Control method, device and intelligent driving equipment

Abstract

A control method, device and intelligent driving equipment, the method comprising: controlling the intelligent driving equipment to travel along a first planned path, the first planned path being planned by a first planning mode; when a first obstacle in the first planned path causes a passable width of a first region corresponding to the first obstacle to be less than or equal to a first preset threshold, and / or when the first obstacle causes a curvature of a feasible path in the first region to be greater than or equal to a second preset threshold, controlling the intelligent driving equipment to switch from traveling along the first planned path to traveling along a second planned path, the second planned path being planned by a second planning mode, the first planning mode and the second planning mode being different, and the first planned path passing through the first region. The method of the present application can be applied to intelligent vehicles such as electric vehicles and new energy vehicles, and can reduce the probability that the intelligent driving equipment cannot plan a path due to obstacles or complex road conditions during AVP parking, thereby helping to improve the success rate of parking.

Description

Technical Field

[0001] This application relates to the field of intelligent driving, and more specifically, to a control method, apparatus, and intelligent driving device. Background Technology

[0002] With the rapid development of the automotive industry, many driver assistance and autonomous driving technologies have emerged, which can reduce driving stress, improve safety, and enhance traffic efficiency. Automatic parking (AP) is one such widely used driver assistance technology. AP refers to automatic parking, meaning the autonomous driving system can semi-automatically or fully automatically help the user park the vehicle in a parking space. Automatic parking can include automatic parking assist (APA), remote parking assist (RPA), and automatic valet parking (AVP), among others.

[0003] Parking lots often feature sharp curves, narrow turns, or complex obstacle locations. Because current AVP path planning capabilities cannot handle these complex situations, vehicles may get stuck due to obstruction when using AVP for parking.

[0004] Therefore, a control scheme that can improve the vehicle's ability to get out of trouble during automatic parking is urgently needed to be developed. Summary of the Invention

[0005] This application provides a control method, device, and intelligent driving equipment that can reduce the probability that the intelligent driving equipment cannot perform path planning due to obstacles or complex road conditions during AVP parking, thereby helping to improve the parking success rate.

[0006] In a first aspect, a control method is provided, which can be executed by an intelligent driving device; or, it can also be executed by the computing platform of the intelligent driving device; or, it can also be executed by a chip or circuit for the intelligent driving device, which is not limited in this application.

[0007] The method includes: controlling an intelligent driving device to travel along a first planned path, the first planned path being planned by a first planning mode; when a first obstacle exists in the first planned path such that the passable width corresponding to the first area is less than or equal to a first preset threshold, and / or when the first obstacle makes the curvature of the feasible path in the first area greater than or equal to a second preset threshold, controlling the intelligent driving device to switch from traveling along the first planned path to traveling along a second planned path, the second planned path being planned by a second planning mode, the first planning mode and the second planning mode being different, the first planned path passing through the first area.

[0008] The aforementioned technical solution provides two path planning modes with different path planning capabilities. During the operation of the intelligent driving device, the mode is switched according to the actual road conditions, which helps improve the device's ability to navigate different road conditions. Especially during AVP parking, it reduces the likelihood that the vehicle will be unable to plan a path in narrow passages or scenarios with complex obstacle positions, thus improving the success rate of AVP parking.

[0009] For example, the first preset threshold can be determined based on the width of the intelligent driving device; the second preset threshold can be 0.01, or 0.1, or other values.

[0010] In some possible implementations, when a first obstacle exists in the first planned path, causing the passable width of the corresponding first area to be less than or equal to a first preset threshold, and / or when the curvature of the feasible path in the first area is greater than or equal to a second preset threshold, the intelligent driving device is controlled to stop driving and switch from the first planning mode to the second planning mode.

[0011] In some possible implementations, the first region may include one or more feasible paths. The curvature of the feasible path in the first region being greater than or equal to the second preset threshold includes: the curvature of the feasible path with the smallest curvature in the first region being greater than or equal to the second preset threshold.

[0012] In some possible implementations, the first region is determined based on the position of the first path and the first sub-obstacle.

[0013] It should be noted that the first and second planning modes have different planning capabilities for different scenarios. The first planning mode can only perform relatively simple path planning, and its planning ability is low in areas with narrow roads, large curvature, and complex obstacle locations. The second planning mode can perform path planning in situations with narrow roads, large curvature, and complex obstacle locations.

[0014] In some possible implementations, the second planning path includes multiple segments of paths with different gear combinations, for example, multiple segments of paths including combinations of driving and reverse gears.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, the first region includes a head end and a tail end, the head end of the first region being the end closest to the current position of the intelligent driving device, and the tail end of the first region being the end closest to the destination of the intelligent driving device; the method further includes: determining a first target pose of the intelligent driving device based on a first planned path; determining a second target pose based on the first target pose and the position of a first obstacle, the second target pose indicating the pose of the intelligent driving device exiting the tail end of the first region; and planning a second planned path based on the current pose of the intelligent driving device, the second target pose, and the first obstacle.

[0016] For example, a second planned path can be planned based on the hybrid A* (A-star) algorithm or geometric methods, according to the current pose of the intelligent driving device, the pose of the second target, and the first obstacle.

[0017] For example, determining a second target pose based on a first target pose and the position of a first obstacle includes: adjusting the lateral and / or longitudinal positions of the first target pose based on the position of the first obstacle to obtain a second target pose.

[0018] In some possible implementations, the first target pose and the second target pose are the same pose.

[0019] In the above technical solution, determining the second target pose based on the first planned path planned under the first planning mode helps reduce the difficulty of path planning. Determining the second target pose based on the position of the first obstacle helps to achieve adaptation to the obstacle scale and obtain a feasible escape position across the current trapped area.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining a drivable area along the first planned path based on the first planned path; and planning a second planned path based on the current pose of the intelligent driving device and the second target pose, including: planning the second planned path in the drivable area based on the current pose, the second target pose, and the first obstacle.

[0021] In the above technical solution, a drivable area is generated based on the first planned path. During driving, this prevents the intelligent driving device from straying far from the road; during parking, it prevents the vehicle from entering other parking spaces. Furthermore, generating a drivable area based on the first planned path prevents the intelligent driving device from being unable to resume cruise control when switching back to the first planning mode, and also prevents the intelligent driving device from becoming stuck again after escaping a difficult situation.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining that the intelligent driving device avoids the first obstacle according to the second planned path when the intelligent driving device enters the preset range of the second target pose, or when the intelligent driving device passes the second target pose.

[0023] For example, the preset range of the second target pose can be a preset range of the center point of the second target pose. This preset range can be a range of 2 meters away from the center point of the second target pose, or it can be other ranges.

[0024] The above technical solution provides a method for determining when the vehicle has successfully escaped a difficult situation. This helps the intelligent driving device switch back to the first planning mode in a timely manner after escaping the difficult situation, reducing the time required for mode switching. This allows the intelligent driving device to stop driving without needing to be controlled when switching back from the second planning mode to the first planning mode, which helps improve traffic efficiency and user experience.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: when the intelligent driving device avoids the first obstacle according to the second planned path, controlling the intelligent driving device to switch from driving along the second planned path to driving along the third planned path, the third planned path being planned by the first planning mode.

[0026] In the above technical solution, when the intelligent driving device completes the extrication from the stalemate, switching back to the first planning mode for path planning helps to improve the planning capability for normal road conditions.

[0027] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: when the intelligent driving device avoids the first obstacle according to the second planned path, the control prompting device prompts to stop the second planning mode and / or start the first planning mode.

[0028] In the above technical solution, when switching planning modes, a prompting device is used to provide a prompt. When the driver of the intelligent driving device is in the loop, it helps the driver to know the current status of the vehicle so that the driver can take over the intelligent driving device in a timely manner.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: when there is a first obstacle in the first planned path that makes the passable width corresponding to the first area less than or equal to a first preset threshold, the control prompting device prompts to stop the first planning mode and / or start the second planning mode.

[0030] In conjunction with the first aspect, in some implementations of the first aspect, the second planning pattern includes a hybrid A* algorithm.

[0031] In the above technical solution, when switching planning modes, a prompting device is used to provide a prompt. When the driver of the intelligent driving device is in the loop, it helps the driver to know the current status of the vehicle so that the driver can take over the intelligent driving device in a timely manner.

[0032] In a second aspect, a control device is provided, comprising a first processing unit and a second processing unit, wherein the first processing unit is configured to: control an intelligent driving device to travel along a first planned path, the first planned path being planned by a first planning mode; and the second processing unit is configured to: when a first obstacle exists in the first planned path such that the passable width corresponding to the first area is less than or equal to a first preset threshold, and / or when the first obstacle causes the curvature of the feasible path in the first area to be greater than or equal to a second preset threshold, control the intelligent driving device to switch from traveling along the first planned path to traveling along a second planned path, the second planned path being planned by a second planning mode, wherein the first planning mode and the second planning mode are different, and the first planned path passes through the first area.

[0033] In conjunction with the second aspect, in some implementations of the second aspect, the first region includes a head end and a tail end, the head end of the first region being the end closest to the current position of the intelligent driving device, and the tail end of the first region being the end closest to the destination of the intelligent driving device; the second processing unit is used to: determine a first target pose of the intelligent driving device based on a first planned path; determine a second target pose based on the first target pose and the position of a first obstacle, the second target pose indicating the pose of the intelligent driving device exiting the tail end of the first region; and plan a second planned path based on the current pose of the intelligent driving device, the second target pose, and the first obstacle.

[0034] In conjunction with the second aspect, in some implementations of the second aspect, the second processing unit is further configured to: determine a drivable area along the first planned path based on the first planned path; and plan a second planned path within the drivable area based on the current pose, the second target pose, and the first obstacle.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, the second processing unit is further configured to: determine that the intelligent driving device avoids the first obstacle according to the second planned path when the intelligent driving device enters the preset range of the second target pose, or when the intelligent driving device passes the second target pose.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the second processing unit is further configured to: when the intelligent driving device avoids the first obstacle according to the second planned path, control the intelligent driving device to switch from driving along the second planned path to driving along the third planned path, the third planned path being planned by the first planning mode.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the second processing unit is further configured to: when the intelligent driving device avoids the first obstacle according to the second planned path, the control prompting device prompts to stop the second planning mode and / or start the first planning mode.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the second processing unit is further configured to: when there is a first obstacle in the first planned path that causes the passable width corresponding to the first area to be less than or equal to a first preset threshold, the control prompting device prompts to stop the first planning mode and / or start the second planning mode.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the second planning pattern includes a hybrid A* algorithm.

[0040] Thirdly, a control device is provided, comprising: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0041] Fourthly, an intelligent driving device is provided, which includes means as described in any possible implementation of the second or third aspect.

[0042] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the intelligent driving device is a vehicle.

[0043] Fifthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer, causes the computer to perform the method in any possible implementation of the first aspect.

[0044] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or packaged separately from the processor.

[0045] In a sixth aspect, a computer-readable medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0046] In a seventh aspect, a chip is provided, the chip including circuitry for performing the method in any of the possible implementations of the first aspect described above. Attached Figure Description

[0047] Figure 1 This is a functional block diagram of the vehicle provided in the embodiments of this application;

[0048] Figure 2 This is a schematic diagram of the system architecture required for implementing the control method provided in the embodiments of this application;

[0049] Figure 3 This is a schematic flowchart of a control method provided in an embodiment of this application;

[0050] Figure 4 This is a schematic diagram of a driving scenario according to an embodiment of this application;

[0051] Figure 5 This is another schematic flowchart of the control method provided in the embodiments of this application;

[0052] Figure 6 This is a schematic diagram of yet another driving scenario involved in an embodiment of this application;

[0053] Figure 7 This is a schematic diagram of a planned path provided in an embodiment of this application;

[0054] Figure 8 This is a schematic diagram of an HMI provided in an embodiment of this application;

[0055] Figure 9 This is another illustrative flowchart of the control method provided in the embodiments of this application;

[0056] Figure 10 This is a schematic block diagram of the control device provided in the embodiments of this application;

[0057] Figure 11 This is another schematic block diagram of the control device provided in the embodiments of this application. Detailed Implementation

[0058] To facilitate understanding of the technical solutions in the embodiments of this application, the concepts involved in this application are first introduced:

[0059] Trapped: refers to a state in which a vehicle is blocked by an obstacle and cannot move smoothly.

[0060] Getting out of trouble: refers to a vehicle getting out of a state where it is blocked by an obstacle and cannot move smoothly, so that it can continue to drive.

[0061] Parking cruise control: refers to the state in which the vehicle travels at a low speed when the target parking location has not been determined.

[0062] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0063] Figure 1 This is a functional block diagram of a vehicle provided in an embodiment of this application. For example... Figure 1As shown, the vehicle 100 may include a sensing system 120, a display device 130, and a computing platform 150. The sensing system 120 may include several sensors for sensing information about the environment surrounding the vehicle 100. For example, the sensing system 120 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou system, or another positioning system. As another example, the sensing system 120 may also include one or more of the following: an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0064] Some or all of the functions of vehicle 100 can be controlled by computing platform 150. Computing platform 150 may include processors 151 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include a memory for storing instructions. Some or all of the processors 151 to 15n can call the instructions in the memory to implement the corresponding functions.

[0065] The in-cabin display devices 130 are mainly divided into two categories: the first is in-vehicle displays; the second is projection displays, such as head-up displays (HUDs). In-vehicle displays are physical displays and an important component of in-vehicle infotainment systems. Multiple displays can be installed in the cabin, such as digital instrument cluster displays and central control screens. Head-up displays, also known as head-up display systems, are mainly used to display driving information such as speed and navigation on a display device in front of the driver (e.g., the windshield). This reduces driver eye movement time, avoids pupil changes caused by eye movement, and improves driving safety and comfort. HUDs include, for example, combiner-HUD (C-HUD) systems, windshield-HUD (W-HUD) systems, and augmented reality HUD (AR-HUD) systems. The display device may also include an interactive system 130 that includes a human-machine interface (HMI) to prompt the user about the switching of planning modes.

[0066] Vehicle 100 may include an advanced driving assistance system (ADAS). ADAS utilizes various sensors on the vehicle (including but not limited to: lidar, millimeter-wave radar, camera devices, ultrasonic sensors, global positioning system, inertial measurement unit) to acquire information from the vehicle's surroundings, and analyzes and processes the acquired information to achieve functions such as obstacle perception, target recognition, vehicle positioning, path planning, and driver monitoring / alerts, thereby improving the safety, automation, and comfort of driving the vehicle.

[0067] Logically, an ADAS system generally includes three main functional modules: a perception module, a decision-making module, and an execution module. The perception module senses the environment around the vehicle through sensors and inputs corresponding real-time data to the decision-making processing center. The perception module mainly includes vehicle cameras, ultrasonic radar, millimeter-wave radar, and lidar. The decision-making module makes corresponding decisions based on the information obtained by the perception module using computing devices and algorithms. After receiving the decision signal from the decision-making module, the execution module takes corresponding actions, such as driving, changing lanes, steering, braking, and issuing warnings.

[0068] At different levels of autonomous driving (L0-L5), ADAS can achieve different levels of automated driving assistance based on artificial intelligence algorithms and information acquired by multiple sensors. The aforementioned autonomous driving levels (L0-L5) are based on the classification standards of the Society of Automotive Engineers (SAE). L0 is no automation; L1 is driver assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At levels L1 to L3, the task of monitoring road conditions and reacting is jointly completed by the driver and the system, requiring the driver to take over dynamic driving tasks. At levels L4 and L5, the driver can completely transform into a passenger. Currently, the functions that ADAS can achieve mainly include, but are not limited to: adaptive cruise control, automatic emergency braking, automatic parking, blind spot monitoring, forward cross-traffic alert / braking, rear cross-traffic alert / braking, forward collision warning, lane departure warning, lane keeping assist, rear collision warning, traffic sign recognition, traffic jam assist, and highway assist. It should be understood that the various functions mentioned above can have specific modes at different levels of autonomous driving (L0-L5), with higher levels of autonomous driving corresponding to more intelligent modes. For example, automatic parking can include APA, RPA, and AVP. With APA, the driver does not need to operate the steering wheel, but still needs to monitor the vehicle's status in real time. With RPA, the driver can remotely park the vehicle from outside using a terminal (e.g., a mobile phone). With AVP, the vehicle can park without a driver. In terms of corresponding autonomous driving levels, APA is approximately at Level 2, RPA is approximately at Level 2-L3, and AVP is approximately at Level 4.

[0069] In this embodiment, the computing platform 150 can switch motion planning modes based on obstacle information in the driving path of the vehicle 100 obtained by the perception system 120, thereby improving the vehicle's traffic efficiency and parking efficiency.

[0070] Figure 2 A schematic diagram of the control system architecture provided in an embodiment of this application is shown. For example... Figure 2 As shown, the system includes a sensing module 210, an obstacle detection module 220, a motion planning module 230, a motion control module 240, and an actuator 250. The sensing module 210 may include... Figure 1 The sensing system 120 shown includes one or more sensors, and the obstacle detection module 220, motion planning module 230, and motion control module 240 can be respectively... Figure 1 One or more processors in the computing platform 150 shown.

[0071] The perception module 210 is used to collect environmental information around the vehicle, including the location and type of obstacles around the vehicle. The perception module 210 can input the obstacle information into the obstacle detection module 220 and the motion planning module 230.

[0072] The obstacle detection module 220 can determine the passable width of the vehicle's current driving path based on the obstacle information collected by the perception module 210, so that the motion planning module 230 can determine the planning mode based on the passable width of the vehicle's current driving path.

[0073] The motion planning module 230 includes a conventional mode planning module 231 and an escape mode planning module 232. The conventional mode planning module 231 can plan a driving path based on existing algorithms (e.g., the current parking cruise algorithm) when the passable width of the driving path is greater than a preset threshold 1. The escape mode planning module 232 can include a target pose generation module, a drivable area generation module, a path planning module, and an end-of-path determination module. The escape mode planning module 232 can plan a driving path for the vehicle when the passable width of the driving path is less than or equal to the preset threshold 1. It should be noted that the conventional mode planning module 231 and the escape mode planning module 232 have different planning capabilities. For example, the conventional mode planning module 231 can generally only perform forward path planning, and its planning capability is weak for areas requiring multiple reversing maneuvers to avoid obstacles (such as areas with narrow drivable roads or areas with complex obstacle positions).

[0074] The motion control module 240 can calculate the corresponding control quantity based on the path planned by the motion planning module 230, and output the control quantity to the actuator 250. When the actuator 250 executes the control quantity, it controls the vehicle to travel along the planned path. In some possible implementations, the actuator may include the steering and braking control system in the vehicle 100.

[0075] For example, when the vehicle is traveling along the driving path 1 planned by the conventional mode planning module 231, and the obstacle detection module 220 determines that the passable width of the driving path in front of the vehicle is less than or equal to a preset threshold 1, the motion control module 240 controls the vehicle to stop, and the motion planning module 230 switches to the escape mode planning module 232 to perform path planning. Specifically, the target pose generation module can generate one or more target poses based on the driving path 1 and / or the position of the obstacle, and perform collision detection based on the obstacle detected by the perception module 210, selecting the target pose 1 from the one or more target poses that can pass through the position of the obstacle without colliding with the obstacle; the drivable area generation module generates a drivable area based on the driving path 1 and the obstacle detected by the perception module 210; the path planning module generates a driving path 2 for the vehicle in the drivable area based on the target pose 1 and the vehicle's pose when it is stopped, and inputs the driving path 2 into the motion control module 240 to control the vehicle to travel along the driving path 2. When the vehicle is traveling along the driving path 2, the end judgment module monitors the vehicle's driving position. When it is determined that the vehicle has passed a position where the passable width is less than or equal to the preset threshold 1, the motion planning module 230 switches from the escape module planning module 232 back to the normal mode planning module 231 to continue path planning.

[0076] It should be understood that the above module is only an example, and in actual applications, it may be added or removed as needed. For example, Figure 2 In the system architecture shown, the motion planning module 230 and the motion control module 240 can be combined into one module; or, the obstacle detection module 220 and the motion planning module 230 can be combined into one module. For example, the system also includes a prompting module that receives information from the motion planning module 230 and issues a prompt message when the motion planning module 230 switches modes to indicate the occurrence of the mode switch.

[0077] Figure 3 A schematic flowchart of a control method provided in an embodiment of this application is shown. This method can be applied to... Figure 1 In the vehicle shown, or the method can be derived from Figure 2 The system shown executes the method. For example, the following description assumes the method is executed by the vehicle's computing platform; the method 300 may include:

[0078] S301 controls the vehicle to travel along a first path based on a first planning mode and detects obstacles in the first path.

[0079] For example, the first planning mode can be a path planning mode performed by the conventional planning module 231 described above, and the first path can include the driving path 1 described above.

[0080] In one example, when planning a driving route for a vehicle in the first planning mode, the planning can be based on a map stored in the vehicle. For instance, when a vehicle is parked in a parking lot, if the vehicle has a map of that parking lot stored in it, the vehicle can plan the first route based on that map and the parking information of each parking space collected in real time by the vehicle.

[0081] In another example, when planning a driving path for a vehicle in the first planning mode, the planning can be based on the surrounding environmental information collected by the vehicle in real time. For example, when a vehicle is parked in a parking lot, the vehicle's sensors can collect environmental information within a range of 200 meters in front of the vehicle. The vehicle can then plan a path from its current position to 200 meters in front of it based on this environmental information. This path can be considered an example of the first path.

[0082] It should be noted that the first path refers to the path from the vehicle's current location to its destination. The vehicle's destination can be its final destination or any point along the route the vehicle takes towards its final destination.

[0083] S302, when the first obstacle makes the passable width of a certain area of ​​the first path less than or equal to a preset threshold 1, or when the first obstacle makes the curvature of the feasible path of a certain area of ​​the first path greater than or equal to a preset threshold 2, switch to the second planning mode to plan the vehicle's driving path.

[0084] For example, the first obstacle is an obstacle in the first path, and the second planning mode can be a path planning mode performed by the above-mentioned escape mode planning module 232.

[0085] For example, the preset threshold 1 can be 2.5 meters, or it can be 2.3 meters, or it can be other values, such as those determined based on the actual width of the vehicle. The preset threshold 2 can be 0.01, or it can be 0.1, or it can be other values.

[0086] It should be noted that a segment of the aforementioned first path may not be part of the planned route for the vehicle; this segment may have a special shape due to the presence of the first obstacle. A segment of the first path can be understood as either including the first path or being a segment the vehicle must traverse to reach its destination from its current position. For example, the first path may be a route planned based on the vehicle's current position and destination, without considering the impact of obstacles during the planning process. However, if the presence of an obstacle in a certain area of ​​the first path results in insufficient passable width or excessive curvature of the feasible path, causing the vehicle to be blocked and unable to proceed at the planned speed and along the planned route when traveling along the first path to this point, the obstacle will prevent it from doing so.

[0087] like Figure 4 As shown in (a), the planned travel path for vehicle 401 is path 405 or path 406. Due to the presence of vehicles 402, 403, and 404, the passable width of area 407 is relatively small. When vehicle 401 travels to area 407, it may be blocked and unable to travel at the planned speed. Path 405 or path 406 can be regarded as the first path, and area 407 can be regarded as a certain area passed through by the aforementioned first path.

[0088] like Figure 4 As shown in (b), the planned driving path for vehicle 410 is path 411, which passes through obstacle 412. In other words, due to the presence of obstacle 412, vehicle 410 may be blocked and unable to travel at the planned speed when it reaches obstacle 412. However, in order to move forward, vehicle 410 must pass through area 414. At this time, area 414 can be regarded as a certain area traversed by the first path mentioned above.

[0089] Hereinafter, a certain area along the first path is referred to as the first area. The first area includes a beginning and a end. The beginning of the first area is the end closest to the current location of the vehicle, and the end of the first area is the end closest to the vehicle's destination.

[0090] When the vehicle reaches the beginning of the first area, it may stop due to the first obstacle. The coordinates of the vehicle's position when it stops are recorded, and the system switches to the second mode to plan a driving path for the vehicle.

[0091] S303 plans a second path using a second planning mode, allowing the vehicle to avoid the first obstacle while traveling along the second path.

[0092] In some possible implementations, when the passable width corresponding to the first area is less than or equal to a preset threshold 1 and greater than or equal to a preset threshold 3, a second path is planned based on the first path and the first obstacle. Here, the preset threshold 3 can be the width of the vehicle, or it can be any other value larger than the width of the vehicle.

[0093] In some possible implementations, when the passable width corresponding to the first area is less than or equal to a preset threshold 1 and less than a preset threshold 3, in the second planning mode, the path for the vehicle is replanned based on the position of the first obstacle.

[0094] In some possible implementations, the second path includes a beginning and a end. The beginning of the second path is the starting point of the path, and the end of the second path coincides with the end of the first area, or the end of the second path is closer to the vehicle's destination than the end of the first area.

[0095] S304, when the vehicle has completed its journey along the second path, switch to the first planning mode to continue planning a driving path for the vehicle.

[0096] For example, when the vehicle reaches the end of the second path, it is determined that the vehicle has completed its journey along the second path. At this point, the system switches to the first planning mode to continue planning a driving path for the vehicle.

[0097] The following combination Figure 5 The specific method for planning the second path under the second planning model is explained. For example... Figure 5 As shown, the method 500 may include:

[0098] S501, Generate the target pose based on the first path.

[0099] For example, when the target pose generation module receives an indication that the vehicle has stopped due to an obstacle, it generates a target pose based on the first path. For example, when the vehicle stops due to an obstacle, the state machine in the motion control module changes to a stop flag, and the aforementioned indication information may include the stop flag of the state machine.

[0100] For example, when the vehicle stops due to obstruction by a first obstacle, one or more target poses are generated based on the position of the first obstacle and the first path. For instance, a target pose is generated where the longitudinal axis is parallel to the tangent of the first path at a first position, and the center point of the target pose is the first position. Here, the first position is a location on the first path behind the first obstacle; "behind the first obstacle" can be understood as the side closer to the vehicle's destination. Another example is generating multiple target poses where the longitudinal axis is parallel to the tangent of the first path at the first position. Yet another example is generating multiple poses where the longitudinal axis is parallel to the tangent at different positions on the first path, all of which are behind the first obstacle and may include the first position.

[0101] In some possible implementations, the target pose can also be generated based on the distribution information of the first obstacle.

[0102] The target pose longitudinal axis is parallel to the vehicle's longitudinal symmetry plane (or Y-reference plane).

[0103] S502 performs a collision check on the target pose and verifies the feasibility of the target pose that passes the collision check.

[0104] For example, a collision check can be performed on each of the above one or more target poses, that is, to determine whether the vehicle will collide with the first obstacle when it is in the target pose.

[0105] For example, collision detection can be performed using the GJK (Gilbert–Johnson–Keerthi) algorithm, or using the separating axis theorem (SAT), or other methods.

[0106] Furthermore, the feasibility of one or more target poses that pass collision detection is verified.

[0107] It should be noted that, in this embodiment, feasibility verification refers to verifying whether the target pose is passable, or verifying whether the target pose can reach the end of the first area. If the feasibility verification is successful, it indicates that the first obstacle will not affect the vehicle's movement from the beginning to the end of the first area.

[0108] S503, determine whether the feasibility verification of the target pose has passed.

[0109] Specifically, if the feasibility verification of the target pose is successful, execute S505; otherwise, execute S504.

[0110] For example, the feasibility of the target pose can be verified by the fast A* detection algorithm, that is, to verify whether the vehicle can drive out of the tail end of the first area with a certain target pose.

[0111] For example, when target pose 1 passes the feasibility verification, target pose 1 can be used as the escape target pose for planning the second path. Target pose 1 is one of the above-mentioned target poses.

[0112] It should be noted that the target position for getting out of trouble indicates the position of the vehicle when it leaves the rear of the first area.

[0113] S504, Adjust the lateral and / or longitudinal position of the target pose.

[0114] For example, for a target pose that does not meet the collision check or fails the feasibility verification, an adjustment is made by first lateral translation and then longitudinal translation to avoid the first obstacle.

[0115] S505, determine virtual boundary 1 and virtual boundary 2 based on the first path.

[0116] For example, virtual boundary 1 and virtual boundary 2 are generated on both sides of the first path at a preset distance.

[0117] For example, the preset distance can be 2 meters, or 2.5 meters, or other values.

[0118] S506, Elimination of abnormal boundary points at large curvature corners.

[0119] In some possible implementations, the first region includes large curvature corners, which may result in abnormal boundary points when generating the virtual boundary. In this case, it is necessary to eliminate the abnormal boundary points to generate a continuous virtual boundary.

[0120] S507, virtual boundary 1 and virtual boundary 2 are mapped onto the obstacle map, and the area between virtual boundary 1 and virtual boundary 2 is the drivable area.

[0121] For example, the virtual boundary 1 and virtual boundary 2 are mapped onto an obstacle map to become virtual obstacles, so that the drivable area of ​​the vehicle can be restricted to this area during planning.

[0122] It should be noted that after mapping virtual boundary 1 and virtual boundary 2 onto the obstacle map, the virtual boundaries and the first obstacle constitute a new obstacle. When the vehicle performs path planning, it needs to perform path planning based on the position of this new obstacle.

[0123] Vehicle 600 Figure 6 When driving in the parking lot shown in (a), a driving path 601 is planned for vehicle 600 in the first planning mode. However, due to the presence of obstacles on both sides of driving path 601, vehicle 600 drives to... Figure 6 The vehicle 600 stops at the location shown in (b) because it is blocked by an obstacle. At this time, the vehicle switches to the second planning mode to continue planning and generates virtual boundaries 602 and 603 based on the driving path 601. For example, when the virtual boundaries 602 and 603 are mapped onto the obstacle map, the obstacle map may include both virtual boundaries and obstacle boundaries (such as obstacle boundaries 604 and 605).

[0124] S508 plans a second path based on the first obstacle within the drivable area.

[0125] For example, a second path for the vehicle is planned in the drivable area based on the vehicle's current pose and the target pose 1 determined in S503.

[0126] In one example, a second path can be generated using a hybrid A* algorithm. For instance, first initialize open and closed lists, and offline generate the node to be expanded based on vehicle kinematic constraints as the state increment of the current node. Add the vehicle's current pose to the open list, expand the node to be expanded using kinematic and obstacle avoidance constraints (such as virtual boundary 1, virtual boundary 2, and the first obstacle), set the parent node as the current node, and remove the starting point from the open list and add it to the closed list. Then repeat the following steps: First, calculate the evaluation function values ​​of all nodes in the open list, select the node with the smallest value as the new expanded node, remove it from the open list, and add it to the closed list; check which nodes this node can expand using vehicle kinematic constraints, while simultaneously satisfying no collision with obstacles and not being in the closed list. If the node to be expanded is not in the open list, add it to the open list and set the current node as the parent node; if the node to be expanded is already in the open list, calculate the evaluation function value of the node under this expansion method, compare it with the original evaluation function value, take the smaller of the two, and update the parent node. The completion condition for the repeated steps is that if the node to be expanded falls within a certain range of the target pose 1, the search can be considered successful; if the completion condition is not met until the open list is empty, the search will fail and exit.

[0127] In another example, a second path can be generated using geometric methods. For instance, the connection from the vehicle's current pose to the target pose 1 can be achieved by splicing multiple straight-arc segments. The variables of the target pose 1 include the x-coordinate, y-coordinate, and heading angle. Describing the geometric relationship between these variables after splicing the straight lines and arcs, a system of linear equations can be established and solved to obtain the lengths of the straight lines and arcs and the splicing method. The splicing patterns of straight-arc segments include straight-arc, arc-straight, and straight-arc-straight. If the path from the current pose to the target pose 1 cannot be planned in one step, intermediate poses still need to be found. The entire problem is then divided and conquered, and the complete path is obtained by solving the sub-problems. For example, the first region can be segmented into multiple regions. A path can be generated for each of these multiple regions using geometric methods, and the paths in the multiple regions can be spliced ​​to obtain the second path.

[0128] For example, such as Figure 7 As shown, in the drivable area formed by virtual boundaries 602 and 603, the second path planned according to the first obstacle can be as shown in path 606.

[0129] S509 monitors the vehicle's driving status while controlling the vehicle to travel along the second path to determine whether the vehicle's extrication from the predicament has been completed.

[0130] In one possible implementation, an endpoint circle criterion or endpoint line criterion is designed. When the vehicle's pose satisfies the endpoint circle criterion or endpoint line criterion, it is determined that the vehicle has completed its escape from the predicament.

[0131] For example, the endpoint circle criterion can be: the vehicle is considered to have successfully escaped the predicament when it enters a certain range of the target pose 1. This certain range can be a range 2 meters from the center of the target pose 1, or it can be any other range. The endpoint line criterion can be: the vehicle is considered to have successfully escaped the predicament when it passes the target pose 1.

[0132] In some possible implementations, once it is determined that the vehicle has successfully extricated itself from the predicament, the system switches back to the first planning mode to continue planning a driving path for the vehicle.

[0133] It should be noted that in the actual implementation process, it is not necessary to execute... Figure 5 All operations within the process, for example, may omit S504 and / or S506. Furthermore, Figure 5 The operations shown may not be performed in the order shown in the figure. For example, S505 to S507 may be performed simultaneously with S501 to S504.

[0134] The control method provided in this application offers two path planning modes. During vehicle operation, the mode is switched according to actual road conditions. This not only helps reduce the computational power required for path planning but also improves the vehicle's ability to overcome obstacles. Especially during AVP parking, it reduces the likelihood of the vehicle being unable to plan a path in narrow passages or scenarios with complex obstacle positions, thus increasing the success rate of AVP parking.

[0135] In some possible implementations, when the vehicle switches modes, the user can be notified of the mode change via an HMI or a speaker / audio device. For example, Figure 8 As shown in (a), during vehicle parking, when the vehicle is about to switch from the first planning mode (such as the normal mode) to the second planning mode (such as the obstacle avoidance mode), a prompt can be displayed on the central control screen: "! Switching to obstacle avoidance mode for parking is imminent." Figure 8 As shown in (b), when the vehicle has successfully escaped the obstacle and is about to switch back to the first planning mode from the second planning mode, a notification can be displayed on the central control screen: "!Extrication complete, about to switch to normal parking mode." It should be understood that... Figure 8 The illustration shown is merely illustrative. In actual implementation, prompts can also be displayed after mode switching.

[0136] Figure 9 A schematic flowchart of a control method provided in an embodiment of this application is shown. This method can be applied to intelligent driving devices, and the method 900 may include:

[0137] S901 controls the intelligent driving device to travel along a first planned path, which is a path planned through a first planning mode.

[0138] For example, the intelligent driving device includes the vehicle in the above embodiments, the first planned path includes the first path in the above embodiments, and the first planning mode includes the first planning mode in the above embodiments.

[0139] S902, when there is a first obstacle in the first planned path that makes the passable width of the first area less than or equal to a first preset threshold, and / or when the first obstacle makes the curvature of the feasible path in the first area greater than or equal to a second preset threshold, the intelligent driving device is controlled to switch from driving along the first planned path to driving along the second planned path. The second planned path is planned by the second planning mode. The first planning mode and the second planning mode are different. The first planned path passes through the first area.

[0140] For example, the second planning mode includes the second planning mode in the above embodiments, and the second planning path includes the second path in the above embodiments.

[0141] For example, the first region includes the first region in the above embodiments. The first region includes a head end and a tail end. The head end of the first region is the end closer to the current position of the intelligent driving device, and the tail end of the first region is the end closer to the destination of the intelligent driving device.

[0142] In some possible implementations, the method further includes: determining a first target pose of the intelligent driving device based on a first planned path; determining a second target pose based on the first target pose and the position of a first obstacle, the second target pose indicating the pose of the intelligent driving device as it exits the first area; and planning a second path based on the current pose of the intelligent driving device, the second target pose, and the first obstacle.

[0143] For example, the first target pose may include the target pose generated in S501; the second target pose may include target pose 1. The specific method for determining the second target pose based on the first target pose and the position of the first obstacle can be referred to the description in S502 and S503, and will not be repeated here.

[0144] In some possible implementations, the method further includes: determining a drivable area along the first planned path based on the first planned path; and planning a second planned path based on the current pose of the intelligent driving device and a second target pose, including: planning the second planned path in the drivable area based on the current pose, the second target pose, and the first obstacle.

[0145] For example, the specific method for planning a second planned path in a drivable area can be referred to the description in S508, and will not be repeated here.

[0146] In some possible implementations, when the intelligent driving device avoids the first obstacle according to the second planned path, the intelligent driving device is controlled to switch from driving along the second planned path to driving along the third planned path, which is planned by the first planning mode.

[0147] For example, when the intelligent driving device enters a preset range of the second target pose, or when the intelligent driving device passes the second target pose, it is determined that the intelligent driving device avoids the first obstacle according to the second planned path.

[0148] In some possible implementations, the method further includes: when the intelligent driving device avoids the first obstacle according to the second planned path, the control prompting device prompts to stop the second planning mode and / or start the first planning mode.

[0149] In some possible implementations, the method further includes: when a first obstacle exists in the first planned path such that the passable width corresponding to the first area is less than or equal to a first preset threshold, and / or when the first obstacle makes the curvature of the feasible path in the first area greater than or equal to a second preset threshold, the control prompting device prompts to stop the first planning mode and / or start the second planning mode.

[0150] For specific prompting methods of the above-mentioned prompting devices, please refer to [link / reference]. Figure 8 The descriptions of the corresponding parts will not be repeated here.

[0151] The control method provided in this application helps improve the traction capability of automatic parking functions, reduces the probability that vehicles cannot plan their routes due to narrow roads or complex road conditions, and increases the parking success rate. Using this method, the traction function can be automatically triggered when stuck in narrow passages with high curvature, without needing to identify specific scenarios, and has wide applicability in complex situations.

[0152] The above text combines Figures 1 to 9 The methods provided in the embodiments of this application are described in detail below. Figure 10 and Figure 11 The apparatus provided in the embodiments of this application is described in detail. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, it will not be repeated here.

[0153] Figure 10A schematic block diagram of a control device 2000 provided in an embodiment of this application is shown. The device 2000 includes a first processing unit 2010 and a second processing unit 2020. The first processing unit 2010 is used to: control an intelligent driving device to travel along a first planned path, which is planned by a first planning mode. The second processing unit 2020 is used to: when a first obstacle exists in the first planned path such that the passable width corresponding to a first area is less than or equal to a first preset threshold, and / or when the first obstacle causes the curvature of the feasible path in the first area to be greater than or equal to a second preset threshold, control the intelligent driving device to switch from traveling along the first planned path to traveling along a second planned path, which is planned by a second planning mode. The first planning mode and the second planning mode are different, and the first planned path passes through the first area.

[0154] Optionally, the first region includes a head end and a tail end, the head end of the first region being the end closest to the current position of the intelligent driving device, and the tail end of the first region being the end closest to the destination of the intelligent driving device; the second processing unit 2020 is used to: determine a first target pose of the intelligent driving device according to a first planned path; determine a second target pose according to the first target pose and the position of a first obstacle, the second target pose indicating the pose of the intelligent driving device exiting the tail end of the first region; and plan a second planned path according to the current pose of the intelligent driving device, the second target pose, and the first obstacle.

[0155] Optionally, the second processing unit 2020 is further configured to: determine a drivable area along the first planned path based on the first planned path; and plan a second planned path in the drivable area based on the current pose, the second target pose, and the first obstacle.

[0156] Optionally, the second processing unit 2020 is further configured to: determine that the intelligent driving device avoids the first obstacle according to the second planned path when the intelligent driving device enters the preset range of the second target pose, or when the intelligent driving device passes the second target pose.

[0157] Optionally, the second processing unit 2020 is further configured to: when the intelligent driving device avoids the first obstacle according to the second planned path, control the intelligent driving device to switch from driving along the second planned path to driving along the third planned path, the third planned path being planned by the first planning mode.

[0158] Optionally, the second processing unit 2020 is further configured to: when the intelligent driving device avoids the first obstacle according to the second planned path, the control prompting device prompts to stop the second planning mode and / or start the first planning mode.

[0159] Optionally, the second processing unit 2020 is further configured to: when there is a first obstacle in the first planned path that makes the passable width corresponding to the first area less than or equal to a first preset threshold, the control prompting device prompts to stop the first planning mode and / or start the second planning mode.

[0160] Optionally, the second planning mode includes a hybrid A* algorithm.

[0161] For example, the first processing unit 2010 and the second processing unit 2020 may be configured in Figure 2 In the illustrated system, more specifically, the first processing unit 2010 can be located in the obstacle detection module 220, and the second processing unit 2020 can be located in the motion planning module 230. Exemplarily, the operations performed by the first processing unit 2010 and the second processing unit 2020 can be executed by a single processor, or they can be executed by different processors. In specific implementations, the one or more processors can be located in the obstacle detection module 220. Figure 1 The processor in the vehicle 100 shown; or, the device 2000 described above may be a chip disposed in the vehicle 100.

[0162] In the specific implementation process, the units in the above device can be integrated together in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0163] Figure 11 This is a schematic block diagram of the control device provided in the embodiments of this application. Figure 11 The control device 2100 shown may include a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, transceiver 2120, and memory 2130 are connected via internal interconnection paths. The memory 2130 stores instructions, and the processor 2110 executes the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 may be coupled to the processor 2110 via an interface or integrated with the processor 2110.

[0164] It should be noted that the transceiver 2120 mentioned above may include, but is not limited to, transceiver devices such as input / output interfaces, to realize communication between device 2100 and other devices or communication networks.

[0165] The memory 2130 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).

[0166] Transceiver 2120 uses transceiver devices, such as but not limited to transceivers, to enable communication between device 2100 and other devices or communication networks to receive / send data / information for implementing the methods in the above embodiments.

[0167] In specific implementation, the device 2100 can be set at... Figure 2 Among the smart devices 100 shown.

[0168] This application embodiment also provides an intelligent driving device, which includes the above-described device 2000 or the above-described device 2100.

[0169] The intelligent driving devices involved in this application can include road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment. For example, an intelligent driving device can be a vehicle, which is a vehicle in a broad sense, including transportation vehicles (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The embodiments of this application do not specifically limit the type of vehicle. Furthermore, a vehicle can be an airplane or a ship, etc.

[0170] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to implement the methods described in the above embodiments of this application.

[0171] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to implement the methods described in the above embodiments of this application.

[0172] This application also provides a chip, including circuitry, for performing the methods described in the above embodiments of this application.

[0173] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, power-on erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0174] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0175] In the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. In this application, "at least one" means one or more, and "more" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0176] The use of prefixes such as "first" and "second" in this application embodiment is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions.

[0177] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0178] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0179] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0180] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0181] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A valet parking control method characterized by comprising: include: Control the intelligent driving device to drive along a first planned path, which is planned by a first planning mode; When there is a first obstacle in the first planning path that makes the passable width of the first area less than or equal to a first preset threshold, and / or when the first obstacle makes the curvature of the feasible path in the first area greater than or equal to a second preset threshold, in the second planning mode, the first target pose of the intelligent driving device is determined according to the first planning path. The first planned path passes through the first region, which includes a beginning and a end. The beginning of the first region is the end closest to the current location of the intelligent driving device, and the end of the first region is the end closest to the destination of the intelligent driving device. A second target pose is determined based on the first target pose and the position of the first obstacle, and the second target pose indicates the pose of the intelligent driving device as it exits the first area. A second planned path is planned based on the current pose of the intelligent driving device, the second target pose, and the first obstacle; The intelligent driving device is controlled to switch from driving along the first planned path to driving along the second planned path, and the first planning mode and the second planning mode are different.

2. The method of claim 1, wherein, The method further includes: Determine the drivable area along the first planned path based on the first planned path; The step of planning a second planned path based on the current pose of the intelligent driving device and the second target pose includes: Based on the current pose, the second target pose, and the first obstacle, a second planned path is planned in the drivable area.

3. The method of claim 1, wherein, The method further includes: When the intelligent driving device enters the preset range of the second target pose, or when the intelligent driving device passes the second target pose, it is determined that the intelligent driving device avoids the first obstacle according to the second planned path.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: When the intelligent driving device avoids the first obstacle according to the second planned path, the intelligent driving device is controlled to switch from driving along the second planned path to driving along the third planned path, which is planned by the first planning mode.

5. The method of claim 4, wherein, The method further includes: When the intelligent driving device avoids the first obstacle according to the second planned path, the control prompting device prompts to stop the second planning mode and / or start the first planning mode.

6. The method according to any one of claims 1 to 3, characterized in that, The method further includes: When a first obstacle exists in the first planned path, causing the passable width of the first area to be less than or equal to the first preset threshold, and / or when the first obstacle causes the curvature of the feasible path in the first area to be greater than or equal to the second preset threshold, the control prompting device prompts to stop the first planning mode and / or start the second planning mode.

7. The method according to any one of claims 1 to 3, characterized in that, The second planning mode includes hybrid A algorithm.

8. A valet parking control device, characterized in that, It includes a first processing unit and a second processing unit, wherein, The first processing unit is used to: control the intelligent driving device to drive along a first planned path, the first planned path being planned by a first planning mode; The second processing unit is used to: determine the first target pose of the intelligent driving device according to the first planning path when there is a first obstacle in the first planning path that makes the passable width of the first area less than or equal to a first preset threshold, and / or when the first obstacle makes the curvature of the feasible path in the first area greater than or equal to a second preset threshold; The first planned path passes through the first region, which includes a beginning and a end. The beginning of the first region is the end closest to the current location of the intelligent driving device, and the end of the first region is the end closest to the destination of the intelligent driving device. The second processing unit is further configured to: determine a second target pose based on the first target pose and the position of the first obstacle, wherein the second target pose indicates the pose of the intelligent driving device as it exits the first area; A second planned path is planned based on the current pose of the intelligent driving device, the second target pose, and the first obstacle; The intelligent driving device is controlled to switch from driving along the first planned path to driving along the second planned path, and the first planning mode and the second planning mode are different.

9. The apparatus of claim 8, wherein, The second processing unit is further configured to: Determine the drivable area along the first planned path based on the first planned path; Based on the current pose, the second target pose, and the first obstacle, a second planned path is planned in the drivable area.

10. The apparatus of claim 8, wherein, The second processing unit is further configured to: When the intelligent driving device enters the preset range of the second target pose, or when the intelligent driving device passes the second target pose, it is determined that the intelligent driving device avoids the first obstacle according to the second planned path.

11. The apparatus of any one of claims 8-10, wherein, The second processing unit is further configured to: When the intelligent driving device avoids the first obstacle according to the second planned path, the intelligent driving device is controlled to switch from driving along the second planned path to driving along the third planned path, which is planned by the first planning mode.

12. The apparatus of claim 11, wherein, The second processing unit is further configured to: When the intelligent driving device avoids the first obstacle according to the second planned path, the control prompting device prompts to stop the second planning mode and / or start the first planning mode.

13. The apparatus of any one of claims 8-10, wherein, The second processing unit is further configured to: When a first obstacle exists in the first planned path, causing the passable width of the first area to be less than or equal to the first preset threshold, and / or when the first obstacle causes the curvature of the feasible path in the first area to be greater than or equal to the second preset threshold, the control prompting device prompts to stop the first planning mode and / or start the second planning mode.

14. The apparatus of any one of claims 8-10, wherein, The second planning mode includes hybrid A algorithm.

15. A valet parking control apparatus, characterised in that, include: Memory, used to store computer programs; A processor for executing a computer program stored in the memory to cause the apparatus to perform the method as described in any one of claims 1 to 7.

16. An intelligent driving device, characterized by comprising: The intelligent driving device includes the apparatus as described in any one of claims 8 to 15.

17. A computer readable storage medium characterized by: It stores instructions that, when executed by a processor, cause the processor to implement the method as described in any one of claims 1 to 7.

18. A chip, characterized by The chip includes circuitry for performing the method as described in any one of claims 1 to 7.

Images