includes position and posture. Obstacle data includes the position and size of obstacles.
[0077] The stability condition is used to ensure the dynamic characteristics of the traction combination on the one hand, and to take into account the unexpected situations of the driving environment on the other hand. Exemplarily, the stability condition includes but is not limited to the distance between the traction combination and the obstacle being less than a preset distance, the lateral swing amplitude of the traction object relative to the driving direction being less than a preset amplitude, and the swing angle of the traction object relative to the tractor being less than a preset angle. To this end, the real-time driving state of the vehicle is determined based on the real-time driving data, including at least one of the following: determining the distance between the traction combination and the obstacle based on the posture data of the tractor, the posture data of the traction object, and the obstacle data; determining the lateral swing amplitude of the traction object relative to the driving direction based on the posture data of the traction object; and determining the swing angle of the traction object relative to a fixed reference object based on the posture data of the tractor and the posture data of the traction object.
[0078] Among them, the control device determines the distance between the traction combination and the obstacle through the posture data of the traction vehicle, the posture data of the traction object, and the obstacle data. The distance between the traction combination and the obstacle includes the distance between the traction vehicle and the traction object and the obstacle. Specifically, the control device can determine the distance between it and each point on the obstacle through the posture data of the traction vehicle and the posture data of the traction object, and then use the minimum distance as the distance between the traction combination and the obstacle, thereby judging whether the stability condition is met. Exemplarily, the control device can calculate the distance through the Euclidean algorithm and the like. The control device can calculate the swing angle of the traction object relative to a fixed reference object by comparing the point cloud data of the traction combination at two different time points or different positions, such as Figure 6 As shown, the fixed reference object is, for example, the driving direction, and the swing angle of the traction object 202 relative to the tractor 201 reflects the stability of the connection. Wherein, taking the due north direction as the reference and the counterclockwise rotation direction as the positive direction, the control device can calculate the swing angle θ=arctan(y / x) through the projection coordinates (x, y) of a certain feature point on the traction combination in the horizontal direction. The lateral swing can usually be determined by analyzing the displacement change of the feature points on the edge or wheel of the traction combination in the horizontal direction. At two consecutive time points t1 and t2, the control device can calculate the coordinates of a certain feature point Q on the edge of the traction combination body as (x1, y1, z1) and (x2, y2, z2) respectively. Then the control device can calculate the displacement change Δx of the feature point Q in the horizontal direction as Δx=x2-x1.
[0079] Therefore, judging the stability of the traction combination during movement based on real-time driving data can monitor the vehicle status in real time and help update the parking path in a timely manner, effectively improving the stability and safety of parking operations.
[0080] When the control device determines that the real-time driving state of the vehicle does not meet the stability condition, the remaining parking path in the parking path is updated. The updating process may involve recalculating the optimal parking path, taking into account factors such as the current position of the towing combination, obstacles in the surrounding environment, and driving restrictions that need to be complied with. The updated parking path should meet the stability condition and be able to safely and efficiently park the towing object into the target parking area.
[0081] In the above embodiment, by real-time monitoring and analysis of the vehicle's driving status and environmental conditions, the system can promptly detect and respond to any factors that may affect parking stability, and ensure that the vehicle safely completes parking along the optimal route by updating the parking path, thereby avoiding accidents or collisions that may occur due to unstable driving conditions.
[0082] In some embodiments, the control device determines a parking path for the tractor to travel to a target parking area based on environmental data and three-dimensional point cloud data under driving restrictions, including: establishing a three-dimensional map based on the environmental data, and establishing a three-dimensional model of the vehicle based on the three-dimensional point cloud data; determining a planned area in the three-dimensional map, and within the planned area, determining a parking path for the tractor to travel to the target parking area based on the three-dimensional model of the vehicle under driving restrictions.
[0083] Specifically, after receiving the environmental data, the control device processes and fuses the acquired environmental data to establish a high-precision three-dimensional map that reflects the terrain and road layout in the real world. At the same time, the control device preliminarily generates a three-dimensional model of the vehicle based on the three-dimensional point cloud data of the vehicle through three-dimensional reconstruction algorithms such as voxelization, polygonization or surface fitting. The three-dimensional model includes but is not limited to the overall shape, windows, doors, hooks and other structural details of the traction combination. In some embodiments, since the generated three-dimensional model may still have problems such as noise points, discontinuous areas and holes, the control device can optimize the model quality through a series of post-processing operations such as filtering, smoothing, and filling holes. In addition, the control device also needs to further refine the model based on the actual physical properties of the traction combination. The actual physical properties include material properties (rigid materials or non-rigid materials, etc.) of the connecting device, physical size constraints, etc. In order to achieve the purpose of precise parking, the control device can also scale and calibrate the three-dimensional model of the vehicle based on a calibration plate with known physical dimensions or measured data to ensure that the model size is consistent with the actual object and consistent with the scale of the three-dimensional map. Then, the control device determines the planning area in the three-dimensional map, which is the available area after removing the space occupied by obstacles. In the planning area, the control device determines the parking path for the tractor to travel to the target parking area under driving restriction conditions based on the size of the traction combination represented by the three-dimensional model of the vehicle. The control device can use a variety of path planning algorithms, including but not limited to one or more of the A algorithm, artificial potential field method, Dijkstra algorithm, etc. Thus, the control device can find an optimal parking path from the starting point to the end point in a complex environment and ensure the safety and feasibility of the parking path.
[0084] In the above embodiment, a planning area that can be used for planning a path is determined with the help of a high-precision three-dimensional map, and within the planning area, by considering driving restrictions and the three-dimensional model of the vehicle, parking path planning can be accurately performed to prevent collisions and accidents and ensure the safety of parking operations.
[0085] In some embodiments, based on the three-dimensional model of the vehicle and under driving restriction conditions, a parking path for the tractor to travel to the target parking area is determined, including: dividing the planning area into multiple grids, determining a starting grid where the tractor combination is located, and a terminal grid where the target parking area is located; determining multiple candidate grids based on a safety distance; based on a turning radius and a reversing angle, starting from the starting grid, sequentially determining multiple target grids from the multiple candidate grids; wherein the first target grid in the target grids is connected to the starting grid, and the last target grid is connected to the terminal grid; based on the starting grid, the multiple target grids, and the terminal grid, determining a parking path for the tractor to travel to the target parking area.
[0086] Specifically, the control device divides the entire planning area into multiple grids, each of which can represent an area of a fixed size, so as to facilitate path planning. Among them, the grid where the starting position of the traction combination is located is the starting grid, and the grid where the target parking area is located is the end grid, that is, the position where the traction object is finally parked. Based on the safety distance, the control device further filters and screens the divided grids to obtain multiple candidate grids to meet the distance margin requirements between the traction combination and the obstacle. Subsequently, parking path planning is performed in these candidate grids. Then, based on the restrictions of turning radius and reversing angle, the control device determines the next grid connected to the starting grid starting from the starting grid, and the next grid can make the traction combination start from the actual position corresponding to the starting grid and drive to the grid to meet the restrictions of turning radius and reversing angle. Thus, multiple target grids passed in the middle are determined in sequence until the end grid is reached. Thus, the control device can connect the starting grid, multiple target grids and the end grid in sequence based on the starting grid, multiple target grids and the end grid, so as to determine the parking path for the tractor to drive to the target parking area. Depending on the size and characteristics of the specific site, the control device can adjust the size and number of grids to adapt to different parking needs and environmental conditions.
[0087] In the above embodiment, accurate grid division and path planning can ensure that the tractor moves in the most efficient and safe way to avoid collision with obstacles. In addition, the algorithm automatically calculates the path, which improves the efficiency and accuracy of the parking process.
[0088] On the basis of the above embodiment, starting from the starting grid, multiple target grids are determined in sequence from multiple candidate grids, including: determining the candidate grids around the starting grid in the current round, and respectively determining the distance costs corresponding to each candidate grid; taking the candidate grid corresponding to the minimum distance cost as the starting grid in the next round, and returning to the step of determining the candidate grids around the starting grid to continue executing until the candidate grid corresponding to the minimum distance cost is the end grid; taking the candidate grid corresponding to the minimum distance cost determined in each round as the determined multiple target grids.
[0089] Specifically, the control device determines the target grid in turn in multiple rounds. In each round, the control device determines the candidate grids around the current starting grid according to the restrictions of the turning radius and the reversing angle. The restrictions of the turning radius and the reversing angle can limit the direction of selecting the surrounding candidate grids. For example, without the restrictions of the turning radius and the reversing angle, the control device can determine the candidate grids around the current starting grid from multiple angles such as the east, southeast, south, southwest, west, northwest, and north. However, under the restrictions of the turning radius and the reversing angle of the current starting grid, the direction of the candidate grid selected by the control device is limited, for example, the candidate grids around it can only be determined from the angles of the east, southeast, and south.
[0090] After determining multiple candidate grids, the control device calculates the distance cost of each candidate grid respectively. The distance cost is used to evaluate the distance loss of each candidate grid, which is used as an indicator basis for selecting one of the candidate grids as the target grid.
[0091] In some embodiments, for any candidate grid, the control device calculates the first distance cost and the second distance cost corresponding to the candidate grid respectively, and determines the distance cost of the candidate grid according to the first distance cost and the second distance cost. Exemplarily, for any candidate grid, its distance cost is the sum of the first distance cost and the second distance cost. Among them, the first distance cost represents the distance between the candidate grid and the initial starting grid, and the second distance cost represents the distance between the candidate grid and the end grid. By considering the distance cost, the moving path of the traction combination can be shortened as much as possible in the planning. Then, the control device determines the minimum value of the calculated distance cost, that is, the minimum distance cost, from multiple candidate grids, and uses the candidate grid corresponding to the minimum distance cost as the starting grid of the next round. If the candidate grid corresponding to the minimum distance cost is the end grid, the path planning is stopped. Repeat the above steps until the determined starting grid is the end grid. In this way, the parking path from the starting position to the target parking area can be gradually determined. In the above embodiment, by considering the distance cost of the candidate grid in each round, the shortest path can be planned, thereby optimizing the parking path and improving the parking efficiency.
[0092] Of course, due to the complexity of the actual parking environment, it is possible that the parking path of the tractor to the target parking area cannot be determined under the driving restriction conditions. To this end, the above method also includes: when the parking path of the tractor to the target parking area cannot be determined under the driving restriction conditions based on the three-dimensional model of the vehicle, re-determining the target parking area.
[0093] Specifically, when the control device cannot determine the parking path for the tractor to drive to the target parking area in the planning area according to the driving restrictions and the three-dimensional model of the vehicle, the available parking area can be re-evaluated according to the current environmental conditions. Alternatively, if the map data is updated or adjusted, the control device can also re-measure on-site through the aircraft to update the map information, thereby re-determining the target parking area. Then, based on the re-determined target parking area, the control device uses the path planning algorithm to recalculate a suitable parking path to ensure that the driving restrictions of the tractor combination are met.
[0094] In the above embodiment, by re-determining the target parking area and re-planning the parking path, the system can avoid parking path planning failures caused by environmental or driving restrictions, thereby improving the reliability and safety of parking operations. In particular, under complex or narrow road conditions, re-determining the target parking area and path can effectively cope with challenges and make parking operations more reliable and controllable.
[0095] Whether the target parking area is determined for the first time or the target parking area is determined again, it can be determined by a user manually triggering or the system automatically triggering. To this end, in some embodiments, the method further includes: in response to a search instruction for a parking area, determining one or more free parking areas within a given range; in response to a trigger operation for the one or more free parking areas, determining the target parking area from the one or more free parking areas.
[0096] Specifically, the user can send a search instruction to the control device by touching the vehicle terminal, or the mechanical buttons on the vehicle, or by operating a mobile phone, a computer, etc., and the search instruction is used to instruct the control device to search for parking areas in a given area. Then, the control device responds to the search instruction for the parking area and searches in the given area to determine one or more free parking areas. The control device can automatically determine the target parking area from the one or more free parking areas. Thus, the utilization rate of the parking lot can be maximized by instantly searching and selecting the free parking area, ensuring the effective allocation and management of resources. Alternatively, the control device can display the one or more free parking areas to the user through a vehicle terminal, a mobile phone, a computer, etc., and the user can select the target parking area through a trigger operation such as touch, click, long press, etc. Thus, the control device responds to the trigger operation for one or more free parking areas, determines the free parking area selected by the user from the one or more free parking areas, and uses it as the target parking area.
[0097] In the above embodiment, by instantly responding to the user's parking search command, the free parking area within a given range is quickly determined, thereby reducing the user's waiting time and improving the efficiency of the parking operation; and the target parking area is determined according to the user's trigger operation, taking into account the user's needs and actual conditions, ensuring that the user can quickly find a suitable parking location, and further optimizing the user's parking experience.
[0098] After the tractor tows the towed object to the target parking area, the method further includes: when the towed object is located in the target parking area, controlling the tractor to separate from the towed object so that the towed object is parked in the target parking area.
[0099] Specifically, when it is determined that the towing object is located in the target parking area, the control device issues a control instruction to control the tractor to separate from the towing object, such as unlocking or contacting the connection by a motor or electric device, or releasing pressure by a pneumatic cylinder to promote separation, so that the towing object is parked in the target parking area. According to actual conditions, the tractor and the towing object can also be separated manually. The control device can send a control instruction to the tractor to implement the separation operation; if the towing object has an intelligent function, such as the towing object has an intelligent control module, the control device can also control the towing object itself to implement the separation operation. During the separation process, the control device can also monitor the connection status of the tractor and the towing object in real time through the aircraft, so as to ensure the safe distance between the front and rear vehicles during the separation process with the help of the aircraft for auxiliary observation, and ensure that the separation process is carried out smoothly.
[0100] In the above embodiment, the towing vehicle and the towing object are separated by automatically controlling the towing vehicle so that the towing object can be accurately parked in the target parking area without manual intervention.
[0101] Furthermore, when the towing object is, for example, an RV, it needs to be docked with camp facilities (such as drainage facilities, electrical facilities, etc.) in some scenarios. To this end, in some embodiments, after the target vehicle is parked in the target parking area, the method further includes: adjusting the posture of the towing object so that the towing object can be docked with the docking facilities in the target parking area. Specifically, the control device automatically performs the posture adjustment operation according to the data collected by the sensor or the aircraft and the preset docking algorithm. Among them, the posture adjustment operation includes but is not limited to adjusting the position and angle of the towing object. The control device can control the towing vehicle to adjust the posture of the towing object before separation, or control the towing object to adjust its own posture after separation (the towing object itself needs to have a posture adjustment function), so that the towing object can be accurately docked with the docking facilities in the target parking area.
[0102] In the above embodiment, the posture adjustment mechanism is used to ensure that the towing object can accurately and quickly dock with the docking facilities in the target parking area, thereby greatly improving the efficiency and speed of the parking operation.
[0103] In the embodiments of the present application, the three-dimensional point cloud data is collected by the aircraft to establish a three-dimensional model, which can perform a global scan of the tractor / towing object, thereby improving the comprehensiveness and accuracy of the data. To this end, in some embodiments, the three-dimensional point cloud data of the vehicle is obtained, including: flying above the towing assembly through the acquisition device to collect first point cloud data of the top surface of the towing assembly; flying around the towing assembly according to a preset trajectory through the acquisition device to collect second point cloud data of the side of the towing assembly; based on the first point cloud data and the second point cloud data, the three-dimensional point cloud data of the vehicle is obtained.
[0104] Specifically, taking the acquisition device as an aircraft as an example, Figure 7 As shown, the control device controls the aircraft to fly above the traction assembly, and scans and measures the traction assembly through sensors such as laser radar or cameras to obtain the point cloud data collected from the top to the bottom, that is, the first point cloud data, to construct the geometric shape of the top of the object. The first point cloud data includes the point cloud data of the top plane of the traction assembly. Then, the control device controls the aircraft to perform multi-angle and multi-directional scanning around the object according to the preset trajectory, and collects point cloud data on all sides of the vehicle body, that is, the second point cloud data. The second point cloud data can provide side information of the traction assembly, including its contour, surface details, etc. Therefore, the control device can combine the first point cloud data and the second point cloud data, and generate a complete three-dimensional point cloud model of the traction assembly through point cloud registration and fusion algorithms. This model reflects the overall shape and structure of the traction assembly.
[0105] It should be noted that the control device can scan the tractor and the towing object respectively to collect point cloud data, obtain the three-dimensional point cloud models of the two respectively, and then obtain the three-dimensional model of the vehicle according to the three-dimensional cloud models of the tractor and the towing object. The above method can be applied to the scanning process of either the tractor or the towing object.
[0106] In the above embodiment, the point cloud data collected from different angles by the acquisition device can provide multi-dimensional information, including data on the top, side and other aspects, which helps to accurately describe the shape and structural characteristics of the towing object. In addition, the non-contact point cloud data collection by the acquisition device avoids contact damage or interference that may occur in traditional measurement methods, effectively avoids the problem of inaccurate data caused by blind spots, and improves the efficiency and safety of data collection.
[0107] Among them, in order to obtain more comprehensive and accurate data, the acquisition device flies around the traction object according to a preset trajectory to collect the second point cloud data of the side of the traction object, including: determining at least one flight altitude and at least one flight angle; the acquisition device flies around the traction object at each flight altitude and at least one flight angle to collect the second point cloud data of the side of the traction object.
[0108] Specifically, the control device pre-sets at least one flight height and at least one flight angle. Assume that the control device determines two flight heights, namely height h1 and height 2; and determines several flight angles, including angle A, angle B, angle C, and angle D. Exemplarily, height h1 can be set to the center height of the towing object, and height h2 can be slightly higher or slightly lower than the towing object to obtain different viewing angles and coverage. Each flight angle can be set as a deflection angle of the flight trajectory. For example, angle A can be around the front side of the towing object, angle B can be a slightly downward angle... and so on.
[0109] Then, the control device controls the acquisition device to fly around the towing object at each flight height according to the set flight angle, and collects the second point cloud data of its side at different heights and different angles. Figure 8 As shown, at height h1, the acquisition device flies around the towing object at angle A to collect the side data at angle A. At height h1, the acquisition device flies around the towing object at angle B to obtain the side data at angle B. Then, at height h2, the acquisition device flies around the towing object at angles C and D respectively to collect the second point cloud data of the side at different angles. This circling process may include multiple flight paths at different heights and angles, and can comprehensively utilize multi-angle and multi-height point cloud data to more accurately analyze the geometric features, volume, surface quality and other parameters of the towing object to ensure that sufficient information is collected for complete reconstruction of the object's three-dimensional model.
[0110] In the above embodiment, by setting different flight altitudes and flight angles, the side information of the towing object can be captured from more angles and perspectives. Each choice of flight altitude and angle can cover different sides of the towing object, ensuring the integrity and comprehensiveness of the data, thereby avoiding data loss or omission of key information, thereby improving the accuracy and reliability of subsequent modeling.
[0111] The detection method of the acquisition device mentioned in the embodiment of the present application is also applicable to other external sensors such as robots and cameras. The external sensor needs to have the ability of comprehensive or combined scanning.
[0112] In a specific embodiment, taking the towing object as a trailer RV and the collection device as an aircraft as an example, Fig. 9As shown, the overall process of the vehicle parking method provided in the embodiment of the present application includes the following steps:
[0113] Step S301, aircraft scanning.
[0114] Before entering the parking lot or campsite, the control device can control the aircraft to take off first, and use the camera, laser radar or 3D point cloud scanning device carried by the aircraft to fully scan the target parking area to obtain information such as terrain, obstacles and parking space size. The aircraft can instantly transmit this data to the on-board computing system or cloud server connected to the RV for processing. At the same time, the aircraft can also scan the traction combination to obtain the 3D point cloud data of the vehicle.
[0115] Step S302: space modeling and path planning.
[0116] The control device can generate an accurate three-dimensional map based on the data collected by the aircraft, and model the towing combination based on the collected three-dimensional point cloud data to obtain a three-dimensional model of the vehicle. As a result, the control device can calculate the optimal driving path and parking position of the trailer RV and the tractor, taking into account factors including but not limited to the overall length, width, turning radius of the RV, and the distance requirements from other vehicles and buildings.
[0117] Step S303: dynamic guidance and monitoring.
[0118] When the tractor starts to perform parking operations, the aircraft can provide a dynamic perspective in the air, monitor the surrounding environment changes in real time, and provide real-time feedback to the control device to ensure that the safety distance and other key parameters are within a reasonable range. If the aircraft has the ability to plan the path, the aircraft can guide the driver through wireless communication technology or directly send feedback to the control device to help the towed object complete accurate parking.
[0119] Step S304: precise docking and separation.
[0120] After the initial tractor docking, if the trailer has intelligent functions, the control device can also use the aircraft to assist in fine-tuning the position of the trailer to accurately dock with the camp facilities. The separation operation can also be assisted by the aircraft for observation and guidance to ensure a safe distance between the front and rear vehicles and a smooth separation process.
[0121] Among them, in the above step S301, if Fig.10 As shown, the steps of aircraft scanning may include:
[0122] Step S3011, initializing the global coordinate system. Before scanning, the control device must first establish a reliable global coordinate system as a reference. The control device can initialize the flight through the aircraft, obtain the current position, and combine the geomagnetic data and other landmark information to create an accurate three-dimensional space.
[0123] Step S3012, top scan and surround scan. The aircraft first flies to the top of the trailer, and uses a downward vertical perspective to perform a high-precision scan of the top of the object, capturing high-density point cloud data to construct the geometric shape of the top of the object. Then, the aircraft performs a multi-angle and multi-directional surround scan around the object according to the preset trajectory, collecting point cloud data on all sides of the vehicle body. By combining the top scan and surround scan of the aircraft, multiple scans are performed on the dragged object to obtain the complete point cloud coordinates of the object, build a three-dimensional model of the object, and complete the overall combination with the car model, ensuring the accuracy of the object size and reducing the risk of collision.
[0124] Among them, in the above step S302, if Fig.11 As shown, the steps of spatial modeling and path planning may include:
[0125] Step S3021, point cloud generation and RV modeling. The control device generates a preliminary 3D model of the trailer RV using a 3D reconstruction algorithm, such as voxelization, polygonization or surface fitting, for the collected 3D point cloud data. This model includes but is not limited to the overall shape, windows, doors, hooks and other structural details of the trailer RV, ensuring a detailed representation of the physical characteristics of the RV.
[0126] Step S3022, model optimization and calibration. Since the preliminary model may have problems such as noise points, discontinuous areas and holes, the control device can optimize the model quality through a series of post-processing operations such as filtering, smoothing, and filling holes. At the same time, the model is further refined according to the actual physical properties of the object. In order to achieve the purpose of precise parking, the model must also strictly match the actual physical size. The control device can scale and calibrate the model based on a calibration plate with known physical dimensions or measured data to ensure that the model size is consistent with the actual object.
[0127] Step S3023, deduce the motion model. Based on the dynamic characteristics of the tractor and the trailer caravan, the control device establishes a kinematic model of the coupling of the tractor and the trailer caravan. This model takes into account factors such as the mass, center of mass, suspension system, and tire friction coefficient of the vehicle, and simulates the dynamic response of the traction combination under various driving conditions. Using the above model, the control device can predict how the tractor and trailer caravan will respond as a whole under different speeds, accelerations, and steering conditions, and calculate the optimal control parameters to minimize the swing amplitude or swing angle of the traction combination, etc., to ensure a safe and efficient driving path. Therefore, for the non-rigid connection between the vehicle body and the towing object, the aircraft scans the connection posture during movement, and deduces the motion model for this traction scenario. At the same time, when the vehicle is running, the aircraft monitors the traction operation status in real time in the air to solve the problem of poor dynamic stability.
[0128] Step S3024, generating a parking path. The control device plans a parking path suitable for the tractor and the RV to travel together based on the parking path planning algorithm. This path should take into account the driving restrictions such as the turning radius, reversing angle and safety distance of the trailer combination.
[0129] Among them, in the above step S303, the steps of dynamic guidance and monitoring may include:
[0130] Step S3031, real-time monitoring by the aircraft. During the driving and parking of the towing combination, the aircraft can be used for aerial monitoring. Since the aircraft is equipped with a camera and / or other sensors, it can transmit the position data of the tractor and the trailer caravan, and the real-time obstacle data of the surrounding area in real time. Then, the control device analyzes the driving status of the tractor and the caravan, including parameters such as vehicle distance, angle change, and lateral swing, to ensure that the vehicle combination remains stable during driving and turning, and also provides real-time feedback for subsequent path planning. Therefore, the aircraft, as an extension of the vehicle body sensor, performs environmental perception and verification throughout the entire process. When faced with suspicious obstacles that suddenly appear behind the towed object, the aircraft sensor will not be abnormally blocked, and can immediately perceive the environment and control the vehicle end to brake, greatly improving the accuracy of environmental perception.
[0131] Among them, Fig.12 As shown, before the above step S301 (such as Fig.12 ), or after step S302 and before step S303 (as shown in (a) in FIG. Fig.12 As shown in (b) above), the above method may further include the following steps:
[0132] Step S300, trailer connection. This stage first involves the physical trailer connection, including the correct docking of the tractor and the trailer caravan. For example, the hook of the tractor can be safely connected to the towing device of the trailer caravan through manual operation by the user or automatic operation of the tractor / towing object, while ensuring that the electrical system (such as brake lights and turn signal lines) are successfully docked through the corresponding wiring harness to ensure that the communication and safety functions between vehicles during driving are normal. After the connection is completed, the control device can confirm the connection through the on-board controller to detect whether the circuit connection is normal. It will also check the linkage of the brake system of the trailer caravan to ensure that all necessary safety mechanisms in the towing mode have been activated.
[0133] In a specific implementation scenario, still taking the towing object as a trailer RV as an example, Fig.13 As shown, the process of the vehicle parking method provided in the embodiment of the present application includes the following steps:
[0134] Step S401, select the trailer caravan. On the vehicle interface, the user selects to start the "trailer mode" through the touch screen button or menu option, and the control device (for example, the vehicle terminal) guides the user to perform a series of interactive operations to confirm the relevant parameters of the trailer caravan. These parameters are crucial for subsequent motion model calculation and path planning. The user may also need to input or select a pre-stored configuration file of the trailer caravan in the system so that the control device can refer to the preset and quickly plan the parking path.
[0135] Step S402, vehicle control connection. On the vehicle computer interface, when the physical connection between the tractor and the trailer caravan is actually completed (such as hooks, brake lines, light signal lines, etc.), the vehicle computer will prompt the user to perform a connection test on the electronic system. The user can follow the instructions on the screen, and the control device will automatically or manually verify the connection status, such as whether the detection circuit is connected, and whether the brake lights, turn signals, etc. are synchronized. If everything is normal, the vehicle computer screen will display a prompt of "Connection successful", and the corresponding icon may light up, indicating that the automatic parking program is ready.
[0136] Step S403: Self-selected parking position. The user can manually select the target parking space by touching the screen, or allow the control device to automatically search for available parking spaces through panoramic view, satellite map, etc. The screen will display a three-dimensional or two-dimensional bird's-eye view of the vehicle's surrounding environment, on which the user can specify an ideal parking spot, or accept the best parking spot recommended by the control device. After selection, the control device will begin to plan a precise parking path from the current position to the parking space.
[0137] Step S404: Execute the automatic parking program. After completing the parking space selection, the user starts the parking program. At this time, the vehicle will ask for further confirmation, such as selecting the "automatic parking" or "start execution" function key. After receiving the command, the control device begins to gradually control the movement of the tractor according to the previously planned route and control parameters, thereby driving the trailer RV to move. During this period, there will be voice prompts to guide the user to release the steering wheel and pedals, and the automatic driving system will take over the control of the vehicle. The vehicle display screen will display the vehicle's driving route, estimated remaining time and current vehicle posture in real time until the entire parking process is successfully completed. During the parking process, if an emergency (such as an obstacle, other vehicles, etc.) is encountered, the control device determines the distance to the obstacle through the aircraft and body sensors, and changes the remaining parking path.
[0138] Based on the same inventive concept, the embodiment of the present application also provides a vehicle parking device for implementing the vehicle parking method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more vehicle parking device embodiments provided below can refer to the limitations of the vehicle parking method above, and will not be repeated here.
[0139] In one embodiment, Fig.14 As shown, a vehicle parking device is provided, which can be integrated in a control device, including: an acquisition module 1401 and a control module 1402, wherein:
[0140] The acquisition module 1401 is used to acquire the environmental data of the target parking area collected by the collection device, wherein the collection device and the vehicle can be separated; the vehicle includes a tractor and a tractor object connected to each other.
[0141] The control module 1402 is used to generate a control instruction according to the environmental data, and control the vehicle to park according to the control instruction so that the towed object is parked in the target parking area.
[0142] In some embodiments, the control module is further used to generate a parking path for the vehicle based on the environmental data, and generate a control instruction carrying the parking path; and control the vehicle to park according to the parking path.
[0143] In some embodiments, the control module is also used to obtain three-dimensional point cloud data of the vehicle; based on the environmental data and the three-dimensional point cloud data, under driving restriction conditions, determine a parking path to the target parking area; wherein the driving restriction conditions are used to ensure the stability of the vehicle during driving.
[0144] In some embodiments, the above-mentioned device also includes a monitoring module for acquiring real-time driving data collected by the collection device; determining the real-time driving status of the vehicle based on the real-time driving data; when the real-time driving status does not meet the stability condition, updating the remaining parking paths in the parking path.
[0145] In some embodiments, the real-time driving data includes at least one of the posture data of the tractor, the posture data of the towing object, and the obstacle data; the monitoring module is further used to determine the distance between the traction combination and the obstacle based on the posture data of the tractor, the posture data of the towing object, and the obstacle data; determine the lateral swing amplitude of the towing object relative to the driving direction based on the posture data of the towing object; or determine the swing angle of the towing object relative to a fixed reference object based on the posture data of the tractor and the posture data of the towing object.
[0146] In some embodiments, the control module is also used to establish a three-dimensional map based on the environmental data, and to establish a three-dimensional model of the vehicle based on the three-dimensional point cloud data; determine a planning area in the three-dimensional map, and within the planning area, based on the three-dimensional model of the vehicle and under driving restrictions, determine a parking path for the tractor to travel to the target parking area.
[0147] In some embodiments, the driving parameters defined by the driving restriction condition include at least a turning radius, a reversing angle, and a safety distance; the control module is further used to divide the planning area into a plurality of grids, determine a starting grid where the traction combination is located, and a terminal grid where the target parking area is located; based on the safety distance, determine a plurality of candidate grids; based on the turning radius and the reversing angle, starting from the starting grid, determine a plurality of target grids in sequence from the plurality of candidate grids; wherein the first target grid in the target grids is connected to the starting grid, and the last target grid is connected to the terminal grid; based on the starting grid, the plurality of target grids, and the terminal grid, determine a parking path for the tractor to travel to the target parking area.
[0148] In some embodiments, the control module is also used to determine the candidate grids around the starting grid in the current round, and respectively determine the distance costs corresponding to each candidate grid; the candidate grid corresponding to the minimum distance cost is used as the starting grid in the next round, and returns to the step of determining the candidate grids around the starting grid to continue executing until the candidate grid corresponding to the minimum distance cost is the end grid; the candidate grid corresponding to the minimum distance cost determined in each round is used as the determined multiple target grids.
[0149] In some embodiments, the apparatus further comprises a redefinition module for redefining the target parking area when a parking path for the tractor to travel to the target parking area cannot be determined based on the three-dimensional model of the vehicle under driving restriction conditions.
[0150] In some embodiments, the above-mentioned device also includes a response module for determining one or more free parking areas within a given range in response to a search instruction for a parking area; and determining a target parking area from the one or more free parking areas in response to a trigger operation for the one or more free parking areas.
[0151] In some embodiments, the apparatus further comprises a separation module, which is used to control the tractor to separate from the tractor when the tractor is located in the target parking area, so that the tractor is parked in the target parking area.
[0152] In some embodiments, the above-mentioned device further includes an adjustment module, which is used to adjust the posture of the towing object so that the towing object can dock with the docking facility in the target parking area.
[0153] In some embodiments, the three-dimensional point cloud data of the vehicle includes the three-dimensional point cloud data of the tractor and the three-dimensional point cloud data of the towing object; the acquisition module is also used to fly above the towing combination through the aircraft to collect first point cloud data of the top surface of the towing combination; fly around the towing combination according to a preset trajectory through the aircraft to collect second point cloud data of the side of the towing combination; based on the first point cloud data and the second point cloud data, the three-dimensional point cloud data of the vehicle is acquired.
[0154] In some embodiments, the acquisition module is also used to determine at least one flight altitude and at least one flight angle; the second point cloud data of the side of the traction assembly is collected by the aircraft flying around the traction assembly at each flight altitude and at least one flight angle.
[0155] Each module in the above-mentioned devices can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of the processor in the control device in the form of hardware, or can be stored in the memory in the control device in the form of software, so that the processor can call and execute the operations corresponding to each module above.
[0156] In some embodiments, a control device is provided, whose internal structure diagram can be as follows: Fig.15As shown. The control device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the control device is used to provide computing and control capabilities. The memory of the control device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the control device is used to exchange information between the processor and an external device. The communication interface of the control device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a vehicle data reporting method is implemented.
[0157] Optionally, the control device further includes a display unit. The display unit of the control device is used to form a visually visible picture, and may be a display screen, a projection device, or a virtual reality imaging device. The display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device of the control device may be a touch layer covered on the display screen, or a key, trackball, or touchpad provided on the housing of the control device, or an external keyboard, touchpad, or mouse, etc.
[0158] Those skilled in the art will understand that Fig.15 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the control device to which the scheme of the present application is applied. The specific control device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The processor involved in each embodiment provided in this application can be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but is not limited thereto.
[0160] In some embodiments, a control device is also provided, including a memory and a processor, wherein a plurality of instructions are stored in the memory, and the processor loads instructions from the memory to execute and implement the steps in the above-mentioned method embodiments.
[0161] In some embodiments, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for a processor to load to execute and implement the steps in the above-mentioned method embodiments.
[0162] In some embodiments, a computer program product is provided, including a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.
[0163] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0164] The above are only preferred embodiments of the present application and do not constitute any form of limitation to the present application. Although the descriptions of each embodiment in the present application have different focuses, for the parts not described in detail in a certain embodiment, reference can be made to the relevant embodiments of other embodiments. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.
Claims
1. A vehicle parking system, characterized in that: The system comprises: A collection device for collecting environmental data of a target parking area, wherein the collection device and the vehicle can be separated; the vehicle includes a tractor and a tractor object connected to each other; A control device, which is in communication with the acquisition device, and is used to generate a control instruction according to the environmental data, and control the vehicle to park according to the control instruction; Wherein, generating a control instruction according to the environmental data includes: generating a parking path of the vehicle according to the environmental data, and generating a control instruction carrying the parking path; The controlling the vehicle to park according to the control instruction includes: controlling the vehicle to park according to the parking path; Generating the parking path of the vehicle according to the environmental data includes: acquiring three-dimensional point cloud data of the vehicle; determining a parking path to the target parking area under driving restriction conditions according to the environmental data and the three-dimensional point cloud data; The driving restriction condition is used to ensure the stability of the vehicle during driving, and the driving restriction condition includes: the distance from the outermost point of the vehicle to the center line of the turning path in the horizontal direction is greater than a preset minimum distance, and / or the relative angle between the tractor and the towed object when the vehicle is reversing is less than a maximum reversing angle, and the reversing angle refers to the maximum reversing angle that can be achieved when the tractor and the towed object need to maintain relative positions through a connecting device when reversing, and the maximum reversing angle is a calibrable value; Determining a parking path to the target parking area based on the environmental data and the three-dimensional point cloud data under driving restriction conditions includes: establishing a three-dimensional map based on the environmental data, and establishing a three-dimensional model of the vehicle based on the three-dimensional point cloud data; determining a planning area in the three-dimensional map, and determining a parking path to the target parking area based on the three-dimensional model of the vehicle under driving restriction conditions within the planning area; The driving parameters defined by the driving restriction condition at least include a turning radius, a reversing angle, and a safety distance; the determining a parking path for driving to the target parking area under the driving restriction condition based on the three-dimensional model of the vehicle includes: dividing the planning area into a plurality of grids, determining a starting grid where the vehicle is located, and a terminal grid where the target parking area is located; determining a plurality of candidate grids based on the safety distance; and determining a plurality of target grids in sequence from the starting grid based on the turning radius and the reversing angle among the plurality of candidate grids; wherein the first target grid among the target grids is connected to the starting grid, and the last target grid is connected to the terminal grid; and determining a parking path for the towing vehicle to drive to the target parking area based on the starting grid, the plurality of target grids, and the terminal grid.
2. The vehicle parking system according to claim 1, characterized in that: The collection device is an aircraft carrying a collection device, or a mobile robot carrying a collection device.
3. The vehicle parking system according to claim 2, characterized in that: The acquisition device is one or more of a camera and a three-dimensional point cloud scanning device.
4. The vehicle parking system according to claim 1, characterized in that: The control device includes a first data calculation module. When the vehicle performs parking, the collection device is used to collect real-time driving data of the vehicle, and the first data calculation module is used to generate a parking correction instruction according to the real-time driving data.
5. The vehicle parking system according to claim 4, characterized in that: The first data calculation module is used to determine the real-time driving status of the tractor and the towing object according to the real-time driving data; when the real-time driving status indicates that the vehicle does not meet the stability condition, generate a parking correction instruction.
6. The vehicle parking system according to claim 1, characterized in that: The control device is mounted on the vehicle, or the control device is communicatively connected to the vehicle.
7. The vehicle parking system according to claim 1, characterized in that: The environmental data includes at least one of terrain data, obstacle data, and parking space size data.
8. The vehicle parking system according to claim 6, characterized in that: The control device further includes a second data calculation module, which is used to generate a map model according to the environmental data; and / or the second data calculation module is used to generate a parking path for the vehicle according to the environmental data.
9. The vehicle parking system according to claim 8, characterized in that: The second data calculation module is used to obtain the driving restriction conditions of the vehicle and generate a parking path of the vehicle according to the environmental data under the constraints of the driving restriction conditions.
10. The vehicle parking system according to claim 8, characterized in that: The traction object is provided with an intelligent control module, and the intelligent control module is used to control the combination or separation of the traction object and external equipment according to the environmental data.
11. A vehicle parking method, characterized in that: The method comprises: Acquiring environmental data of a target parking area collected by a collection device, wherein the collection device and the vehicle are detachably arranged; the vehicle comprises a tractor and a tractor object connected to each other; generating a control instruction according to the environmental data, and controlling the vehicle to park according to the control instruction so that the towed object is parked in the target parking area; Wherein, generating a control instruction according to the environmental data includes: generating a parking path of the vehicle according to the environmental data, and generating a control instruction carrying the parking path; The controlling the vehicle to park according to the control instruction includes: controlling the vehicle to park according to the parking path; Generating the parking path of the vehicle according to the environmental data includes: acquiring three-dimensional point cloud data of the vehicle; determining a parking path to the target parking area under driving restriction conditions according to the environmental data and the three-dimensional point cloud data; The driving restriction condition is used to ensure the stability of the vehicle during driving, and the driving restriction condition includes: the distance from the outermost point of the vehicle to the center line of the turning path in the horizontal direction is greater than a preset minimum distance, and / or the relative angle between the tractor and the towed object when the vehicle is reversing is less than a maximum reversing angle, and the reversing angle refers to the maximum reversing angle that can be achieved when the tractor and the towed object need to maintain relative positions through a connecting device when reversing, and the maximum reversing angle is a calibrable value; Determining a parking path to the target parking area based on the environmental data and the three-dimensional point cloud data under driving restriction conditions includes: establishing a three-dimensional map based on the environmental data, and establishing a three-dimensional model of the vehicle based on the three-dimensional point cloud data; determining a planning area in the three-dimensional map, and determining a parking path to the target parking area based on the three-dimensional model of the vehicle under driving restriction conditions within the planning area; The driving parameters defined by the driving restriction condition at least include a turning radius, a reversing angle, and a safety distance; the determining a parking path for driving to the target parking area under the driving restriction condition based on the three-dimensional model of the vehicle includes: dividing the planning area into a plurality of grids, determining a starting grid where the vehicle is located, and a terminal grid where the target parking area is located; determining a plurality of candidate grids based on the safety distance; and determining a plurality of target grids in sequence from the starting grid based on the turning radius and the reversing angle among the plurality of candidate grids; wherein the first target grid among the target grids is connected to the starting grid, and the last target grid is connected to the terminal grid; and determining a parking path for the towing vehicle to drive to the target parking area based on the starting grid, the plurality of target grids, and the terminal grid.
12. The vehicle parking method according to claim 11, characterized in that: During the process of the vehicle parking according to the parking path, the method further includes: Acquire real-time driving data collected by a collection device; Determining the real-time driving state of the vehicle according to the real-time driving data; When the real-time driving state does not satisfy the stability condition, the remaining parking paths in the parking paths are updated.
13. The vehicle parking method according to claim 12, characterized in that: The real-time driving data includes at least one of the posture data of the tractor, the posture data of the towing object, and the obstacle data; and determining the real-time driving state of the vehicle according to the real-time driving data includes at least one of the following: Determining the distance between the vehicle and the obstacle based on the posture data of the tractor, the posture data of the towing object, and the obstacle data; Determining a lateral swing amplitude of the traction object relative to a driving direction according to the position and posture data of the traction object; The swing angle of the towing object relative to a fixed reference object is determined according to the position and posture data of the towing vehicle and the position and posture data of the towing object.
14. The vehicle parking method according to claim 11, characterized in that: Starting from the starting grid, determining a plurality of target grids in sequence from the plurality of candidate grids includes: Determine candidate grids around the starting grid in the current round, and determine the distance costs corresponding to each candidate grid; The candidate grid corresponding to the minimum distance cost is used as the starting grid in the next round, and the step of determining the candidate grids around the starting grid is returned to continue execution until the candidate grid corresponding to the minimum distance cost is the end grid; The candidate grid corresponding to the minimum distance cost determined in each round is used as the determined multiple target grids.
15. The vehicle parking method according to claim 11, characterized in that: The method further comprises: When a parking path to the target parking area cannot be determined based on the three-dimensional model of the vehicle under driving restriction conditions, the target parking area is re-determined.
16. The vehicle parking method according to any one of claims 11 to 14, characterized in that: The method further comprises: In response to a search instruction for a parking area, determining one or more free parking areas within a given range; In response to a trigger operation for the one or more free parking areas, a target parking area is determined from among the one or more free parking areas.
17. The vehicle parking method according to claim 11, characterized in that: The method further comprises: When the towing object is located in the target parking area, the towing vehicle is controlled to separate from the towing object so that the towing object is parked in the target parking area.
18. The vehicle parking method according to claim 11 or 17, characterized in that: After the towing object is parked in the target parking area, the method further includes: The posture of the towing object is adjusted so that the towing object docks with the docking facility in the target parking area.
19. The vehicle parking method according to any one of claims 11 to 14, characterized in that: The three-dimensional point cloud data of the vehicle includes three-dimensional point cloud data of the towing vehicle and three-dimensional point cloud data of the towing object; The step of obtaining the three-dimensional point cloud data of the vehicle includes: Flying above the vehicle by means of a collection device to collect first point cloud data of the top surface of the vehicle; The collecting device flies around the vehicle according to a preset trajectory to collect second point cloud data of the side surface of the vehicle; Based on the first point cloud data and the second point cloud data, three-dimensional point cloud data of the vehicle is acquired.
20. The vehicle parking method according to claim 19, characterized in that: The collecting device flies around the vehicle according to a preset trajectory to collect second point cloud data of the side of the vehicle, including: determining at least one flight altitude and at least one flight angle; The acquisition device flies around the vehicle at each flight altitude and at least one flight angle to acquire second point cloud data of the side surface of the vehicle.
21. A vehicle parking system, characterized in that: It comprises a collection device, a control device, a tractor and a tractor object; wherein the control device is used to execute the steps of the vehicle parking method as described in any one of claims 11 to 20.
22. A control device, characterized in that: It comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps of the vehicle parking method as described in any one of claims 11 to 20.
23. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps of the vehicle parking method as described in any one of claims 11 to 20.
24. A computer program product, characterized in that The method comprises a computer program, wherein the computer program is executed by a processor to perform the steps of the vehicle parking method as described in any one of claims 11 to 20.
