A method, device, and vehicle for parallel parking based on human-machine co-driving

Abstract

This invention discloses a method, device, and vehicle for parallel parking based on human-machine co-driving, belonging to the field of intelligent driving technology. One specific implementation of the method includes: constructing a vehicle's driving space model and obtaining the vehicle's location information; calling a preset scene condition table, using the driving space model and the location information to determine the vehicle's parking scene; obtaining an evaluation result for a recommended parking area based on the parking scene and a preset evaluation model; and matching and executing the corresponding human-machine co-driving mode based on the evaluation result. This method can guide the driver to provide high-level decisions through innovative interaction, while the vehicle is responsible for executing precise low-level control, achieving a hierarchical and intuitive human-machine co-driving technical effect.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to a method, device and vehicle for parallel parking based on human-machine co-driving. Background Technology

[0002] Currently, automatic parking systems are designed to address drivers' temporary parking needs, such as picking up or dropping off children or quickly retrieving items. However, existing automatic parking functions often fail in complex and diverse scenarios (e.g., irregular curbs, dense pedestrian traffic, or extremely narrow spaces) due to system limitations (e.g., uncertain perception or conservative algorithms), resulting in the system disengaging and requiring complete driver intervention. This transfer of driving tasks can cause frustration and operational stress for some users. On the other hand, purely manual operation places high demands on driver skills and carries the risk of errors under stress. Summary of the Invention

[0003] In view of this, the present invention provides a method, device and vehicle for parallel parking based on human-machine co-driving, which can guide the driver to make high-level decisions through innovative interactive methods, while the vehicle is responsible for executing precise low-level controls, thereby achieving a hierarchical and intuitive human-machine co-driving technical effect.

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for parallel parking based on human-machine co-driving, applied to a computer terminal, comprising: constructing a vehicle driving space model and obtaining the vehicle's location information; calling a preset scene condition table and using the driving space model and the location information to determine the vehicle's parking scene; obtaining an evaluation result of a recommended parking area based on a preset evaluation model according to the parking scene; and matching and executing the corresponding human-machine co-driving mode through the evaluation result.

[0005] Optionally, constructing the vehicle's driving space model includes: collecting detection data from the cameras and radars configured in the vehicle, fusing them with acquired map data, and constructing the vehicle's driving space model.

[0006] Optionally, obtaining the vehicle's location information includes: determining the vehicle's location information in the lane in real time based on the driving space model and in conjunction with data transmitted from the vehicle's global positioning system, inertial measurement unit, and wheel speed sensors.

[0007] Optionally, the scene condition table includes dimensional information and element attributes and element judgment conditions corresponding to each dimensional information.

[0008] Optionally, matching the corresponding human-machine co-driving mode through the evaluation results includes: matching a human-machine co-driving mode where the driver designates a parking area and the automatic parking is performed by the autonomous driving assistance system based on the evaluation results of multiple parking areas to be selected.

[0009] Optionally, it further includes: determining the location information of the plurality of parking areas and displaying it on the control screen of the vehicle; in response to the operation of selecting a designated area from the plurality of parking areas on the control screen, calling a preset scanning decision model to process the designated area, obtaining an optimal planning path, and controlling the vehicle to perform parking according to the optimal planning path by the automatic driving assistance system.

[0010] Optionally, matching the corresponding human-machine co-driving mode through the evaluation results includes: based on the evaluation results including the narrowness of the parking area or the presence of multiple vulnerable road users around the parking area, matching the human-machine co-driving mode to be the driver making steering decisions and the accelerator and brake being controlled by the automatic driving assistance system.

[0011] Optionally, it further includes: in response to a request for the decentralization of control by the driver, setting the steering wheel control authority of the vehicle to the driver and setting the speed control authority of the vehicle to the automatic driving assistance system, and performing a parking operation of the vehicle; monitoring and displaying the distance between the vehicle and surrounding obstacles in real time through the automatic driving assistance system, and triggering an alarm procedure and emergency braking in response to the distance being equal to a preset distance threshold.

[0012] Optionally, matching the evaluation results to the corresponding human-machine co-driving mode includes: based on the evaluation results including the absence of a suitable parking area, matching the human-machine co-driving mode to a mode that provides multiple parking options and allows for one-click selection; executing the one-click selection mode, and then visually presenting the parking options on the vehicle's display device in the form of virtual trajectory lines and / or text for selection.

[0013] Secondly, embodiments of the present invention provide a roadside parking device based on human-machine co-driving, comprising: an acquisition unit, a determination unit, and a processing unit, wherein the acquisition unit is used to construct a vehicle driving space model and acquire the vehicle's location information; the determination unit is used to call a preset scene condition table and, using the driving space model and the location information, determine the parking scene of the vehicle; the processing unit is used to obtain an evaluation result of a recommended parking area based on the parking scene and a preset evaluation model, and to match and execute the corresponding human-machine co-driving mode through the evaluation result.

[0014] Thirdly, embodiments of the present invention provide a vehicle including a processor, a memory, and a display, wherein the processor is configured to acquire and execute code in the memory to perform the method provided in the first aspect embodiments described above.

[0015] Fourthly, embodiments of the present invention provide an in-vehicle electronic device for parallel parking based on human-machine co-driving, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement a method for parallel parking based on human-machine co-driving as described in the above embodiments of the present invention.

[0016] Fifthly, embodiments of the present invention provide a computer-readable storage medium for parallel parking based on human-machine co-driving, wherein a computer program for implementing parallel parking based on human-machine co-driving is stored thereon, and when the computer program is executed by an on-board processor, it implements a parallel parking method based on human-machine co-driving according to embodiments of the present invention.

[0017] The technical solution of the above invention has the following advantages or beneficial effects: The present invention addresses the technical problem of vehicles abnormally exiting when parking on the side of the road in complex scenarios. It proposes a solution based on perfect cooperation between the driver and the autonomous driving assistance system to handle complex and diverse scenarios of parking on the side of the road, and to solve the abnormal function exit problem of the long tail of the autonomous driving assistance system. This enables intelligent identification and evaluation of the complexity of parking scenarios, matching it with different levels of human-machine co-driving modes, and relying on the driver's high-level decision-making to complete various parking tasks together with the vehicle, thereby improving the usability of the autonomous driving assistance system. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the main steps in a roadside parking scenario based on human-machine co-driving, according to some embodiments of the present invention; Figure 2 This is a schematic diagram of the main steps in a roadside parking scenario based on human-machine co-driving according to the second embodiment of the present invention; Figure 3 This is a schematic diagram of the main steps in a roadside parking scenario based on human-machine co-driving according to the third embodiment of the present invention; Figure 4 This is a schematic diagram of the main steps in a roadside parking scenario based on human-machine co-driving, according to the fourth embodiment of the present invention; Figure 5 This is a schematic diagram of the main steps in a roadside parking scenario based on human-machine co-driving, according to the fifth embodiment of the present invention; Figure 6This is a schematic diagram of a roadside parking system based on human-machine co-driving provided according to some embodiments of the present invention; Figure 7 This is a schematic diagram of the main units of a roadside parking device based on human-machine co-driving according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of a vehicle according to an embodiment of the present invention; Figure 9 This is an exemplary vehicle system architecture diagram provided by embodiments of the present invention that can be applied thereto; Figure 10 This is a schematic diagram of the structure suitable for implementing the computer system provided in the embodiments of the present invention. Detailed Implementation

[0019] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0020] It should be noted that, unless otherwise specified, the embodiments of the present invention and the technical features thereof can be combined with each other.

[0021] Furthermore, the terms "first," "second," and "third," etc., included in the terminology of this invention are used to distinguish similar objects and are not necessarily used to describe a specific number or order. It should be understood that such terms can be used interchangeably where appropriate; this is merely a distinguishing method used in the embodiments of this invention when describing objects with the same attributes.

[0022] Furthermore, the vehicles involved in the embodiments of the present invention may be internal combustion engine vehicles that use an engine as a power source, hybrid vehicles that use an engine and an electric motor as power sources, electric vehicles that use an electric motor as a power source, etc.

[0023] Figure 1 This is a schematic diagram illustrating the main steps of a computer terminal in a roadside parking scenario based on human-machine co-driving, according to some embodiments of the present invention. Figure 1 As shown, this human-machine co-driving-based parallel parking method mainly includes the following steps: Step S101: Construct a driving space model of the vehicle and obtain the location information of the vehicle.

[0024] In a further embodiment of the present invention, step S101 can construct a vehicle driving space model by fusing multi-sensor detection data. The specific implementation process includes: collecting detection data from the vehicle's cameras and radar, fusing it with acquired map data, and constructing the vehicle's driving space model. Examples of sensor types include, but are not limited to, cameras, lidar, millimeter-wave radar, and maps. Camera detection types may include, but are not limited to, identifying traffic signs, lane lines, curb types, pedestrians, bicycles, etc. LiDAR detection types may include, but are not limited to, accurately measuring the distance between the vehicle and curbs / obstacles, constructing a 3D spatial model, and identifying vertical clearance areas. Millimeter-wave radar detection types may include, but are not limited to, detecting the speed and distance of vehicles in front / behind and to the sides. Map detection types may include, but are not limited to, providing prior information (examples: number of lanes, shoulder width, speed limit information, traffic flow, fixed no-stopping zones, etc.).

[0025] In a further embodiment of the present invention, step S101 can achieve accurate positioning of the vehicle. The specific implementation process includes: based on the driving space model, combined with the data transmitted by the vehicle's Global Positioning System (GPS), Inertial Measurement Unit (IMU) and wheel speed sensors, determining the vehicle's position information in the lane in real time to achieve high-precision vehicle positioning.

[0026] Step S102: Call the preset scene condition table, and use the driving space model and the location information to determine the parking scene of the vehicle.

[0027] In some embodiments, the scene condition table of the present invention may include dimensional information and element attributes and element judgment conditions corresponding to each dimensional information. For example: dimensional information may include, but is not limited to, safety and regulations, dynamic traffic, and comfort; wherein, each element attribute corresponding to the dimensional information safety and regulations may include, but is not limited to, explicit prohibition by traffic regulations, special road sections, spatial physical constraints, and line of sight (visibility), while the element judgment conditions corresponding to the element attribute explicit prohibition by traffic regulations may include, but are not limited to, the existence of "no parking". In areas marked with signs such as "No Temporary Parking," the element judgment conditions corresponding to special road sections may include, but are not limited to, the presence of intersections, railway crossings, sharp bends, bridges, tunnels, and fire lanes. The element judgment conditions corresponding to spatial physical constraints may include, but are not limited to, whether the minimum safe space requirements for vehicles are not met (for example, the length and width of the target parking area must be greater than the sum of the vehicle's dimensions and a preset safety margin, defined as 0.5-0.9 meters front and rear, and 0.5 meters to the sides). The element judgment conditions corresponding to line-of-sight may include, but are not limited to, whether the location is in a blind spot such as a curve or the crest of a hill. Each element attribute corresponding to dynamic traffic dimensional information may include, but is not limited to, the risk of vehicles approaching from behind and the risk of vulnerable road users (VRUs) (wherein, the vulnerable road user can be...). This refers to vulnerable groups in road traffic, such as pedestrians, cyclists, and motorcyclists. The element judgment conditions corresponding to the element attribute "risk of oncoming vehicles behind" can include, but are not limited to, whether there is an oncoming vehicle within a preset distance behind the vehicle. The element judgment conditions corresponding to the element attribute "risk of vulnerable road users" can include, but are not limited to, whether the types of vulnerable road users are diverse and complex. Each element attribute corresponding to the dimension information "comfort" can include, but is not limited to, road conditions and ease of getting on and off the vehicle. The element judgment conditions corresponding to the element attribute "road conditions" can include, but are not limited to, whether there is a flat, solid road surface, avoiding potholes, manhole covers, gravel, or drainage ditches. The element judgment conditions corresponding to the element attribute "ease of getting on and off the vehicle" can include, but are not limited to, whether the distance to the destination is within a preset threshold range. The scenario condition table is as follows:

[0028] As can be seen, step S102 utilizes the scene condition table to achieve intelligent scene judgment and obtain the final parking scene, preparing for the subsequent step S103 to obtain the evaluation results of the recommended parking area. It is worth noting that the parking scene described in this invention may include one or more dimension information and their judgment results in the scene condition table. Different dimension information, element attributes, and element judgment conditions can be configured according to different practical application needs.

[0029] Step S103: Based on the parking scenario, obtain the evaluation result of the recommended parking area based on the preset evaluation model, and match the corresponding human-machine co-driving mode through the evaluation result and execute it.

[0030] In this embodiment, step S103 inputs a parking scenario, including one or more dimensions of information and their judgment results, into a preset evaluation model to obtain a complexity assessment of the parking scenario. This allows for matching a suitable human-machine co-driving mode, thereby providing different parking modes. The evaluation model may include, but is not limited to, the analytic hierarchy process (AHP), regression model evaluation, classification model evaluation, etc. The evaluation results may include, but are not limited to, multiple parking areas to choose from, narrow parking areas, multiple vulnerable road users surrounding the parking area, or no suitable parking area currently available. The matched human-machine co-driving mode may include, but is not limited to, a mode where the driver designates a parking area and the automated driving assistance system performs automatic parking, a mode where the driver makes steering decisions and the automated driving assistance system controls the accelerator and brakes, or a mode that provides multiple parking options and allows one-click selection.

[0031] In a further embodiment of the present invention, the present invention can match the evaluation results of multiple parking areas to a corresponding human-machine co-driving mode. The specific implementation process includes: based on the evaluation results of multiple parking areas to a choice, matching the human-machine co-driving mode to a mode in which the driver designates a parking area and the automatic parking is performed by the automatic driving assistance system.

[0032] In a further embodiment of the present invention, if the human-machine co-driving mode of the present invention is a mode in which the driver designates a parking area and the automatic parking is executed by the autonomous driving assistance system, the specific implementation process includes: determining the location information of the multiple parking areas and displaying it on the control screen of the vehicle; and in response to the operation of selecting a designated area from the multiple parking areas on the control screen, calling a preset scanning decision model to process the designated area, obtaining the optimal planning path, and controlling the vehicle to perform parking according to the optimal planning path. The scanning decision model may include, but is not limited to, decision tree models, simulation models, centralized decision models, etc. For example: when the vehicle identifies multiple potential parking areas but cannot make a decision, or in a non-standard area (such as without a clear curb), a "parking area" is displayed on the surround-view top view of the central control screen. The driver selects a general area as the designated area by sliding their finger on the central control screen. In response to the operation of selecting the designated area, a refined scanning decision is performed on the designated area to obtain a safe, comfortable, and efficient optimal planning path, and precise parking control is executed.

[0033] In a further embodiment of the present invention, if the human-machine co-driving mode of the present invention is used in a narrow parking area or where there are multiple vulnerable road users around the parking area, the specific implementation process includes: based on the evaluation results including the narrow parking area or the presence of multiple vulnerable road users around the parking area, a human-machine co-driving mode is matched where the driver makes steering decisions and the automatic driving assistance system controls the accelerator and brakes. The driver's steering decisions involve the allocation of driving rights, behavioral decisions, and motion planning between the driver and the automatic driving assistance system to ensure safe, comfortable, and efficient vehicle control. In a further embodiment of the present invention, in response to a request for the decentralization of control rights involving the driver, the present invention sets the steering wheel control authority of the vehicle to the driver and sets the speed control authority of the vehicle to the automatic driving assistance system, and performs the parking operation of the vehicle; the automatic driving assistance system monitors and displays the distance between the vehicle and surrounding obstacles in real time, and in response to the distance equaling a preset distance threshold, triggers an alarm procedure and performs emergency braking. For example: In a narrow parking area (e.g., the length and width of the parking area are only greater than the vehicle's dimensions and the safety margin is only 0.1 meters in front and behind and 0.1 meters to the side) or with too many vulnerable road users around (e.g., there are 4 vulnerable road users around), the matched human-machine co-driving mode is where the driver makes steering decisions and the automatic driving assistance system controls the accelerator and brakes. Specifically, the vehicle will decentralize control and request the driver to participate in the operation. The driver is responsible for the lateral control of the vehicle (i.e., operating the steering wheel) and providing directional guidance, while the automatic driving assistance system is responsible for the vehicle's speed control, automatically adjusting the accelerator and brakes to move at a low and constant safe speed (3-7 kph), and monitoring the distance to surrounding obstacles (e.g., vehicles in front and behind, vulnerable road users, curbs, etc.) in real time, and dynamically displaying this information on the vehicle's infotainment system. When a collision is imminent (e.g., the distance between the vehicle and a surrounding obstacle is equal to a distance threshold of 0.5 meters), the system will automatically trigger a sequential alarm and emergency braking.

[0034] In a further embodiment of the present invention, based on an evaluation result including the absence of a suitable parking area, the present invention matches the human-machine co-driving mode to a mode providing multiple parking options with one-click selection. The one-click selection mode is then executed, and the parking options are visualized on the vehicle's display device using virtual trajectory lines and / or text for selection. The one-click selection mode refers to selecting a parking option from the provided multiple options via a button and executing it. For example: the vehicle's automatic driving assistance system generates 2-3 feasible parking options and visualizes them on an AR-HUD, in-vehicle infotainment system, or dashboard using virtual trajectory lines and / or text (e.g., parking option A is system exit, driver takes over; parking option B is continue driving (finding a better parking area); parking option C is parking in an empty space 10 meters ahead). The driver selects one of the parking options with a single click via voice or a steering wheel button, and the automatic driving assistance system executes the selected parking option.

[0035] Regarding the roadside parking method based on human-machine co-driving provided in the embodiments of the present invention, such as Figure 2 The diagram illustrates the main steps of a roadside parking scenario based on human-machine co-driving provided in the second embodiment of the present invention. The embodiments of the present invention include the following steps: Step S201: Collect detection data from the cameras and radars configured in the vehicle, and fuse them with the acquired map data to construct a driving space model of the vehicle.

[0036] Step S202: Based on the driving space model, and combined with the data transmitted by the vehicle's global positioning system, inertial measurement unit, and wheel speed sensors, determine the vehicle's position information in the lane in real time.

[0037] Step S203: Call the preset scene condition table, and use the driving space model and the location information to determine the parking scene of the vehicle.

[0038] Step S204: Based on the parking scenario, obtain the evaluation results of the recommended parking area based on the preset evaluation model.

[0039] Step S205: Match the corresponding human-machine co-driving mode based on the evaluation results and execute it.

[0040] As can be seen, this invention can not only match different levels of human-machine co-driving modes based on the identified parking scenarios, and rely on the driver's high-level decision-making to complete various parking tasks together with the vehicle, but also achieve high-precision vehicle positioning.

[0041] Regarding the roadside parking method based on human-machine co-driving provided in the embodiments of the present invention, such as Figure 3The diagram illustrates the main steps of a roadside parking scenario based on human-machine co-driving provided in the third embodiment of the present invention. The embodiments of the present invention include the following steps: Step S301: Construct a driving space model of the vehicle and obtain the location information of the vehicle.

[0042] Step S302: Call the preset scene condition table, and use the driving space model and the location information to determine the parking scene of the vehicle.

[0043] Step S303: Based on the parking scenario, obtain an evaluation result that includes multiple parking areas to choose from based on a preset evaluation model.

[0044] Step S304: Match the human-machine co-driving mode to the mode in which the driver designates a parking area and the automatic parking is performed by the automatic driving assistance system.

[0045] Step S305: Determine the location information of the multiple parking areas and display it on the vehicle's control screen.

[0046] Step S306: In response to the operation of selecting a specified area from multiple parking areas on the control screen, a preset scanning decision model is invoked to process the specified area and obtain the optimal planned path.

[0047] Step S307: The vehicle is controlled by the automatic driving assistance system to stop according to the optimal planned path.

[0048] As can be seen, this invention can not only match different levels of human-machine co-driving modes based on the identified parking scenarios, and rely on the driver's high-level decision-making to complete various parking tasks together with the vehicle, but also perform refined scanning and decision-making on designated areas to obtain a safe, comfortable, and efficient optimal planning path and execute precise parking control.

[0049] Regarding the roadside parking method based on human-machine co-driving provided in the embodiments of the present invention, such as Figure 4 The illustration shows a schematic diagram of a roadside parking scenario based on human-machine co-driving provided in the fourth embodiment of the present invention. This embodiment includes the following steps: Step S401: Construct a driving space model of the vehicle and obtain the location information of the vehicle.

[0050] Step S402: Call the preset scene condition table, and use the driving space model and the location information to determine the parking scene of the vehicle.

[0051] Step S403: Based on the parking scenario, obtain assessment results including narrow parking areas or multiple vulnerable road users around the parking area based on a preset assessment model.

[0052] Step S404: The human-machine co-driving mode is matched to a mode in which the driver makes steering decisions and the accelerator and brake are controlled by the automatic driving assistance system.

[0053] Step S405: In response to the request to decentralize control by the driver, set the steering wheel control authority of the vehicle to the driver and set the speed control authority of the vehicle to the automatic driving assistance system, and execute the parking operation of the vehicle.

[0054] Step S406: The distance between the vehicle and surrounding obstacles is monitored and displayed in real time by the automatic driving assistance system. In response to the distance being equal to a preset distance threshold, an alarm procedure is triggered and emergency braking is initiated.

[0055] As can be seen, this invention can not only match different levels of human-machine co-driving modes based on the identified parking scenarios, and rely on the driver's high-level decision-making to complete various parking tasks together with the vehicle, but also effectively trigger alarm programs and emergency braking.

[0056] Regarding the roadside parking method based on human-machine co-driving provided in the embodiments of the present invention, such as Figure 5 The diagram illustrates the main steps of a roadside parking scenario based on human-machine co-driving provided in the fifth embodiment of the present invention. The embodiments of the present invention include the following steps: Step S501: Construct a driving space model of the vehicle and obtain the location information of the vehicle.

[0057] Step S502: Call the preset scene condition table, and use the driving space model and the location information to determine the parking scene of the vehicle.

[0058] Step S503: Based on the parking scenario, obtain an evaluation result including the absence of a suitable parking area based on a preset evaluation model.

[0059] Step S504: The human-machine co-driving mode is matched to provide multiple parking options and one-click selection mode.

[0060] Step S505: Execute the mode that provides multiple parking options and allows one-click selection, and then visualize the parking options on the vehicle's display device in the form of virtual trajectory lines and / or text for selection.

[0061] Step S506: In response to the selection operation of the parking scheme, obtain the target parking scheme and execute it.

[0062] As can be seen, this invention can not only match different levels of human-machine co-driving modes based on the identified parking scenarios, but also rely on the driver's high-level decision-making to complete various parking tasks together with the vehicle, and can provide multiple parking solutions and visualization presentation.

[0063] like Figure 6 The diagram illustrates a human-machine co-driving-based parallel parking system according to some embodiments of the present invention. The system includes a scenario complexity assessment module 601, a co-driving mode decision module 602, a multimodal human-machine interface (HMI) module 603, and a control allocation and execution module 604. In the embodiments, the scenario complexity assessment module 601 constructs a vehicle driving space model and obtains the vehicle's location information in real time. It then calls a preset scenario condition table to determine the vehicle's parking scenario and, based on the parking scenario and a preset assessment model, obtains an evaluation result for a recommended parking area, i.e., outputs a quantification of the difficulty of the current parallel parking scenario. The co-driving mode decision module 602 dynamically matches and triggers the corresponding human-machine co-driving mode based on the evaluation result. A preferred co-driving mode decision module 602 may also consider driver status, driver's historical driving preferences, etc., when matching the human-machine co-driving mode. The multimodal human-machine interface (HMI) module 603 provides intuitive interaction with the driver during the execution of the human-machine co-driving-based parallel parking method of the present invention through touchscreen, AR-HUD, voice, etc. The control allocation and execution module 604 can accurately allocate lateral control (e.g., steering wheel control) and longitudinal control (e.g., speed control) according to the matched human-machine co-driving mode, and execute the corresponding control commands.

[0064] Therefore, this invention can significantly improve drivers' satisfaction when using autonomous driving assistance systems, thereby increasing the frequency of use and user peace of mind, solving the awkward exit problem in the long tail problem, and improving the usability and user trust of the function; it combines the advantages of human global cognition and fuzzy decision-making ability with the precise control and tireless nature of machines to achieve complementary advantages between humans and machines; in any mode, the machine acts as a safety monitor to prevent accidents caused by human error, achieving safety redundancy; the interaction method is intuitive and low-burden, significantly reducing the psychological pressure and operational burden on drivers in complex scenarios.

[0065] The above steps are provided only to help understand the method, structure, and core ideas of this invention. Those skilled in the art can make various improvements and modifications to this invention without departing from its principles, and these improvements and modifications also fall within the scope of protection of the claims.

[0066] Figure 7This is a schematic diagram of the main unit of a computer terminal for a roadside parking device based on human-machine co-driving, according to an embodiment of the present invention. Figure 7 As shown, a parking device 700 based on human-machine co-driving according to an embodiment of the present invention includes: an acquisition unit 701, a determination unit 702, and a processing unit 703. The acquisition unit 701 is used to construct a vehicle driving space model and acquire the vehicle's location information. The determination unit 702 is used to call a preset scene condition table and, using the driving space model and the location information, determine the parking scene of the vehicle. The processing unit 703 is used to obtain an evaluation result of a recommended parking area based on a preset evaluation model according to the parking scene, and to match and execute the corresponding human-machine co-driving mode based on the evaluation result.

[0067] In this embodiment of the invention, the acquisition unit 701 is further configured to: collect detection data from the cameras and radars configured in the vehicle, fuse them with the acquired map data, and construct a driving space model of the vehicle.

[0068] In this embodiment of the invention, the acquisition unit 701 is further configured to: determine the vehicle's position information in the lane in real time based on the driving space model and in conjunction with the data transmitted by the vehicle's global positioning system, inertial measurement unit and wheel speed sensor.

[0069] In this embodiment of the invention, the scene condition table includes dimensional information and element attributes and element judgment conditions corresponding to each dimensional information.

[0070] In this embodiment of the invention, the processing unit 703 is further configured to: match a human-machine co-driving mode where the driver designates a parking area and the automatic parking is performed by the automatic driving assistance system, based on the evaluation results of multiple parking areas to be selected.

[0071] In this embodiment of the invention, the processing unit 703 is further configured to: determine the location information of the plurality of parking areas and display it on the control screen of the vehicle; in response to the operation of selecting a specified area from the plurality of parking areas on the control screen, call a preset scanning decision model to process the specified area, obtain the optimal planning path, and control the vehicle to perform parking according to the optimal planning path by the automatic driving assistance system.

[0072] In this embodiment of the invention, the processing unit 703 is further configured to: based on the assessment results including the narrowness of the parking area or the presence of multiple vulnerable road users around the parking area, match a human-machine co-driving mode in which the driver makes steering decisions and the automatic driving assistance system controls the accelerator and brake.

[0073] In this embodiment of the invention, the processing unit 703 is further configured to: respond to a request for the decentralization of control rights by the driver, set the steering wheel control authority of the vehicle to the driver and set the speed control authority of the vehicle to the automatic driving assistance system, and perform a parking operation of the vehicle; monitor and display the distance between the vehicle and surrounding obstacles in real time through the automatic driving assistance system, and trigger an alarm program and perform emergency braking in response to the distance being equal to a preset distance threshold.

[0074] In this embodiment of the invention, the processing unit 703 is further configured to: match the human-machine co-driving mode as a mode that provides multiple parking options and allows one-click selection based on the assessment result including the absence of a suitable parking area; execute the mode that provides multiple parking options and allows one-click selection, and then visualize the parking options on the vehicle's display device in the form of virtual trajectory lines and / or text for selection.

[0075] like Figure 8 As shown, an embodiment of the present invention provides a vehicle 800, which may include the human-machine co-driving-based parking device 700 provided in the above embodiments.

[0076] Figure 9 An exemplary vehicle system architecture 900 is shown, to which the human-machine co-driving-based parallel parking method or human-machine co-driving-based parallel parking device of the present invention can be applied.

[0077] like Figure 9 As shown, the vehicle system architecture 900 may include various systems, such as an intelligent driving system 901, a powertrain system 902, a sensor system 903, a control system 904, one or more peripheral devices 905, a power supply 906, a computer system 907, and a user interface 908. Optionally, the vehicle system architecture 900 may include more or fewer systems, and each system may include multiple components. Furthermore, each system and component of the vehicle system architecture 900 can be interconnected via wired or wireless means.

[0078] The vehicle system architecture 900 includes an intelligent driving system 901, which can be in a fully or partially automated driving mode. For example, the intelligent driving system 901 can automatically control the vehicle's driving without human interaction; the intelligent driving system 901 can also control the vehicle's automated driving while in automated driving mode, and can also adjust its automated driving behavior through human interaction. Specifically, the intelligent driving system 901 can also construct a vehicle driving space model and obtain the vehicle's location information; call a preset scene condition table, and use the driving space model and the location information to determine the vehicle's parking scene; based on the parking scene, obtain an evaluation result of a recommended parking area based on a preset evaluation model, and match and execute the corresponding human-machine co-driving mode through the evaluation result.

[0079] The powertrain 902 may include components that provide power to the vehicle. For example, the powertrain 902 may include an engine, an energy source, a transmission, wheels, tires, etc. The engine may be an internal combustion engine, an electric motor, an air-compressed engine, or other combinations of engines, such as a hybrid engine consisting of a gasoline engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air-compressed engine. The engine converts the energy source into mechanical energy to supply the transmission. Examples of energy sources may include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other electrical sources. The energy source may also provide energy to other systems in the vehicle. Furthermore, the transmission may include a gearbox, a differential, a drive shaft, and a clutch, etc.

[0080] Sensor system 903 may include sensors for sensing the vehicle's surrounding environment. Examples include a positioning system (which may be a Global Positioning System (GPS), BeiDou Navigation Satellite System, or other positioning systems), radar, a laser rangefinder, an inertial measurement unit (IMU), and a camera. The positioning system can be used to determine the vehicle's geographical location. The IMU is used to sense changes in the vehicle's position and orientation based on inertial acceleration. In one embodiment, the IMU may be a combination of an accelerometer and a gyroscope. Radar can use radio signals to sense objects in the vehicle's surrounding environment. In some embodiments, in addition to sensing objects, radar can also be used to sense the speed and / or direction of travel of objects.

[0081] To monitor environmental information and objects located in front of, behind, or to the sides of the vehicle, radar, cameras, and other devices can be configured at appropriate locations on the exterior of the vehicle. For example, to acquire an image of the front of the vehicle, a camera can be configured inside the vehicle and close to the windshield. Alternatively, the camera can be configured around the front bumper or radiator grille. Similarly, to acquire an image of the rear of the vehicle, a camera can be configured inside the vehicle and close to the rear window. Alternatively, the camera can be configured around the rear bumper, trunk, or tailgate. To acquire images of the sides of the vehicle, a camera can be configured inside the vehicle and close to at least one of the side windows. Alternatively, the camera can be configured around the side mirrors, fenders, or doors.

[0082] Laser rangefinders use lasers to sense objects in the environment in which a vehicle is located.

[0083] A camera can be used to capture multiple images of the vehicle's surroundings. The camera can be a still or video camera.

[0084] The control system 904 may include software systems for implementing autonomous driving, such as a route planning system, an obstacle avoidance system, and a vision system for image analysis. The control system 904 may also include hardware systems such as an accelerator and steering wheel system. Furthermore, the control system 904 may add or replace components other than those shown and described. Alternatively, some of the components shown above may be omitted.

[0085] The control system 904 interacts with external sensors, other autonomous driving devices, other computer systems, or users via peripheral devices 905. Peripheral devices 905 may include wireless communication systems, on-board computers, microphones, and / or speakers.

[0086] In some embodiments, peripheral device 905 provides a means for user interaction with the control system 904 via a user interface. For example, an onboard computer may provide information to a user of the vehicle. The user interface may also operate the onboard computer to receive user input. The onboard computer may be operated via a touchscreen. In other cases, peripheral device may provide a means for communicating with other devices located within the vehicle. For example, a microphone may receive audio (e.g., voice commands or other audio input) from a user of the control system 904. Similarly, a speaker may output audio to a user of the control system 904.

[0087] Wireless communication systems can communicate wirelessly with one or more devices, either directly or via a communication network. For example, wireless communication systems can use networks such as cellular networks, WiFi, and wireless local area networks (WLANs), or they can use infrared links, Bluetooth, or ZigBee to communicate directly with devices. Other wireless protocols include those used in various autonomous driving communication systems.

[0088] The power source 906 can provide power to various components of the vehicle. The power source 906 can be a rechargeable lithium-ion or lead-acid battery.

[0089] The computer system 907 controls some or all of the functions enabling autonomous driving. The computer system 907 may include at least one processor that executes instructions stored in a non-transitory computer-readable medium such as memory. The computer system 907 provides the execution code for the aforementioned intelligent driving system to enable autonomous driving.

[0090] The processor can be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor can be a special-purpose device such as an application-specific integrated circuit (ASIC) or other hardware-based processor. Those skilled in the art will understand that the processor, computer, or memory can actually include multiple processors, computers, or memories that may or may not be stored in the same physical housing. For example, memory can be a hard disk drive or other storage media located in a housing different from that of a computer. Therefore, references to processors or computers will be understood to include references to a collection of processors or computers or memories that may or may not operate in parallel. Unlike using a single processor to perform the steps described herein, some components, such as steering and deceleration components, may each have their own processor that performs calculations only related to the component's specific function.

[0091] User interface 908 is used to provide information to or receive information from users of the vehicle. Optionally, user interface 908 may include one or more input / output devices within a set of peripheral devices 905, such as wireless communication systems, on-board computers, microphones, and speakers.

[0092] It should be understood that the components described above are merely an example. In actual applications, components in the various modules or systems mentioned above may be added or removed as needed. Figure 9 This should not be construed as a limitation on the embodiments of this application.

[0093] The following is for reference. Figure 10 It shows a schematic diagram of the structure of a computer system 1000 suitable for implementing embodiments of the present invention. Figure 10 The computer system shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0094] like Figure 10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage section 1008 into random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the operation of the system 1000. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0095] The following components are connected to I / O interface 1005: an input section 1006; an output section 1007 including devices such as cathode ray tubes (CRTs), liquid crystal displays (LCDs), and speakers; a storage section 1008 including devices such as hard disks; and a communication section 1009 including network interface cards such as LAN cards and modems. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1010 as needed so that computer programs read from it can be installed into storage section 1008 as needed.

[0096] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs the functions defined above in the system of this invention.

[0097] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0098] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0099] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor; for example, a processor can be described as including an acquisition unit, a determination unit, and a processing unit. The names of these units do not necessarily limit the module itself; for example, the processing unit can also be described as "a unit that matches human-machine co-driving modes based on evaluation results."

[0100] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: constructing a driving space model of a vehicle and obtaining the vehicle's location information; invoking a preset scene condition table, using the driving space model and the location information to determine the vehicle's parking scene; obtaining an evaluation result of a recommended parking area based on a preset evaluation model according to the parking scene; and matching and executing a corresponding human-machine co-driving mode based on the evaluation result.

[0101] According to the technical solution of the present invention, the present invention addresses the technical problem of abnormal exit when a vehicle attempts to park at the side of the road in complex scenarios. It proposes a solution based on perfect cooperation between the driver and the autonomous driving assistance system, which solves the complex and diverse scenarios of parking at the side of the road and resolves the abnormal function exit of the long-tail problem of the autonomous driving assistance system. This enables intelligent identification and evaluation of the complexity of parking scenarios, matching it with different levels of human-machine co-driving modes, and relying on the driver's high-level decision-making to complete various parking tasks together with the vehicle, thereby improving the usability of the autonomous driving assistance system.

[0102] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for parallel parking based on human-machine co-driving, characterized in that, include: Construct a driving space model of the vehicle and obtain the vehicle's location information; By calling a preset scene condition table and using the driving space model and the location information, the parking scene of the vehicle is determined; Based on the parking scenario, an evaluation result for the recommended parking area is obtained based on a preset evaluation model. The evaluation result is then used to match and execute the corresponding human-machine co-driving mode.

2. The method for parallel parking based on human-machine co-driving as described in claim 1, characterized in that, The construction of the vehicle's driving space model includes: The detection data from the cameras and radars configured in the vehicle are collected and fused with the acquired map data to construct a driving space model of the vehicle.

3. The method for parallel parking based on human-machine co-driving according to claim 1, characterized in that, The acquisition of vehicle location information includes: Based on the driving space model, and combined with data transmitted from the vehicle's GPS, inertial measurement unit, and wheel speed sensors, the vehicle's position information in the lane is determined in real time.

4. The method for parallel parking based on human-machine co-driving as described in claim 1, characterized in that, The scenario condition table includes dimensional information and element attributes and element judgment conditions corresponding to each dimensional information.

5. The method for parallel parking based on human-machine co-driving according to claim 1, characterized in that, The evaluation results are used to match the corresponding human-machine co-driving mode, including: Based on the evaluation results of multiple parking areas to choose from, the human-machine co-driving mode is matched to a mode in which the driver designates a parking area and the automatic parking is performed by the autonomous driving assistance system.

6. The method for parallel parking based on human-machine co-driving according to claim 5, characterized in that, Also includes: Determine the location information of the multiple parking areas and display it on the vehicle's control screen; In response to the operation of selecting a designated area from multiple parking areas on the control screen, a preset scanning decision model is invoked to process the designated area, obtain the optimal planned path, and the vehicle is controlled by the automatic driving assistance system to perform parking according to the optimal planned path.

7. The method for parallel parking based on human-machine co-driving according to claim 1, characterized in that, The evaluation results are used to match the corresponding human-machine co-driving mode, including: Based on the assessment results, including the narrowness of the parking area or the presence of multiple vulnerable road users around the parking area, the human-machine co-driving mode is matched so that the driver makes steering decisions and the automatic driving assistance system controls the accelerator and brake.

8. The method for parallel parking based on human-machine co-driving according to claim 7, characterized in that, Also includes: In response to a request to decentralize control from the driver, the steering wheel control authority of the vehicle is set to the driver and the speed control authority of the vehicle is set to the automatic driving assistance system, and the vehicle is then put into operation. The autonomous driving assistance system monitors and displays the distance between the vehicle and surrounding obstacles in real time. In response to the distance being equal to a preset distance threshold, an alarm procedure is triggered and emergency braking is initiated.

9. The method for parallel parking based on human-machine co-driving according to claim 1, characterized in that, The evaluation results are used to match the corresponding human-machine co-driving mode, including: Based on the assessment results, including the current lack of suitable parking areas, the human-machine co-driving mode is matched to provide multiple parking options and a one-click selection mode. The system provides multiple parking options and offers a one-click selection mode, thereby visually presenting the parking options on the vehicle's display device in the form of virtual trajectory lines and / or text for selection.

10. A roadside parking device based on human-machine co-driving, characterized in that, include: The unit comprises an acquisition unit, a determination unit, and a processing unit, wherein... The acquisition unit is used to construct a driving space model of the vehicle and acquire the location information of the vehicle; The determining unit is used to call a preset scene condition table and, using the driving space model and the location information, determine the parking scene of the vehicle. The processing unit is used to obtain the evaluation result of the recommended parking area based on the parking scenario and a preset evaluation model, and to match and execute the corresponding human-machine co-driving mode through the evaluation result.

Images