Intelligent vehicle automatic driving formation obstacle avoidance control method and device

Abstract

The invention relates to the technical field of intelligent vehicles, in particular to an intelligent vehicle automatic driving formation obstacle avoidance control method and device, and the method comprises the steps: constructing an intelligent vehicle formation controller according to the destination data and obstacle data of a target intelligent vehicle formation, so as to control the target intelligent vehicle formation to move towards the destination; establishing an intelligent vehicle formation space-time transformation strategy based on the queue expansion coefficient according to the queue expansion coefficient of the target intelligent vehicle formation and the driving safety boundary; performing dynamic optimization on the intelligent vehicle formation controller by adopting a Levy flight random search logic based on a cuckoo algorithm to obtain an optimized intelligent vehicle formation controller; and controlling the target intelligent vehicle formation to avoid obstacles by using the optimized intelligent vehicle formation controller and the intelligent vehicle formation space-time transformation strategy based on the queue expansion coefficient. Therefore, the problems that when intelligent vehicle formation obstacle avoidance is carried out through a traditional artificial potential field method, local minimum value and obstacle avoidance track jittering are likely to happen, and complex dynamic environments cannot be rapidly adapted are solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle technology, and in particular to a method and device for intelligent vehicle autonomous driving formation obstacle avoidance control. Background Technology

[0002] As a typical implementation mode of intelligent connected systems, intelligent vehicle platooning has wide application value in military and civilian fields due to its compact system organization and good environmental adaptability. Intelligent vehicle platooning control is one of the core technologies of vehicle platooning, which can improve the energy efficiency and fuel economy of vehicle platooning driving modes and reduce environmental pollution. In vehicle platooning control, obstacle avoidance control technology plays a crucial role in driving safety, traffic efficiency, and adaptability to complex environments. Among various vehicle platooning obstacle avoidance control strategies, the artificial potential field method has the advantages of low computational cost, good real-time performance, and simple structure, and is widely used in intelligent vehicle platooning control.

[0003] Artificial potential field methods, based on local optimum calculation logic, can smooth vehicle trajectories during obstacle avoidance. However, when the target point is within the influence range of an obstacle, the repulsive force on a single intelligent vehicle can increase to the point of detaching from the target's gravitational pull, leading to target unreachability. While this can be avoided using a velocity-variable model based on visual velocity vectors or constraint equations based on navigation functions, these methods do not consider the uncertainties in obstacle motion patterns within the driving environment, which can cause local minima or trajectory jitter in formation obstacle avoidance. To address this issue, it is necessary to overcome the limitations of the incremental coefficient setting method in solving intelligent vehicle formation calculations using artificial potential field methods. This could be achieved by combining artificial potential field methods with fuzzy control strategies or using a particle swarm optimization-based artificial potential field method to optimize the incremental coefficients of attraction and repulsion in the artificial potential field. However, these methods are primarily applied to individual autonomous intelligent vehicles and have not yet been applied to intelligent vehicle formations. Therefore, establishing a formation obstacle avoidance strategy that ensures target reachability and smooth obstacle avoidance trajectories, thereby improving its safety and adaptability in complex driving environments, requires further in-depth research. Summary of the Invention

[0004] This invention provides a method, device, and vehicle for obstacle avoidance control in multi-vehicle autonomous driving formation, to solve the problems of traditional artificial potential field methods for obstacle avoidance in intelligent vehicle formation, such as being prone to getting stuck in local minima and obstacle avoidance trajectory jitter, and being unable to quickly adapt to complex dynamic environments.

[0005] A first aspect of the present invention provides a method for intelligent vehicle autonomous driving platooning obstacle avoidance control, comprising the following steps: An intelligent vehicle formation controller is constructed based on the destination and obstacle data of the target intelligent vehicle formation to control the formation to move towards the destination. A formation-based spatiotemporal transformation strategy is established based on the formation's queue scaling factor and driving safety boundary. The intelligent vehicle formation controller is dynamically optimized using a Levy flight random search logic based on the cuckoo algorithm to obtain an optimized controller. The optimized controller and the formation-based spatiotemporal transformation strategy are then used to control the target intelligent vehicle formation to avoid obstacles.

[0006] Optionally, the step of constructing an intelligent vehicle formation controller based on destination data and obstacle data of the target intelligent vehicle formation to control the target intelligent vehicle formation to move toward the destination includes: The system acquires destination data for the target intelligent vehicle convoy and collects obstacle data that obstructs the convoy's movement in the driving environment. Based on the destination data, it determines the heading angle of each individual vehicle to construct a convoy gravitational potential field function. Based on the obstacle data, it constructs a convoy repulsive potential field function. Based on the convoy gravitational and repulsive potential field functions, it builds an intelligent vehicle convoy controller. Based on the intelligent vehicle convoy controller, it simultaneously applies gravitational and repulsive forces to the individual intelligent vehicles in the target intelligent vehicle convoy, causing the convoy to move towards its destination.

[0007] Optionally, the step of establishing a spatiotemporal transformation strategy for intelligent vehicle formation based on the queue scaling coefficient and driving safety boundary of the target intelligent vehicle formation includes: The queue width of the target intelligent vehicle formation and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment are obtained; the queue expansion coefficient of the target intelligent vehicle formation along the driving direction of the lead vehicle is calculated based on the queue expansion coefficient and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment; and the spatiotemporal transformation strategy of the intelligent vehicle formation based on the queue expansion coefficient is established based on the queue expansion coefficient and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment.

[0008] Optionally, the intelligent vehicle platooning formation spatiotemporal transformation strategy based on the queue scaling coefficient includes a formation-no-transformation strategy, a formation-isomorphic transformation strategy, and a formation-heterogeneous transformation strategy, wherein, When the queue scaling factor is greater than or equal to 1, the formation-no-change strategy is executed, allowing the vehicle to pass through the current driving environment without adjusting the formation. When the queue scaling factor is greater than a preset minimum queue scaling factor but less than 1, the formation isomorphic transformation strategy is executed to adjust the queue scaling factor, enabling the target intelligent vehicle convoy to pass through the current driving environment while maintaining the formation. When the queue scaling factor is less than or equal to the preset minimum queue scaling factor, the formation heterogeneous transformation mode is executed, allowing each intelligent vehicle in the target intelligent vehicle convoy to perform obstacle avoidance and autonomous driving. When exiting this mode, the formation is restored based on the driving status of the navigator vehicle.

[0009] A second aspect of the present invention provides an intelligent vehicle autonomous driving platooning obstacle avoidance control device, comprising: The system includes a controller construction module for constructing an intelligent vehicle formation controller based on destination and obstacle data of the target intelligent vehicle formation, thereby controlling the target intelligent vehicle formation to move towards its destination; a strategy construction module for establishing a spatiotemporal transformation strategy for the intelligent vehicle formation based on the queue scaling factor and driving safety boundaries; a dynamic optimization module for dynamically optimizing the intelligent vehicle formation controller using a Levy flight random search logic based on the cuckoo algorithm, to obtain an optimized intelligent vehicle formation controller; and an obstacle avoidance module for controlling the target intelligent vehicle formation to avoid obstacles using the optimized intelligent vehicle formation controller and the spatiotemporal transformation strategy based on the queue scaling factor.

[0010] Optionally, the controller construction module includes: The system includes: a data acquisition unit for acquiring destination data of the target intelligent vehicle formation and data on obstacles hindering the formation in the driving environment; a first potential field unit for determining the heading angle of each individual vehicle based on the destination data to construct a formation gravitational potential field function; a second potential field unit for constructing a formation repulsive potential field function based on the obstacle data; a construction unit for constructing the intelligent vehicle formation controller based on the formation gravitational potential field function and the formation repulsive potential field function; and a force application unit for simultaneously applying gravitational and repulsive forces to the individual intelligent vehicles in the target intelligent vehicle formation based on the intelligent vehicle formation controller, causing the target intelligent vehicle formation to move towards its destination.

[0011] Optionally, the strategy construction module includes: The acquisition unit is used to acquire the queue width of the target intelligent vehicle formation and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment; the calculation unit is used to calculate the queue expansion coefficient of the target intelligent vehicle formation along the driving direction of the lead vehicle based on the queue width and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment; the strategy establishment unit is used to establish the spatiotemporal transformation strategy of the intelligent vehicle formation based on the queue expansion coefficient based on the queue expansion coefficient and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment.

[0012] Optionally, the intelligent vehicle platooning formation spatiotemporal transformation strategy based on the queue scaling coefficient includes a formation-no-transformation strategy, a formation-isomorphic transformation strategy, and a formation-heterogeneous transformation strategy, wherein, When the queue scaling factor is greater than or equal to 1, the formation-no-change strategy is executed, allowing the vehicle to pass through the current driving environment without adjusting the formation. When the queue scaling factor is greater than a preset minimum queue scaling factor but less than 1, the formation isomorphic transformation strategy is executed to adjust the queue scaling factor, enabling the target intelligent vehicle convoy to pass through the current driving environment while maintaining the formation. When the queue scaling factor is less than or equal to the preset minimum queue scaling factor, the formation heterogeneous transformation mode is executed, allowing each intelligent vehicle in the target intelligent vehicle convoy to perform obstacle avoidance and autonomous driving. When exiting this mode, the formation is restored based on the driving status of the navigator vehicle.

[0013] A third aspect of the present invention provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent vehicle autonomous driving platooning obstacle avoidance control method as described in the above embodiments.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent vehicle autonomous driving platooning obstacle avoidance control method.

[0015] The intelligent vehicle autonomous driving platooning obstacle avoidance control method and device proposed in this invention designs a spatiotemporal transformation strategy for intelligent vehicle platooning formation and switches the formation transformation mode by using a queue scaling coefficient, thereby improving the adaptability of intelligent vehicle platooning to complex environments. The Levy flight mechanism from the Cuckoo Search algorithm is introduced into the traditional artificial potential field method to establish a vehicle platooning search logic based on the Levy flight mechanism. The gravity and repulsion increment coefficients are optimized to solve the problem of randomness in driving scenarios caused by the uncertainty of obstacle intent in complex driving environments, overcoming the limitations of gravity and repulsion increment coefficient settings in the traditional artificial potential field method. By optimizing the gravity and repulsion increment coefficients and cooperating with appropriate formation modes, the obstacle avoidance capability of intelligent vehicle platooning in complex driving environments is established, improving the safety and adaptability of intelligent vehicle platooning in complex driving environments and shortening the platooning obstacle avoidance time.

[0016] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0017] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart of an intelligent vehicle autonomous driving formation obstacle avoidance control method provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating an intelligent vehicle platooning formation change obstacle avoidance method according to an embodiment of the present invention. Figure 3 This is a block diagram of an intelligent vehicle autonomous driving formation obstacle avoidance control device according to an embodiment of the present invention; Figure 4 This is a structural schematic diagram of a vehicle according to an embodiment of the present invention.

[0018] Explanation of reference numerals in the attached figures: 30-Intelligent vehicle autonomous driving formation obstacle avoidance control device, 301-Controller construction module, 302-Strategy construction module, 303-Dynamic optimization module, 304-Avoidance module, 401-Memory, 402-Processor and 403-Communication interface. Detailed Implementation

[0019] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0020] The following description, with reference to the accompanying drawings, illustrates an intelligent vehicle autonomous driving formation obstacle avoidance control method and apparatus according to embodiments of the present invention.

[0021] Figure 1 This is a flowchart illustrating an intelligent vehicle autonomous driving formation obstacle avoidance control method provided in an embodiment of the present invention.

[0022] like Figure 1 As shown, the intelligent vehicle autonomous driving formation obstacle avoidance control method includes the following steps: In step S101, an intelligent vehicle formation controller is constructed based on the destination data and obstacle data of the target intelligent vehicle formation to control the target intelligent vehicle formation to move toward the destination.

[0023] In some embodiments, an intelligent vehicle formation controller is constructed based on destination data and obstacle data of the target intelligent vehicle formation to control the target intelligent vehicle formation to move toward the destination, including: Acquire destination data of the target intelligent vehicle platoon and collect obstacle data that hinders the target intelligent vehicle platoon in the driving environment; The heading angle of each vehicle is determined based on the destination data in order to construct the formation gravitational potential field function; Construct the formation repulsion potential field function based on obstacle data; A smart vehicle formation controller is built based on the formation gravitational potential field function and the formation repulsive potential field function. Based on the intelligent vehicle platoon controller, attractive and repulsive forces are simultaneously applied to the individual intelligent vehicles in the target intelligent vehicle platoon, causing the target intelligent vehicle platoon to move toward the destination.

[0024] In actual implementation, based on the system attributes of the complex driving environment in which the intelligent vehicle platoon is located, the driving environment can be equivalent to a mixed field composed of multiple force fields. Therefore, the platoon obstacle avoidance strategy is essentially the optimal sequence group corresponding to each moment of the spatiotemporal evolution of some observable particles with dynamic response in the mixed field.

[0025] Assuming the intelligent vehicle platoon has a single destination, the destination generates a gravitational potential field, the direction of which is determined by the heading angle of each individual vehicle within the platoon. Correspondingly, various scene elements in the driving environment that obstruct the intelligent vehicle platoon can be considered as obstacles, generating a repulsive potential field pointing towards each individual vehicle. Therefore, the heading angle of each individual vehicle can be determined based on the destination data to construct the platoon's gravitational potential field function, and the platoon's repulsive potential field function can be constructed based on the obstacle data. Thus, an intelligent vehicle platoon controller can be built based on the platoon's gravitational and repulsive potential field functions.

[0026] The intelligent vehicle platooning controller based on the artificial potential field method applies both attractive and repulsive forces to individual intelligent vehicles in the target intelligent vehicle platoon, causing the target intelligent vehicle platoon to move toward its destination, and calculates a smooth, collision-free path in real time.

[0027] Among them, the gravitational potential field function of complex driving environment U at ( x and repulsive potential field function U re ( x As shown in the following formula: (1) (2) In the formula, or at and or re These are the gravitational increment coefficient and the repulsive increment coefficient, respectively. x , x gl and x ob These are the current location coordinates of the intelligent vehicle, the destination, and the obstacle, respectively. r ( x , x gl ( ) represents the distance between the intelligent vehicle and the destination. r ( x , x ob ( ) represents the shortest distance between the intelligent vehicle and the obstacle. r 0 is a constant, and r 0>0 describes the actual distance of the obstacle's influence. n These are constants given based on experience.

[0028] Gravitational force on a single intelligent vehicle and repulsive force for U at ( x )and U re ( x The negative gradient of ) is shown in the following equation: (3) (4) (5) (6) In the formula, F re1The direction is from the obstacle towards the individual intelligent vehicle. F re2 The direction is from the individual intelligent vehicle to the destination. Therefore, the resultant force on the individual intelligent vehicle in the resultant potential field is as shown in equation (7). The intelligent vehicle formation is subjected to the combined effect of the attraction of the destination and the repulsive force of obstacles in the driving scene, and continuously moves towards the destination.

[0029] (7) In the formula, This represents the net force experienced by a single intelligent vehicle in the net potential field.

[0030] In step S102, a spatiotemporal transformation strategy for intelligent vehicle formation based on the queue scaling coefficient is established according to the queue scaling coefficient of the target intelligent vehicle formation and the driving safety boundary.

[0031] In some embodiments, a spatiotemporal transformation strategy for intelligent vehicle formation based on the queue scaling coefficient is established according to the queue scaling coefficient of the target intelligent vehicle formation and the driving safety boundary, including: Obtain the queue width of the target intelligent vehicle platoon and the driving safety boundaries of adjacent vehicles within the platoon under the current driving environment; The queue expansion coefficient of the target intelligent vehicle platoon along the direction of travel of the lead vehicle is calculated based on the queue width and the driving safety boundary of adjacent vehicles in the current driving environment. Based on the queue scaling factor and the driving safety boundaries of adjacent vehicles in the queue under the current driving environment, a spatiotemporal transformation strategy for intelligent vehicle platooning formation is established.

[0032] In some embodiments, the spatiotemporal transformation strategy for intelligent vehicle platooning based on the queue scaling coefficient includes a no-transformation strategy, a homogeneous transformation strategy, and a heterogeneous transformation strategy, wherein... When the queue expansion coefficient is greater than or equal to 1, the formation-no-change strategy is executed, and the current driving environment can be passed without adjusting the formation. If the queue scaling factor is greater than the preset minimum queue scaling factor but less than 1, the formation isomorphism transformation strategy is executed to adjust the queue scaling factor so that the target intelligent vehicle formation can pass through the current driving environment while maintaining the formation. When the queue scaling factor is less than or equal to the preset minimum queue scaling factor, the formation heterogeneous transformation mode is executed, so that each intelligent vehicle in the target intelligent vehicle formation performs obstacle avoidance and autonomous driving. When the mode is switched out, the formation is restored according to the driving status of the navigator vehicle.

[0033] In actual implementation, the obstacle avoidance process of a single intelligent vehicle based on the artificial potential field method only needs to consider the safety of obstacle avoidance and the ability to reach the destination quickly. However, in the process of intelligent vehicles forming a platoon to avoid obstacles, in order to improve their adaptability to complex environments, it is necessary not only to consider the safety of obstacle avoidance and the ability to reach the destination quickly, but also to consider the spatiotemporal transformation strategy of the intelligent vehicle platoon formation.

[0034] Therefore, embodiments of the present invention simultaneously consider the longitudinal and lateral scaling of the intelligent vehicle platoon along the direction of travel of the lead vehicle, as well as the driving safety boundaries of adjacent vehicles within the platoon. First, the queue width of the target intelligent vehicle platoon and the driving safety boundaries of adjacent vehicles within the platoon under the current driving environment are obtained. Based on the queue width and the driving safety boundaries of adjacent vehicles within the platoon under the current driving environment, the queue scaling coefficient of the target intelligent vehicle platoon along the direction of travel of the lead vehicle is calculated. Then, based on the queue scaling coefficient and the driving safety boundaries of adjacent vehicles within the platoon under the current driving environment, a system is established using the queue scaling coefficient. c The formation and spacetime transformation strategy.

[0035] Among them, the platooning scaling factor of the target intelligent vehicle platoon along the direction of travel of the lead vehicle. c The specific expression is as follows: (8) In the formula, W The queue width for intelligent vehicle platooning. W max This refers to the maximum width of the drivable area within the driving environment for intelligent vehicle platooning. c min It is the minimum scaling factor that prevents collisions between adjacent vehicles in a platoon of intelligent vehicles, representing the baseline value for changes in the intelligent vehicle platoon.

[0036] During the journey of an intelligent vehicle platoon towards its destination, the lead vehicle (i.e., the first vehicle) uses intelligent sensors to perceive scene information such as obstacles in the driving environment in order to calculate the current position. c Values, and determine the formation transformation mode values. k The system plans the desired driving path for intelligent vehicle platoons. Within the platoon, individual vehicles restore and maintain the platoon formation based on the driving status of the lead vehicle, thereby improving the platoon's driving safety and environmental adaptability in complex driving environments.

[0037] Among them, the formation transformation modes mainly include three modes: no formation change, isomorphic formation transformation, and heteromorphic formation transformation.

[0038] (1) Formation without change mode ( k =1 mode). When c When ≥1, test Wmax ≥ W This means that the drivable area within the driving environment of the lead vehicle is sufficient to accommodate the current formation of the intelligent vehicle platoon, allowing it to pass through the current driving environment without adjusting its formation. (2) Formation isomorphic transformation mode ( k =2 mode). When c min < c When the value is less than 1, the width of the drivable area within the driving environment of the lead vehicle is relatively low. Intelligent vehicle platooning can adjust this by... c The value passes through this area, and the pattern maintains the historical formation. c min Set the minimum queue scaling factor; (3) Formation Heterogeneous Transformation Mode ( k =3 mode). When c ≤ c min When the intelligent vehicle platoon cannot complete the driving task through isomorphic transformation, the platoon formation must be changed to achieve the intended driving task. In this mode, each vehicle in the intelligent vehicle platoon performs obstacle avoidance and autonomous driving independently. When switching out of this mode, the platoon formation is restored based on the driving status of the lead vehicle.

[0039] In step S103, the intelligent vehicle formation controller is dynamically optimized using the Levy flight random search logic based on the cuckoo algorithm to obtain the optimized intelligent vehicle formation controller.

[0040] In practical implementation, to address the randomness of driving scenarios caused by the uncertainty of obstacle intentions in complex driving environments, this embodiment of the invention designs a vehicle platooning search logic for complex driving environments. Specifically, it employs a Levy flight random search logic based on the cuckoo algorithm to dynamically optimize the incremental coefficients in the platooning controller designed based on the artificial potential field method. or at and or re Furthermore, dynamic vehicle platooning spatiotemporal transformation strategies are considered to improve the driving safety and scenario adaptability of intelligent vehicle platooning.

[0041] The Lévy flight mechanism is based on a non-normally distributed stochastic process, with compensation calculations following a Lévy stable distribution and motion directions following a uniform distribution. During the search process, it alternates between short-distance movements with small step sizes and long-distance movements with large step sizes, thereby enhancing global search capabilities and reducing the possibility of getting trapped in local optima. The stochastic step size function of Lévy flight is described below. l ( S t , q As shown in the following formula: (9) In the formula, L ( S t , q Let Γ be the Lévy distribution function, and Γ be the gamma function. q The step size index, S t The stochastic step size in the Lévy flight mechanism can be used as a stochastic increment of the artificial potential field. For better implementation... S t In engineering applications of the Lévy flight stochastic search logic, the following expression is used to calculate... S t : (10) In the formula, the parameters m and v It follows a normal distribution as follows: (11) (12) In the formula, s μ and s v To use empirical values ​​calibrated through experiments, and to obtain the corresponding... m and v。

[0042] The Levy flight mechanism based on the cuckoo algorithm dynamically optimizes the incremental coefficients in the intelligent vehicle formation controller, and has the following steps: (1) Initialization L ( S t , q Calculate the incremental coefficients based on the relevant parameters in the table. or at and or re ; (2) The obstacle avoidance strategy of intelligent vehicle formation is calculated by using the artificial potential field method, and the number of iterations for the lead vehicle to reach the desired position after obstacle avoidance is set. n and calculate the corresponding k value; (3) Calculate according to formula (9) l ( S t , q ) value, and calculate the updated value. or at and or re ; (4) Update the platooning position of the intelligent vehicles and calculate the position in the current iteration step. l (S t , q The extreme values ​​of ) are used to determine the most suitable ( or at , or re )combination; (5) Judgment n If the value exceeds a predetermined value, output the value of ( ). or at , or re If the optimal value is found, return (2); (6) After the iteration ends, return the formation solution data corresponding to the optimal value, and the optimal ( or at , or re The combination is shown in the following formula: (13) (14) Substituting the stochastic step size from the Lévy flight mechanism into the gravitational and repulsive potential field functions of the artificial potential field method, we obtain the corresponding... U at ( x )and U re ( x The optimized intelligent vehicle platooning controller is shown in the following formula: (15) (16) In step S104, the target intelligent vehicle formation is controlled to avoid obstacles using the optimized intelligent vehicle formation controller and the intelligent vehicle formation spatiotemporal transformation strategy based on the queue scaling coefficient.

[0043] In practical implementation, the optimized intelligent vehicle formation controller possesses vehicle formation search logic with Lévy flight random search characteristics, which improves the solution of obstacle avoidance logic for intelligent vehicle formation using the classical artificial potential field method. Therefore, by utilizing the optimized intelligent vehicle formation controller and the intelligent vehicle formation spatiotemporal transformation strategy based on the queue scaling coefficient, the obstacle avoidance process of the controlled target intelligent vehicle formation can be improved, such as the vehicle formation scene adaptability evaluator. The specific obstacle avoidance process is as follows: (1) Initialize the intelligent vehicle formation and build a database of commonly used intelligent vehicle formations; (2) Determine the drivable area of ​​the lead vehicle in the intelligent vehicle platoon at the current moment. When the lead vehicle has only a single travel path, determine the drivable area based on the platoon expansion coefficient. cCalculate and determine the most suitable formation configuration for the current obstacle avoidance situation. k When the lead vehicle has multiple drivable routes and the driving environment is complex, it can only choose one route. k =2 formation change patterns; (3) If multiple feasible paths are found and the formation change is in a heterogeneous mode, the optimized artificial potential field method is used to determine the current driving environment. or at and or re The value of is used to guide intelligent vehicle platooning in obstacle avoidance; (4) In k =0 and k In =1 mode, the following vehicle adopts the strategy of following the lead vehicle to maintain the intelligent vehicle formation shape; k In =2 mode, the following vehicle adopts an independent obstacle avoidance strategy; (5) Determine whether the lead vehicle has reached the destination. If it has not yet reached the destination, continue to execute the obstacle avoidance logic again. Throughout the entire driving process, the key internal parameters of the obstacle avoidance strategy adapt to the driving environment to ensure that the intelligent vehicle platoon can maintain its formation to the greatest extent and successfully reach the destination.

[0044] In summary, the intelligent vehicle autonomous driving platooning obstacle avoidance control method proposed in this embodiment of the invention designs a spatiotemporal transformation strategy for intelligent vehicle platooning formations and switches the formation transformation mode by using a queue scaling coefficient, thereby improving the adaptability of intelligent vehicle platooning to complex environments. The Levy flight mechanism from the Cuckoo Search algorithm is introduced into the traditional artificial potential field method to establish a vehicle platooning search logic based on the Levy flight mechanism. The gravity and repulsion increment coefficients are optimized, solving the problem of randomness in driving scenarios caused by the uncertainty of obstacle intent in complex driving environments, and overcoming the limitations of gravity and repulsion increment coefficient settings in the traditional artificial potential field method. By optimizing the gravity and repulsion increment coefficients and cooperating with appropriate formation modes, the obstacle avoidance capability of intelligent vehicle platooning in complex driving environments is established, improving the safety and adaptability of intelligent vehicle platooning in complex driving environments and shortening the platooning obstacle avoidance time.

[0045] Next, the intelligent vehicle autonomous driving formation obstacle avoidance control device according to an embodiment of the present invention is described with reference to the accompanying drawings.

[0046] Figure 3 This is a block diagram of an intelligent vehicle autonomous driving formation obstacle avoidance control device provided in an embodiment of the present invention.

[0047] like Figure 3 As shown, the intelligent vehicle autonomous driving formation obstacle avoidance control 30 includes: a controller construction module 301, a strategy construction module 302, a dynamic optimization module 303, and an obstacle avoidance module 304.

[0048] The system comprises the following modules: Controller Construction Module 301: Constructs an intelligent vehicle formation controller based on destination and obstacle data of the target intelligent vehicle formation to control the formation's movement towards its destination. Strategy Construction Module 302: Establishes a spatiotemporal transformation strategy for the intelligent vehicle formation based on the queue scaling factor and driving safety boundaries. Dynamic Optimization Module 303: Dynamically optimizes the intelligent vehicle formation controller using a Lévy flight random search logic based on the cuckoo algorithm to obtain an optimized controller. Obstacle Avoidance Module 304: Controls the target intelligent vehicle formation to avoid obstacles using the optimized controller and the spatiotemporal transformation strategy based on the queue scaling factor.

[0049] In some embodiments, the controller construction module 301 includes: The system comprises: a data acquisition unit for acquiring destination data of the target intelligent vehicle formation and data on obstacles hindering the formation in the driving environment; a first potential field unit for determining the heading angle of each individual vehicle based on the destination data to construct the formation's gravitational potential field function; a second potential field unit for constructing the formation's repulsive potential field function based on the obstacle data; a construction unit for constructing an intelligent vehicle formation controller based on the gravitational and repulsive potential field functions; and a force application unit for simultaneously applying gravitational and repulsive forces to the individual intelligent vehicles in the target intelligent vehicle formation, based on the intelligent vehicle formation controller, to cause the target intelligent vehicle formation to move towards its destination.

[0050] In some embodiments, the policy construction module 302 includes: The acquisition unit is used to acquire the queue width of the target intelligent vehicle formation and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment; the calculation unit is used to calculate the queue expansion coefficient of the target intelligent vehicle formation along the driving direction of the lead vehicle based on the queue width and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment; the strategy establishment unit is used to establish a spatiotemporal transformation strategy of intelligent vehicle formation based on the queue expansion coefficient and the driving safety boundaries of adjacent vehicles in the formation under the current driving environment.

[0051] In some embodiments, the spatiotemporal transformation strategy for intelligent vehicle platooning based on the queue scaling coefficient includes a no-transformation strategy, a homogeneous transformation strategy, and a heterogeneous transformation strategy, wherein... When the queue scaling factor is greater than or equal to 1, the formation-no-change strategy is executed, allowing the vehicle to pass through the current driving environment without adjusting the formation. When the queue scaling factor is greater than the preset minimum queue scaling factor but less than 1, the formation isomorphic transformation strategy is executed to adjust the queue scaling factor, enabling the target intelligent vehicle formation to pass through the current driving environment while maintaining the formation. When the queue scaling factor is less than or equal to the preset minimum queue scaling factor, the formation heterogeneous transformation mode is executed, allowing each intelligent vehicle in the target intelligent vehicle formation to perform obstacle avoidance and autonomous driving. When switching out of this mode, the formation is restored based on the driving status of the navigator vehicle.

[0052] It should be noted that the foregoing explanation of the embodiment of the intelligent vehicle autonomous driving formation obstacle avoidance control method also applies to the intelligent vehicle autonomous driving formation obstacle avoidance control device of this embodiment, and will not be repeated here.

[0053] The intelligent vehicle autonomous driving platooning obstacle avoidance control device proposed in this embodiment of the invention designs a spatiotemporal transformation strategy for intelligent vehicle platooning formations and switches the formation transformation mode by using a queue scaling coefficient, thereby improving the adaptability of intelligent vehicle platooning to complex environments. The Lévy flight mechanism from the Cuckoo Search algorithm is introduced into the traditional artificial potential field method to establish a vehicle platooning search logic based on the Lévy flight mechanism. The gravity and repulsion increment coefficients are optimized, solving the problem of randomness in driving scenarios caused by the uncertainty of obstacle intent in complex driving environments, and overcoming the limitations of gravity and repulsion increment coefficient settings in the traditional artificial potential field method. By optimizing the gravity and repulsion increment coefficients and cooperating with appropriate formation modes, the obstacle avoidance capability of intelligent vehicle platooning in complex driving environments is established, improving the safety and adaptability of intelligent vehicle platooning in complex driving environments and shortening the platooning obstacle avoidance time.

[0054] Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of the present invention.

[0055] The vehicle may include: a memory 401, a processor 402, and a computer program stored on the memory 401 and capable of running on the processor 402.

[0056] When the processor 402 executes the program, it implements the intelligent vehicle autonomous driving formation obstacle avoidance control method provided in the above embodiments.

[0057] Furthermore, the vehicle also includes: Communication interface 403 is used for communication between memory 401 and processor 402.

[0058] The memory 401 is used to store computer programs that can run on the processor 402.

[0059] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0060] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0061] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0062] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0063] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent vehicle autonomous driving platooning obstacle avoidance control method.

[0064] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0065] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0066] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0067] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0068] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0069] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0070] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0071] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for intelligent vehicle autonomous driving platooning obstacle avoidance control, characterized in that, Includes the following steps: An intelligent vehicle formation controller is constructed based on the destination data and obstacle data of the target intelligent vehicle formation to control the target intelligent vehicle formation to move toward the destination; Based on the queue scaling coefficient and driving safety boundary of the target intelligent vehicle formation, establish a spatiotemporal transformation strategy for intelligent vehicle formation based on the queue scaling coefficient; The intelligent vehicle formation controller is dynamically optimized using the Levy flight random search logic based on the cuckoo algorithm to obtain the optimized intelligent vehicle formation controller. The optimized intelligent vehicle formation controller and the spatiotemporal transformation strategy of intelligent vehicle formation based on the queue scaling coefficient are used to control the target intelligent vehicle formation to avoid obstacles.

2. The intelligent vehicle autonomous driving platooning obstacle avoidance control method according to claim 1, characterized in that, The step of constructing an intelligent vehicle platoon controller based on destination data and obstacle data of the target intelligent vehicle platoon to control the target intelligent vehicle platoon to move toward the destination includes: Acquire destination data of the target intelligent vehicle convoy and collect obstacle data that obstructs the target intelligent vehicle convoy in the driving environment; The heading angle of each vehicle is determined based on the destination data in order to construct the formation gravitational potential field function; Construct a formation repulsion potential field function based on the obstacle data; The intelligent vehicle formation controller is constructed based on the formation gravitational potential field function and the formation repulsive potential field function. Based on the intelligent vehicle platoon controller, attractive and repulsive forces are simultaneously applied to the individual intelligent vehicles in the target intelligent vehicle platoon, causing the target intelligent vehicle platoon to move toward its destination.

3. The intelligent vehicle autonomous driving platooning obstacle avoidance control method according to claim 1, characterized in that, The step of establishing a spatiotemporal transformation strategy for intelligent vehicle formation based on the queue scaling coefficient and driving safety boundary includes: Obtain the queue width of the target intelligent vehicle platoon and the driving safety boundary of adjacent vehicles within the platoon under the current driving environment; The queue expansion coefficient of the target intelligent vehicle formation along the direction of travel of the lead vehicle is calculated based on the queue width and the driving safety boundary of adjacent vehicles in the current driving environment. The intelligent vehicle formation spatiotemporal transformation strategy based on the queue scaling coefficient is established according to the queue scaling coefficient and the driving safety boundary of adjacent vehicles in the current driving environment.

4. The intelligent vehicle autonomous driving platooning obstacle avoidance control method according to claim 3, characterized in that, The intelligent vehicle platooning formation spatiotemporal transformation strategy based on the queue scaling coefficient includes a formation-no-transformation strategy, a formation-isomorphic transformation strategy, and a formation-heterogeneous transformation strategy, wherein... When the queue expansion coefficient is greater than or equal to 1, the formation-no-change strategy is executed, and the current driving environment can be passed without adjusting the formation; If the queue scaling factor is greater than the preset minimum queue scaling factor but less than 1, the formation isomorphic transformation strategy is executed to adjust the queue scaling factor so that the target intelligent vehicle formation can pass through the current driving environment while maintaining the formation. When the queue scaling factor is less than or equal to the preset minimum queue scaling factor, the formation heterogeneous transformation mode is executed, so that each intelligent vehicle in the target intelligent vehicle formation performs obstacle avoidance and autonomous driving. When the mode is switched out, the formation is restored according to the driving status of the navigator vehicle.

5. A smart vehicle autonomous driving platooning obstacle avoidance control device, characterized in that, include: The controller construction module is used to construct an intelligent vehicle formation controller based on the destination data and obstacle data of the target intelligent vehicle formation, so as to control the target intelligent vehicle formation to move towards the destination; The strategy construction module is used to establish a spatiotemporal transformation strategy for intelligent vehicle formation based on the queue scaling coefficient and driving safety boundary of the target intelligent vehicle formation. The dynamic optimization module is used to dynamically optimize the intelligent vehicle formation controller by employing the Levy flight random search logic based on the cuckoo algorithm, so as to obtain the optimized intelligent vehicle formation controller. The obstacle avoidance module is used to control the target intelligent vehicle formation to avoid obstacles using the optimized intelligent vehicle formation controller and the intelligent vehicle formation spatiotemporal transformation strategy based on the queue scaling coefficient.

6. The intelligent vehicle autonomous driving platooning obstacle avoidance control device according to claim 5, characterized in that, The controller construction module includes: The acquisition unit is used to acquire destination data of the target intelligent vehicle convoy and to acquire obstacle data that hinders the target intelligent vehicle convoy in the driving environment. The first potential field unit is used to determine the heading angle of each vehicle unit based on the destination data, so as to construct the formation gravitational potential field function; The second potential field unit is used to construct the formation repulsion potential field function based on the obstacle data; A construction unit is used to construct the intelligent vehicle formation controller based on the formation gravitational potential field function and the formation repulsive potential field function. The force application unit is used to simultaneously apply attractive and repulsive forces to individual smart vehicles in the target smart vehicle formation based on the smart vehicle formation controller, so that the target smart vehicle formation moves toward the destination.

7. The intelligent vehicle autonomous driving platooning obstacle avoidance control device according to claim 5, characterized in that, The strategy construction module includes: The acquisition unit is used to acquire the queue width of the target intelligent vehicle formation and the driving safety boundary of adjacent vehicles in the formation under the current driving environment; The calculation unit is used to calculate the queue expansion coefficient of the target intelligent vehicle formation along the direction of travel of the lead vehicle based on the queue width and the driving safety boundary of adjacent vehicles in the current driving environment. The strategy establishment unit is used to establish the intelligent vehicle formation spatiotemporal transformation strategy based on the queue scaling coefficient and the driving safety boundaries of adjacent vehicles in the platoon under the current driving environment.

8. The intelligent vehicle autonomous driving platooning obstacle avoidance control device according to claim 7, characterized in that, The intelligent vehicle platooning formation spatiotemporal transformation strategy based on the queue scaling coefficient includes a formation-no-transformation strategy, a formation-isomorphic transformation strategy, and a formation-heterogeneous transformation strategy, wherein... When the queue expansion coefficient is greater than or equal to 1, the formation-no-change strategy is executed, and the current driving environment can be passed without adjusting the formation; If the queue scaling factor is greater than the preset minimum queue scaling factor but less than 1, the formation isomorphic transformation strategy is executed to adjust the queue scaling factor so that the target intelligent vehicle formation can pass through the current driving environment while maintaining the formation. When the queue scaling factor is less than or equal to the preset minimum queue scaling factor, the formation heterogeneous transformation mode is executed, so that each intelligent vehicle in the target intelligent vehicle formation performs obstacle avoidance and autonomous driving. When the mode is switched out, the formation is restored according to the driving status of the navigator vehicle.

9. A vehicle, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent vehicle autonomous driving platooning obstacle avoidance control method as described in any one of claims 1-4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the intelligent vehicle autonomous driving formation obstacle avoidance control method as described in any one of claims 1-4.

Images