Driving control method and device of hovercar, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a running control method and device of a hovercar, a storage medium and electronic equipment, and the method comprises the steps: in the process that the hovercar autonomously flies according to a set running path, under the condition that a sensing device on the hovercar senses a target obstacle blocking the running path, controlling the hovercar to run according to the target obstacle; determining the priority of the target obstacle according to the set of specified features of the target obstacle; according to the priority of the target obstacle, configuring an avoidance distance for the target obstacle; and performing three-dimensional planning of a local path for the hovercar based on the avoidance distance of the target obstacle, and controlling the hovercar to run according to a detour path under the condition that the detour path meeting the distance condition is planned. Through the driving control method and device, the technical problem that the driving safety of autonomous flight is poor in the driving control method of the hovercar in the related technology can be solved, and the technical effect of improving the driving safety of autonomous flight is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of flying cars. Specifically, the embodiments of the present application relate to a driving control method and device, a storage medium, and an electronic device for a flying car. Background Art

[0002] As a new type of transportation vehicle, a flying car combines the characteristics of a car and an airplane and can realize the function of both land and air use. It has basic features such as electric vertical takeoff and landing, and land-air amphibious transportation. A flying car can be configured with an autonomous flight mode, and it can travel according to a set driving path. However, in the low-altitude or ground environment of a city, static obstacles such as buildings (buildings, water towers, etc.), utility poles, and billboards are densely distributed and have various shapes. In the outdoor environment, there are a large number of natural obstacles such as trees and mountains. The flying car may collide with these obstacles, which will not only cause damage to its own structure but may also lead to serious safety accidents, endangering the lives of passengers and the safety of surrounding personnel and facilities.

[0003] It can be seen that the driving control method of the flying car in the related technology has the technical problem of poor driving safety in autonomous flight. Summary of the Invention

[0004] The embodiments of the present application provide a driving control method and device, a storage medium, and an electronic device for a flying car, so as to at least solve the technical problem of poor driving safety in autonomous flight existing in the driving control method of the flying car in the related technology.

[0005] According to one aspect of the embodiments of the present application, a driving control method for a flying car is provided, including: during the process of the flying car performing autonomous flight according to a set driving path, when a target obstacle blocking the driving path is sensed by a sensing device on the flying car, determining the priority of the target obstacle according to a set of specified features of the target obstacle; configuring an avoidance distance for the target obstacle according to the priority of the target obstacle, where the avoidance distance of the target obstacle is the closest distance allowed between the flying car and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle; performing three-dimensional planning of a local path for the flying car based on the avoidance distance of the target obstacle, and when a detour path that meets the distance condition is planned, controlling the flying car to travel according to the detour path, where the distance condition is that the minimum distance between the flying car and the target obstacle when the flying car travels along the planned path is greater than or equal to the avoidance distance of the target obstacle.

[0006] According to another aspect of the embodiments of the present application, there is also provided a driving control device for a flying car, including: a determining unit, configured to determine the priority of a target obstacle that blocks the driving path according to a set of specified features of the target obstacle when the flying car autonomously flies along a set driving path and the target obstacle is sensed by a sensing device on the flying car; a configuring unit, configured to configure an avoidance distance for the target obstacle according to the priority of the target obstacle, where the avoidance distance of the target obstacle is the closest distance allowed between the flying car and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle; a control unit, configured to perform three-dimensional planning of a local path for the flying car based on the avoidance distance of the target obstacle, and when a detour path that meets the distance condition is planned, control the flying car to drive along the detour path, where the distance condition is that the minimum distance between the flying car and the target obstacle when the flying car drives along the planned path is greater than or equal to the avoidance distance of the target obstacle.

[0007] According to yet another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium storing a computer program, where the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0008] According to yet another aspect of the embodiments of the present application, there is provided a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in any one of the above method embodiments.

[0009] According to yet another aspect of the embodiments of the present application, there is also provided an electronic device including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to execute the steps in any one of the above method embodiments through the computer program.

[0010] Through this application, by means of intelligently sensing obstacles, configuring avoidance distances for obstacles according to the priorities of the obstacles, and performing local path optimization based on the avoidance distances of the obstacles, during the autonomous flight of a flying vehicle along a set driving path, when a target obstacle blocking the driving path is sensed by a sensing device on the flying vehicle, the priority of the target obstacle is determined according to a set of specified features of the target obstacle; according to the priority of the target obstacle, an avoidance distance is configured for the target obstacle, where the avoidance distance of the target obstacle is the closest distance allowed between the flying vehicle and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle; based on the avoidance distance of the target obstacle, a three-dimensional plan of the local path is made for the flying vehicle, and when a detour path that meets the distance condition is planned, the flying vehicle is controlled to travel along the detour path, where the distance condition is that the minimum distance between the flying vehicle and the target obstacle when the flying vehicle travels along the planned path is greater than or equal to the avoidance distance of the target obstacle. Since when an obstacle blocking the driving path is sensed, an avoidance distance is configured for the obstacle and a local path is re-planned for the flying vehicle according to the avoidance distance of the obstacle to bypass the obstacle, the technical effect of improving the driving safety of autonomous flight can be achieved, thereby solving the technical problem of poor driving safety of autonomous flight in the driving control method of a flying vehicle in the related art; in addition, determining the priority of an obstacle according to the specified features of the obstacle and setting an avoidance distance for the obstacle according to the priority of the obstacle can not only ensure the reliability of obstacle avoidance but also improve the flexibility of obstacle avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a schematic diagram of an application scenario of a driving control method for a flying vehicle according to an embodiment of the present application;

[0012] Figure 2 is a schematic flowchart of an optional driving control method for a flying vehicle according to an embodiment of the present application;

[0013] Figure 3 is a schematic flowchart of another optional driving control method for a flying vehicle according to an embodiment of the present application;

[0014] Figure 4 is a structural block diagram of an optional driving control device for a flying vehicle according to an embodiment of the present application;

[0015] Figure 5 is a block diagram of a computer system structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0018] According to one aspect of the embodiments of this application, a driving control method for a flying car is provided. Optionally, in this embodiment, the above-mentioned driving control method for a flying car can be but is not limited to being applied to a hardware environment such as Figure 1 shown in Figure 102 including a terminal device 102 and a server 104. The server 104 can be connected to the terminal device 102 through a network and can be used to provide services (such as application services, etc.) for the terminal device 102 or the client installed on the terminal device 102. A database can be set on the server 104 or independently of the server 104 to provide data storage services for the server 104.

[0019] The above-mentioned network can include but is not limited to at least one of the following: a wired network, a wireless network. The above-mentioned wired network can include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network. The above-mentioned wireless network can include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 can be an in-vehicle terminal matching the flying car or a terminal device integrated into the flying car, etc. The server 104 can be but is not limited to a cloud server, a server cluster or other server types.

[0020] The driving control method of the flying car according to the embodiment of the present application can be executed by the server 104, or can be executed by the terminal device 102, or can also be jointly executed by the server 104 and the terminal device 102. Among them, the execution of the driving control method of the flying car according to the embodiment of the present application by the terminal device 102 can also be executed by the client installed thereon.

[0021] Taking the execution of the driving control method of the flying car in this embodiment by the terminal device 102 as an example, Figure 2 It is a schematic flowchart of an optional driving control method of a flying car according to an embodiment of the present application, as Figure 2 shown, the process of this method can include the following steps:

[0022] Step S202, during the autonomous flight of the flying car according to the set driving path, when a target obstacle blocking the driving path is sensed by the sensing device on the flying car, determine the priority of the target obstacle according to a set of specified features of the target obstacle;

[0023] Step S204, configure an avoidance distance for the target obstacle according to the priority of the target obstacle, where the avoidance distance of the target obstacle is the closest distance allowed between the flying car and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle;

[0024] Step S206, perform three-dimensional planning of the local path for the flying car based on the avoidance distance of the target obstacle, and when a detour path that meets the distance condition is planned, control the flying car to drive according to the detour path, where the distance condition is that the minimum distance between the flying car and the target obstacle when driving along the planned path is greater than or equal to the avoidance distance of the target obstacle.

[0025] The driving control method of the flying car in this embodiment can be applied to the technical field of flying cars and applied to the scenario of controlling the autonomous flight of flying cars. A flying car refers to a new type of transportation vehicle that can fly in the air or drive on the ground, realizing a convenient travel mode that can be used both on land and in the air. However, during the actual operation of a flying car, whether it is flying at low altitude or driving on the ground, it will inevitably encounter various static obstacles. Static obstacles include, but are not limited to: buildings, utility poles, billboards, trees, etc. These static obstacles are not only numerous but also densely distributed, and their shapes, sizes, and heights are also different.

[0026] Once a flying car collides with a static obstacle, its structure may suffer severe damage, resulting in the flying car losing its normal driving or flying ability. In addition, the collision accident may also endanger the lives of passengers and pose risks or cause damage to surrounding pedestrians, vehicles, and public facilities. Therefore, during the driving process of a flying car, it is necessary to always remain highly vigilant to avoid collisions with static obstacles.

[0027] To at least partially solve the above technical problems, in this embodiment, in combination with sensing devices, feature recognition of surrounding static obstacles (including size, distance, attributes, etc.) is performed. By analyzing these features, the priority of static obstacles is evaluated, and dynamic path planning is carried out based on the priority of static obstacles to control the driving of the flying car, ensuring a safe distance is maintained between the flying car and the obstacles, thereby achieving static obstacle avoidance.

[0028] During the autonomous flight of the flying car along the set driving path, the flying car can continuously scan the surrounding environment through its equipped sensing devices. Here, the sensing devices refer to the hardware devices on the flying car for environmental perception. For example, lidar (used to measure the distance and shape of target obstacles), cameras (used for image recognition), ultrasonic sensors (used to assist in detecting target obstacles at close range), etc.

[0029] When the sensing devices on the flying car sense a target obstacle blocking the driving path, the target obstacle can be detected, and the target obstacle information is sent to the obstacle avoidance system. Here, the target obstacle refers to a static obstacle that appears in the driving path of the flying car. After receiving the target obstacle information, the obstacle avoidance system analyzes the target obstacle information based on a preset set of specified feature parameters, calculates a set of specified features of the target obstacle, and based on the set of specified features, the parameter value of the avoidance reference parameter representing the urgency of avoiding the obstacle can be determined. The higher the parameter value of the avoidance reference parameter, the higher the priority. Therefore, based on a set of specified features of the target obstacle, the priority of the target obstacle can be determined.

[0030] Based on the priority of the target obstacle, an avoidance distance is configured for the target obstacle. The avoidance distance of the target obstacle is the closest distance allowed between the flying car and the target obstacle. The setting of the avoidance distance can ensure that the flying car will not come into contact with the obstacle under any circumstances. Here, the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle, and a higher-priority target obstacle is configured with a farther avoidance distance.

[0031] For example, the obstacle avoidance system analyzes the characteristics of obstacle A and obstacle B sensed by the sensing device, and the parameter values of the avoidance reference parameters calculated are as follows: for obstacle A, 90; for obstacle B, 75. Since the parameter value of the avoidance reference parameter of obstacle A is higher than that of obstacle B, the priority of obstacle A is higher than that of obstacle B. Correspondingly, the avoidance distance configured for obstacle A is farther than that configured for obstacle B. The configured avoidance distances are: for obstacle A, 10 meters; for obstacle B, 6 meters.

[0032] After determining the avoidance distance of the target obstacle, the flying car can perform path planning to avoid the target obstacle. Path planning refers to performing three-dimensional local path planning for the flying car based on the avoidance distance of the target obstacle, which not only requires planning in the horizontal direction but also in the vertical direction to find a detour path that meets the safety distance condition.

[0033] The obstacle avoidance system evaluates the detour path to check whether it meets the safety distance condition. If the detour path meets the distance condition, it controls the flying car to drive along the detour path. Here, the distance condition is that the minimum distance between the flying car and the target obstacle when driving along the planned path is greater than or equal to the avoidance distance of the target obstacle.

[0034] Through the embodiments provided in this application, during the process of the flying car autonomously flying along the set driving path, when a target obstacle blocking the driving path is sensed by the sensing device on the flying car, according to a set of specified characteristics of the target obstacle, the priority of the target obstacle is determined; according to the priority of the target obstacle, an avoidance distance is configured for the target obstacle, where the avoidance distance of the target obstacle is the closest distance allowed between the flying car and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle; based on the avoidance distance of the target obstacle, three-dimensional local path planning is performed for the flying car, and when a detour path that meets the distance condition is planned, the flying car is controlled to drive along the detour path, where the distance condition is that the minimum distance between the flying car and the target obstacle when driving along the planned path is greater than or equal to the avoidance distance of the target obstacle, which solves the technical problem of poor driving safety during autonomous flight in the driving control method of the flying car in the related art and improves the driving safety during autonomous flight.

[0035] In an exemplary embodiment, a set of specified characteristics can be configured as needed, which can include one or more characteristics that affect the driving safety of the flying car, and can include but are not limited to at least one of the following: obstacle size, the distance between the obstacle and the flying car, obstacle type, and can also include other types of parameters.

[0036] Optionally, in this embodiment, a set of specified features of the target obstacle may include: the size of the target obstacle, the distance between the target obstacle and the flying vehicle, and the type of the target obstacle. Through the multi-dimensional feature evaluation of the target obstacle, potential threats in the environment around the flying vehicle can be identified and responded to more accurately. Correspondingly, according to a set of specified features of the target obstacle, the priority of the target obstacle is determined, including: determining the priority of the target obstacle according to the size of the target obstacle, the distance between the target obstacle and the flying vehicle, and the type of the target obstacle.

[0037] Through this embodiment, by determining the priority of the obstacle according to the size of the obstacle, the distance between the obstacle and the flying vehicle, and the type of the obstacle, the priority of the obstacle can be determined through multiple dimensions, improving the reliability of the priority determination, and thus improving the rationality of the avoidance distance configuration.

[0038] In an exemplary embodiment, there can be multiple ways to determine the priority of the target obstacle according to a set of specified features of the target obstacle, including but not limited to one of the following: using a pre-trained neural network model for priority identification; scoring based on each specified feature and fusing the scores of each specified feature to evaluate the priority of the target obstacle, and other priority determination methods can also be adopted.

[0039] As an optional implementation manner, determining the priority of the target obstacle according to a set of specified features of the target obstacle includes: inputting a set of specified features of the target obstacle into a pre-trained target classification model to obtain the priority of the target obstacle output by the target classification model.

[0040] In this embodiment, a trained target classification model can be used to judge the priority of static obstacles. Among them, the target classification model is used to predict the probability that the input set of specified features belongs to each priority corresponding to a set of priorities for the input set of specified features of the obstacle, and output the priority with the highest corresponding probability in the set of priorities. The target classification model can be a machine learning model or other classification models that can classify by priority.

[0041] After the flying vehicle obtains a set of specified features of the target obstacle through the sensing device, it inputs the set of specified features of the target obstacle into the pre-trained target classification model. The target classification model can predict the probability that the target obstacle belongs to each priority in a set of priorities according to the input set of specified features, and output the priority with the highest probability as the final priority. The set of priorities is the classification categories of the set target classification model.

[0042] For example, a set of specified features of the target obstacle are as follows: the size of the obstacle, 5 meters in length, 4 meters in width, and 15 meters in height; the distance from the flying car, 100 meters; the type of the obstacle, building. A set of priorities includes: high priority, medium priority, and low priority. After inputting the set of specified features of the target obstacle into the target classification model, the probabilities that the target obstacle predicted by the target classification model belongs to each priority are respectively: high priority, 65%; medium priority, 30%; low priority, 5%. Therefore, the priority with the highest probability output by the target classification model is: high.

[0043] As another alternative implementation, to determine the priority of the target obstacle according to a set of specified features of the target obstacle, it includes: respectively assigning scores to the target obstacle according to each specified feature in the set of specified features of the target obstacle to obtain the scores of each specified feature; performing weighted summation on the scores of each specified feature to obtain the target score; determining the priority corresponding to the score interval where the target score is located in a set of set score intervals as the priority of the target obstacle.

[0044] In this embodiment, the priority of the obstacle can also be determined by means of feature evaluation and weighted summation. First, according to each specified feature of the target obstacle, scores are respectively assigned to it, and then by performing weighted summation on the scores of each specified feature, the target score of the target obstacle is obtained. For different types of specified features, the ways of assigning scores to them can be different. For example, for the size of the obstacle, a linear or non-linear correspondence can be used to assign scores to it, and for the type of the obstacle, an enumeration method can be used to assign scores to it. Weighted summation means multiplying the score of each specified feature by the weight coefficient corresponding to each specified feature and then summing them to obtain the total score of the target obstacle, that is, the target score.

[0045] Then, determine the score interval where the target score is located in a set of score intervals, and determine the priority corresponding to the score interval where the target score is located as the priority of the target obstacle. Here, a set of score intervals is a plurality of pre-set score intervals, and the score intervals in the set of score intervals correspond one by one to the priorities in the set of priorities. The score intervals and the priorities can be in a positive correlation relationship, that is, the larger the score interval, the higher the priority.

[0046] For example, for the obstacles detected by the flying car, the scores of each specified feature are determined respectively as follows: the size of the obstacle, 10 points; the distance between the obstacle and the flying car, 7 points; the type of the obstacle, 9 points. The weights corresponding to the size of the obstacle, the distance between the obstacle and the flying car, and the type of the obstacle are 0.5, 0.3, and 0.2 respectively. Through weighted summation calculation, the score of the obstacle can be obtained as 8.9. The corresponding relationship between the preset score range and the priority is: [0 - 5], low priority; [5 - 10], medium priority; [10 - 15], high priority. Since 8.9 ∈ [5 - 10], the priority of the obstacle is medium priority.

[0047] Through this embodiment, the priority of the target obstacle is obtained through a classification model or through a comprehensive evaluation (weighted summation) of multiple features of the target obstacle, improving the accuracy of the priority judgment of the target obstacle.

[0048] In an exemplary embodiment, according to the priority of the target obstacle, an avoidance distance is configured for the target obstacle, including: looking up a preset corresponding relationship table based on the priority of the target obstacle; configuring the avoidance distance corresponding to the priority of the target obstacle found as the avoidance distance of the target obstacle.

[0049] In order to automatically determine an appropriate avoidance distance according to the priority of the obstacle when the flying car encounters an obstacle, a corresponding relationship table can be preset. Here, the corresponding relationship table records the corresponding relationship between the priority and the avoidance distance, which can provide accurate guidance on the obstacle avoidance distance for the flying car.

[0050] Optionally, after the obstacle avoidance system determines the priority of the target obstacle, it can look up the avoidance distance corresponding to the priority of the target obstacle in the preset corresponding relationship table. At the same time, the obstacle avoidance system configures the avoidance distance corresponding to the priority of the target obstacle for the target obstacle as the minimum safe distance that the flying car needs to maintain when bypassing the target obstacle.

[0051] For example, in the preset corresponding relationship table, the avoidance distance corresponding to the high priority is 200 meters, the avoidance distance corresponding to the medium priority is 100 meters, and the avoidance distance corresponding to the low priority is 50 meters. When the obstacle avoidance system evaluates that the priority of the target obstacle is high priority, the avoidance distance configured for the target obstacle is 200 meters. Similarly, when the obstacle avoidance system evaluates that the priority of the target obstacle is medium priority, the avoidance distance configured for the target obstacle is 100 meters. When the obstacle avoidance system evaluates that the priority of the target obstacle is low priority, the avoidance distance configured for the target obstacle is 50 meters.

[0052] Through this embodiment, the corresponding avoidance distance is configured for the perceived obstacle based on the correspondence table, so that the flying car can configure an appropriate avoidance distance according to the influence degree of different obstacles, so as to realize the dynamic adjustment of the avoidance distance.

[0053] In an exemplary embodiment, a three-dimensional local path planning is performed for the flying car based on the avoidance distance of the target obstacle, including: using at least one path planning algorithm to search for a local path for the flying car to search for a three-dimensional path that meets the distance condition; in the case of finding a candidate path that meets the distance condition, based on the kinematic parameters and dynamic parameters of the flying car, optimize the candidate path to obtain a detour path.

[0054] When the flying car performs static obstacle avoidance, local search is performed through a path planning algorithm to search for a three-dimensional detour path that meets the safety distance condition. Here, the path planning algorithm includes but is not limited to: A*, D*, RRT, heuristic algorithm or a combination of the above methods, etc. Optionally, the flying car uses at least one path planning algorithm according to the position and priority of the target obstacle to perform three-dimensional path search in the local area of the current flight path to find a candidate path to bypass the target obstacle. The obstacle avoidance system evaluates the candidate path to further determine whether the minimum distance between the flying car on the candidate path and the obstacle meets the preset avoidance distance condition.

[0055] For the candidate path that meets the distance condition, the obstacle avoidance system optimizes the candidate path based on the kinematic parameters and dynamic parameters of the flying car to obtain a detour path to ensure that the flying car can fly safely and stably along this path. Here, the kinematic parameters are the parameters that describe the motion state of the flying car, such as speed, acceleration, steering angular velocity, etc.; the dynamic parameters are the parameters that describe the force state and flight ability of the flying car, such as maximum thrust, maximum lift, weight, air resistance coefficient, etc. Optimizing the candidate path through these parameters can avoid flight accidents caused by these parameters exceeding the physical limits of the flying car.

[0056] Through this embodiment, searching for a candidate path that meets the distance condition within a local range and optimizing the candidate path based on the kinematic parameters and dynamic parameters of the flying car can ensure the safety of the flying car during flight.

[0057] In an exemplary embodiment, based on the kinematic parameters of the flying car and the dynamic parameters of the flying car, trajectory optimization is performed on a candidate path to obtain a detour path, including at least one of the following: performing at least one trajectory optimization on the candidate path by using a quintic polynomial trajectory planning method until the optimized candidate path satisfies the kinematic parameters of the flying car and the dynamic parameters of the flying car, to obtain a detour path; performing at least one trajectory optimization on the candidate path by using a spline curve planning method until the optimized candidate path satisfies the kinematic parameters of the flying car and the dynamic parameters of the flying car, to obtain a detour path.

[0058] In this embodiment, a quintic polynomial trajectory planning method can be used to perform at least one trajectory optimization on the candidate path. The quintic polynomial trajectory planning method describes the motion trajectory of the flying car from the current position to the target point by defining a quintic polynomial function, so as to achieve smooth control of motion parameters such as speed and acceleration. Usually, the quintic polynomial trajectory planning starts from defining boundary conditions (such as the speed and acceleration at the starting position), and through the boundary conditions and the differentiation of the polynomial, a system of equations about the undetermined coefficients is established, and the specific coefficients of the polynomial are solved. After obtaining the coefficients, the quintic polynomial function can be used to optimize the candidate trajectory. After optimizing the candidate trajectory through the quintic polynomial function, it is also necessary to check whether the generated trajectory satisfies the kinematic parameters of the flying car and the dynamic parameters of the flying car. If not, the boundary conditions need to be adjusted and the trajectory optimization is performed again until the optimized candidate path satisfies the kinematic parameters of the flying car and the dynamic parameters of the flying car, to obtain a detour path.

[0059] In this embodiment, a spline curve planning method can also be used to perform at least one trajectory optimization on the candidate path. The spline curve generates a continuous and smooth flight trajectory by fitting multiple line segments. Optionally, first determine the key points that the flying car needs to pass through, and these points form the control point set of the spline curve. Here, the control point set can be the starting point, the ending point, and the intermediate points set according to the target obstacle. After determining the key points, select a suitable spline curve (such as a cubic spline, a B-spline, etc.), and parameterize the spline curve, that is, use a parameter to represent any point on the curve (usually associated with time, such as (t)). Then, according to the selected spline type and control points, the coefficients of the spline function are solved by mathematical methods, and the position, speed, and acceleration of the flying car at any parameter are calculated according to the coefficients of the spline function, so as to generate a complete detour trajectory. During the optimization process, the spline curve planning also needs to consider the constraints of the kinematic parameters of the flying car and the dynamic parameters of the flying car. The spline curve can be fine-tuned by adjusting the position of the control points and the time interval to ensure that the optimized detour trajectory satisfies the constraints of the kinematic parameters and the dynamic parameters of the flying car.

[0060] In an actual obstacle avoidance scenario, the detour trajectory needs to be adjusted according to the real-time environment. For example, when a new obstacle is detected, the quintic polynomial trajectory planning method or the spline curve planning method is re-adopted to adjust or optimize the detour trajectory, and a real-time detour path is generated.

[0061] Through this embodiment, the detour trajectory is optimized at least once by using the quintic polynomial trajectory planning method or the spline curve planning method to generate a detour path, ensuring the smoothness and safety of the flying car during obstacle avoidance.

[0062] In an exemplary embodiment, after performing three-dimensional planning of the local path for the flying car based on the avoidance distance of the target obstacle, the above method further includes: in the case where a local path that meets the distance condition is not planned, controlling the flying car to perform at least one of the following processing operations: controlling the flying car to hover and wait; controlling the prompting component to issue a collision warning message; sending a manual takeover request to the target object; and switching the driving mode of the flying car from the autonomous flight mode to the manual control mode when receiving a manual takeover instruction.

[0063] For the case where the planned detour path does not meet the distance condition, the obstacle avoidance system needs to take a series of emergency measures to prevent the flying car from hitting the target obstacle during flight and ensure flight safety.

[0064] As an alternative implementation, the obstacle avoidance system can take the emergency measure of hovering and waiting. Hovering and waiting means that the flying car stops moving in the air and waits for a re-planned path, a manual instruction, or other instructions. The flying car needs to select a safe position for hovering and waiting to avoid colliding with the target obstacle or affecting the normal operation of other flying cars to ensure the safety of the hovering position. Optionally, the hovering position of the flying car is a position on the driving path or a position where the minimum distance from the driving path is greater than or equal to a preset distance threshold, and the distance between the hovering position of the flying car and the target obstacle is greater than or equal to the avoidance distance of the target obstacle.

[0065] As another alternative implementation, the obstacle avoidance system can take the emergency measure of issuing a collision warning. If the flying car cannot hover immediately or the hovering position does not meet the requirements of a safe position, the flying car can issue a collision warning message through a sound alarm, a visual warning light, or other prompting components to remind the driver or other surrounding flying cars of the danger. The flying car can also send a collision warning to the background. The flying car can issue a collision warning when it cannot hover immediately or the hovering position does not meet the requirements of a safe position, or when it is hovering and waiting.

[0066] As another alternative embodiment, the obstacle avoidance system can also take emergency handling measures of manual takeover. Manual takeover means that the obstacle avoidance system sends a request to the driver of the flying car or the remote control center, asking for manual intervention. The driver or the staff in the remote control center can manually control the flight attitude and direction of the flying car to avoid the target obstacle.

[0067] For the three emergency handling measures of hovering and waiting, issuing a collision warning, and manual takeover, either a single measure can be selected, or a combination of multiple measures can be chosen, which is not limited in this embodiment.

[0068] Through this embodiment, the flying car can effectively avoid potential collision risks by means of hovering and waiting, collision warning, and manual takeover.

[0069] The following explains the driving control method of the flying car in the embodiment of the present application with reference to optional examples. In this optional example, during the driving process of the flying car, when a static obstacle appears on the predetermined planned route, the drivable range of the vehicle is judged and a decision is made to take an operation of bypassing the obstacle in space, so as to realize the function of static obstacle avoidance.

[0070] Figure 3 It is a schematic flowchart of another alternative driving control method of the flying car according to the embodiment of the present application. As Figure 3 shown, during the autonomous flight of the flying car, if it detects a static obstacle (an example of the target obstacle) in front and blocking the driving route, the priority of the obstacle is judged; a corresponding anti-collision safety distance threshold (an example of the avoidance distance) is set according to the priority of the obstacle. The higher the priority, the larger the safety distance threshold; a three-dimensional local path planning is carried out according to the safety distance corresponding to the static obstacle. After trajectory search, the trajectory is optimized according to the kinematics and dynamics of the flying car to make it conform to the actual physical reality conditions; it is judged whether the optimized trajectory meets the safety conditions (the minimum distance from the static obstacle is greater than the safety distance threshold). If it meets, this bypass trajectory is adopted and output to the control module for execution; if it does not meet or a bypass trajectory cannot be generated, one or a combination of the following methods is adopted: hovering and waiting, collision warning, manual takeover.

[0071] Through this optional example, during the autonomous flight of the flying car, when a static obstacle appears on the predetermined planned route, an adaptive decision is made, the drivable range of the vehicle is judged and a decision is made, and an operation of bypassing the obstacle in space or hovering / warning / manual takeover is taken, which can improve the driving safety of the flying car and expand the applicable range of the autonomous flight of the flying car.

[0072] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0073] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, optical disk), and includes several instructions to enable a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of this application.

[0074] According to another aspect of the embodiments of this application, a driving control device for a flying car is further provided. The driving control device for the flying car can be used to implement the driving control method for the flying car provided in the above embodiments, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation by hardware, or a combination of software and hardware, is also possible and contemplated.

[0075] Figure 4 is a structural block diagram of an optional driving control device for a flying car according to an embodiment of this application. As Figure 4 shown in, the driving control device for the flying car includes:

[0076] A determination unit 402, configured to, during the process of the flying car autonomously flying according to a set driving path, when a target obstacle blocking the driving path is sensed by a sensing device on the flying car, determine the priority of the target obstacle according to a set of specified features of the target obstacle.

[0077] Configuration unit 404 is configured to configure an avoidance distance for a target obstacle according to the priority of the target obstacle, where the avoidance distance of the target obstacle is the closest distance allowed between the flying vehicle and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle.

[0078] Execution unit 406 is configured to perform three-dimensional planning of a local path for the flying vehicle based on the avoidance distance of the target obstacle, and when a detour path that meets the distance condition is planned, control the flying vehicle to travel along the detour path, where the distance condition is that the minimum distance between the flying vehicle and the target obstacle when the flying vehicle travels along the planned path is greater than or equal to the avoidance distance of the target obstacle.

[0079] It should be noted that the determination unit 402 in this embodiment can be used to execute the above-mentioned step S202, the configuration unit 404 in this embodiment can be used to execute the above-mentioned step S204, and the execution unit 406 in this embodiment can be used to execute the above-mentioned step S206.

[0080] Through the embodiment provided by the present application, during the process of the flying vehicle performing autonomous flight according to the set driving path, when a target obstacle blocking the driving path is sensed by the sensing device on the flying vehicle, the priority of the target obstacle is determined according to a set of specified features of the target obstacle; according to the priority of the target obstacle, an avoidance distance is configured for the target obstacle, where the avoidance distance of the target obstacle is the closest distance allowed between the flying vehicle and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle; three-dimensional planning of a local path is performed for the flying vehicle based on the avoidance distance of the target obstacle, and when a detour path that meets the distance condition is planned, control the flying vehicle to travel along the detour path, where the distance condition is that the minimum distance between the flying vehicle and the target obstacle when the flying vehicle travels along the planned path is greater than or equal to the avoidance distance of the target obstacle, which solves the technical problem that the driving control method of the flying vehicle in the related art has poor driving safety during autonomous flight, and improves the driving safety during autonomous flight.

[0081] In an exemplary embodiment, the determination unit includes: a first determination module configured to determine the priority of the target obstacle according to the size of the target obstacle, the distance between the target obstacle and the flying vehicle, and the type of the target obstacle.

[0082] In an exemplary embodiment, the determination unit includes: an input module configured to input a set of specified features of a target obstacle into a pre-trained target classification model to obtain the priority of the target obstacle output by the target classification model, where the target classification model is configured to predict, based on the input set of specified features, the probability corresponding to each priority in a set of priorities for the obstacle to which the input set of specified features belongs, and output the priority with the highest corresponding probability in the set of priorities.

[0083] In an exemplary embodiment, the determination unit includes: an assignment module configured to assign scores to the target obstacle respectively according to each specified feature in a set of specified features of the target obstacle to obtain the score of each specified feature; a calculation module configured to perform a weighted sum of the scores of each specified feature to obtain a target score; and a second determination module configured to determine, as the priority of the target obstacle, the priority corresponding to the score interval in a set of set score intervals where the target score is located, where one score interval in the set of score intervals corresponds to one priority.

[0084] In an exemplary embodiment, the configuration unit includes: a lookup module configured to look up a preset correspondence table based on the priority of the target obstacle, where the correspondence table is configured to record the correspondence between the priority and the avoidance distance; and a configuration module configured to configure the avoidance distance corresponding to the priority of the target obstacle found as the avoidance distance of the target obstacle.

[0085] In an exemplary embodiment, the execution unit includes: a search module configured to perform a local path search for the flying vehicle using at least one path planning algorithm to search for a three-dimensional path that meets the distance condition; and an optimization module configured to, in the case where a candidate path that meets the distance condition is searched, perform trajectory optimization on the candidate path based on the kinematic parameters and dynamic parameters of the flying vehicle to obtain a detour path.

[0086] In an exemplary embodiment, the optimization module includes at least one of the following: a first optimization sub-module configured to perform at least one trajectory optimization on the candidate path in a quintic polynomial trajectory planning manner until the optimized candidate path meets the kinematic parameters and dynamic parameters of the flying vehicle to obtain a detour path; and a second optimization sub-module configured to perform at least one trajectory optimization on the candidate path in a spline curve planning manner until the optimized candidate path meets the kinematic parameters and dynamic parameters of the flying vehicle to obtain a detour path.

[0087] In an exemplary embodiment, the above-mentioned device further includes: a control unit. After performing three-dimensional planning of a local path for the flying vehicle based on the avoidance distance of the target obstacle, when no local path that meets the distance condition is planned, the control unit controls the flying vehicle to perform at least one of the following processing operations: controlling the flying vehicle to hover and wait, where the position where the flying vehicle hovers is a position on the driving path or a position where the minimum distance from the driving path is greater than or equal to a preset distance threshold, and the distance between the position where the flying vehicle hovers and the target obstacle is greater than or equal to the avoidance distance of the target obstacle; controlling the prompt component to send out a collision warning message; sending a manual takeover request to the target object; and when receiving a manual takeover instruction, switching the driving mode of the flying vehicle from the autonomous flight mode to the manual control mode.

[0088] It should be noted that the above-mentioned various modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited thereto: all the above-mentioned modules are located in the same processor; or, the above-mentioned various modules are respectively located in different processors in any combination form.

[0089] According to another aspect of the embodiments of the present application, there is provided a computer-readable storage medium, which includes a stored program, and when the program runs, it executes the steps in any one of the above-mentioned method embodiments.

[0090] In an exemplary embodiment, the above-mentioned computer-readable storage medium may include, but is not limited to: various media such as USB flash drives, ROM, RAM, mobile hard disks, magnetic disks, or optical discs that can store computer programs.

[0091] According to another aspect of the embodiments of the present application, there is provided an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor is configured to execute the steps in any one of the above-mentioned method embodiments through the computer program. In an exemplary embodiment, the above-mentioned electronic device may further include a transmission device and an input / output device, where the transmission device is connected to the above-mentioned processor, and the input / output device is connected to the above-mentioned processor.

[0092] The specific examples in this embodiment may refer to the examples described in the above-mentioned embodiments and exemplary embodiments, and will not be repeated here.

[0093] According to another aspect of the embodiments of the present application, a computer program product is further provided. The computer program product includes computer programs / instructions, and the computer programs / instructions contain program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, various functions provided by the embodiments of the present application are executed. The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0094] Figure 5 is a block diagram of the computer system structure of an optional electronic device according to the embodiments of the present application. As Figure 5 shown, the computer system 500 includes a CPU (Central Processing Unit) 501, which can execute various appropriate actions and processes according to the programs stored in the ROM 502 or the programs loaded from the storage part 508 into the RAM 503. In the random access memory 503, various programs and data required for system operation are also stored. The central processing unit 501, the read-only memory 502, and the random access memory 503 are connected to each other through a bus 504. The I / O (Input / Output) interface 505 is also connected to the bus 504.

[0095] The following components are connected to the I / O interface 505: an input part 506 including a keyboard, a mouse, etc.; an output part 507 including, for example, a CRT (Cathode Ray Tube), an LCD (Liquid Crystal Display), etc. and a speaker, etc.; a storage part 508 including a hard disk, etc.; and a communication part 509 including a network interface card such as a local area network card, a modem, etc. The communication part 509 performs communication processing via a network such as the Internet. The drive 510 is also connected to the input / output interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that the computer program read from it can be installed into the storage part 508 as needed.

[0096] In particular, according to an embodiment of the present application, the processes described in each method flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit 501, various functions defined in the system of the present application are executed.

[0097] It should be noted that Figure 5 The computer system 500 of the electronic device shown is only an example, and should not bring any limitation to the functions and usage scope of the embodiments of the present application.

[0098] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be implemented by a general-purpose computing device. They can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a sequence different from that here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to be implemented. In this way, the present application is not limited to any specific combination of hardware and software.

[0099] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the principle of the present application shall be included within the protection scope of the present application.

Claims

1. A flying car driving control method, characterized in that: include: During the autonomous flight of the flying car according to the set driving path, when a target obstacle blocking the driving path is sensed by a sensing device on the flying car, determining the priority of the target obstacle according to a set of specified features of the target obstacle; According to the priority of the target obstacle, configuring an avoidance distance for the target obstacle, wherein the avoidance distance of the target obstacle is the shortest distance allowed between the flying car and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle; A three-dimensional planning of a local path is performed for the flying car based on the avoidance distance of the target obstacle, and when a detour path satisfying a distance condition is planned, the flying car is controlled to travel along the detour path, wherein the distance condition is that a minimum distance between the flying car and the target obstacle when the flying car travels along the planned path is greater than or equal to the avoidance distance of the target obstacle.

2. The method according to claim 1, characterized in that The step of determining the priority of the target obstacle according to a set of specified features of the target obstacle comprises: The priority of the target obstacle is determined according to the size of the target obstacle, the distance between the target obstacle and the flying car, and the type of the target obstacle.

3. The method according to claim 1, characterized in that The step of determining the priority of the target obstacle according to a set of specified features of the target obstacle comprises: Inputting the set of specified features of the target obstacle into a pre-trained target classification model to obtain the priority of the target obstacle output by the target classification model, wherein the target classification model is used to predict the probability of the obstacle to which the set of specified features inputted belongs corresponding to each priority in a set of priorities based on the set of specified features inputted, and output the priority with the largest probability corresponding to the set of priorities; or According to each designated feature in the set of designated features of the target obstacle, a score is assigned to the target obstacle to obtain the score of each designated feature; the score of each designated feature is weightedly summed to obtain a target score; and the priority corresponding to the score interval where the target score is located in a set set of score intervals is determined as the priority of the target obstacle, wherein one score interval in the set of score intervals corresponds to one priority.

4. The method according to claim 1, characterized in that: The configuring an avoidance distance for the target obstacle according to the priority of the target obstacle includes: Searching a preset correspondence table based on the priority of the target obstacle, wherein the correspondence table is used to record the correspondence between the priority and the avoidance distance; The found avoidance distance corresponding to the priority of the target obstacle is configured as the avoidance distance of the target obstacle.

5. The method according to claim 1, characterized in that The three-dimensional planning of a local path for the flying car based on the avoidance distance of the target obstacle includes: Using at least one path planning algorithm to perform a local path search for the flying car to search for a three-dimensional path that satisfies the distance condition; When a candidate path that meets the distance condition is searched, trajectory optimization is performed on the candidate path based on the kinematic parameters of the flying car and the dynamic parameters of the flying car to obtain the detour path.

6. The method according to claim 5, characterized in that The step of performing trajectory optimization on the candidate path based on the kinematic parameters of the flying car and the dynamic parameters of the flying car to obtain the detour path includes at least one of the following: Performing trajectory optimization on the candidate path at least once by using a quintic polynomial trajectory planning method until the optimized candidate path satisfies the kinematic parameters of the flying car and the dynamic parameters of the flying car, thereby obtaining the detour path; The candidate path is optimized at least once by using a spline curve planning method until the optimized candidate path satisfies the kinematic parameters of the flying car and the dynamic parameters of the flying car, thereby obtaining the detour path.

7. The method according to any one of claims 1 to 6, characterized in that After performing three-dimensional planning of a local path for the flying car based on the avoidance distance of the target obstacle, the method further includes: In the case that a local path satisfying the distance condition is not planned, the flying car is controlled to perform at least one of the following processing operations: Controlling the flying car to hover and wait, wherein the hovering position of the flying car is a position on the driving path or a position whose minimum distance from the driving path is greater than or equal to a preset distance threshold, and the distance between the hovering position of the flying car and the target obstacle is greater than or equal to the avoidance distance of the target obstacle; The control prompt component issues a collision warning message; A manual takeover request is issued to the target object; and upon receiving the manual takeover instruction, the driving mode of the flying car is switched from the autonomous flight mode to the manual control mode.

8. A flying car driving control device, characterized in that: include: a determination unit, configured to determine the priority of a target obstacle according to a set of specified features of the target obstacle when a target obstacle blocking the driving path is sensed by a sensing device on the flying car during the autonomous flight of the flying car according to a set driving path; a configuration unit, configured to configure an avoidance distance for the target obstacle according to the priority of the target obstacle, wherein the avoidance distance of the target obstacle is the shortest distance allowed between the flying car and the target obstacle, and the avoidance distance of the target obstacle is positively correlated with the priority of the target obstacle; A control unit is used to perform three-dimensional planning of a local path for the flying car based on the avoidance distance of the target obstacle, and control the flying car to travel along the bypass path when a bypass path that meets a distance condition is planned, wherein the distance condition is that the minimum distance between the flying car and the target obstacle when traveling along the planned path is greater than or equal to the avoidance distance of the target obstacle.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of any one of the methods of claims 1 to 7 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images