Automatic driving control method and device, computer device and storage medium

Abstract

The application relates to an automatic driving control method and device, computer equipment and a storage medium. The application relates to the technical field of automatic driving. The method comprises the following steps: firstly, determining a target obstacle in the current environment of a vehicle, acquiring vehicle feature information of the vehicle and obstacle feature information of the target obstacle, determining an automatic driving mode required by the vehicle based on a preset condition, if the obstacle feature information meets the preset condition relative to the vehicle feature information, acquiring a longitudinal planning time interval and a first lateral planning distance, further generating a best first planning strategy according to the vehicle feature information, the obstacle feature information, the longitudinal planning time interval and the first lateral planning distance, and controlling the automatic driving of the vehicle according to the first planning strategy. The method can generate multiple planning strategies suitable for different driving scenes in different driving scenes, and realizes the automatic driving of the vehicle.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to an autonomous driving control method, device, computer equipment, storage medium, and computer program product. Background Technology

[0002] Decision planning technology is used to generate drivable paths for autonomous vehicles and the expected speed at each point along the path, which has a significant impact on the performance of autonomous vehicles.

[0003] Currently, decision-making and planning technologies mostly adopt a layered architecture, which includes three layers: task planning, behavioral decision-making, and action planning. Task planning solves the problem of which lanes to take from point A to point B; behavioral decision-making solves strategic problems, such as whether to follow other vehicles, whether to avoid obstacles, whether to change lanes, and whether to stop at traffic lights; action planning considers vehicle kinematic constraints, dynamic constraints, static obstacles, dynamic obstacles, and road geometry to generate executable driving paths for the vehicle and the expected speed at each point on the path.

[0004] However, current decision-making and planning technologies for autonomous driving can only generate a limited number of candidate paths. When making sharp turns or avoiding obstacles, there is a risk that an executable trajectory cannot be generated. Furthermore, they are difficult to adapt to high-speed and urban road scenarios and can only be used in low-speed scenarios such as automatic parking, which greatly limits the driving scenarios in which they can be applied. Summary of the Invention

[0005] Therefore, it is necessary to provide an autonomous driving control method, device, computer equipment, computer-readable storage medium, and computer program product that can be applied to different driving scenarios to address the aforementioned technical problems.

[0006] Firstly, this application provides an autonomous driving control method. The method includes:

[0007] Identify the target obstacles in the vehicle's current environment;

[0008] Acquire vehicle feature information and obstacle feature information of the target obstacle;

[0009] If the obstacle feature information meets the preset conditions relative to the vehicle feature information, then the longitudinal planning time distance and the first lateral planning distance are obtained.

[0010] A first planning strategy is generated based on vehicle feature information, obstacle feature information, longitudinal planning time distance, and first lateral planning distance, and the autonomous driving of the vehicle is controlled according to the first planning strategy.

[0011] In one embodiment, determining the target obstacle in the vehicle's current environment includes:

[0012] Establish a Frenet coordinate system based on the lane centerline in the current environment of the vehicle;

[0013] In the Frenet coordinate system, the obstacle closest to the vehicle is taken as the target obstacle.

[0014] In one embodiment, the vehicle feature information includes the vehicle's initial longitudinal position and initial lateral position in the Frenet coordinate system, and the obstacle feature information includes the target obstacle's longitudinal position and lateral position in the Frenet coordinate system.

[0015] If the obstacle feature information meets preset conditions relative to the vehicle feature information, then the longitudinal planning time distance and the first lateral planning distance are obtained, including:

[0016] The longitudinal distance between vehicles is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and the lateral spacing is obtained based on the lateral position of the obstacle.

[0017] If the longitudinal distance between vehicles is less than the minimum distance threshold and the lateral distance is less than the lane width threshold, obtain multiple longitudinal planning time distances and multiple first lateral planning distances.

[0018] In one embodiment, a first planning strategy is generated based on vehicle feature information, obstacle feature information, longitudinal planning time distance, and a first lateral planning distance, including:

[0019] Multiple sets of first planning parameters are obtained by arranging and combining multiple vertical planning time intervals and multiple first horizontal planning distances;

[0020] Determine multiple consecutive planning steps within a preset planning time period, and configure multiple sets of first planning parameters for each planning step;

[0021] Based on the multiple sets of first planning parameters corresponding to each planning step, the time sequence relationship of each planning step is arranged and combined to obtain multiple adaptive planning strategies. The adaptive planning strategy includes multiple planning steps continuously acquired within a preset planning time, and each planning step corresponds to one set of first planning parameters.

[0022] Based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, calculate the cost parameters corresponding to each planning step in the adaptive planning strategy, and further calculate the cost parameters and sum corresponding to each adaptive planning strategy.

[0023] The adaptive planning strategy that minimizes the cost parameters is taken as the first planning strategy.

[0024] In one embodiment, the method further includes:

[0025] If the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then the acceleration planning time and the second lateral planning distance are obtained.

[0026] A second planning strategy is generated based on vehicle characteristic information, acceleration planning time, and second lateral planning distance, and the autonomous driving of the vehicle is controlled according to the second planning strategy.

[0027] In one embodiment, the vehicle feature information includes the vehicle's initial longitudinal position and initial lateral position in the Frenet coordinate system, and the obstacle feature information includes the target obstacle's longitudinal position and lateral position in the Frenet coordinate system.

[0028] If the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then the acceleration planning time and the second lateral planning distance are obtained, including:

[0029] The longitudinal distance between vehicles is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and the lateral spacing is obtained based on the lateral position of the obstacle.

[0030] If the longitudinal distance between vehicles is not less than the minimum distance threshold, or the lateral distance is not less than the lane width threshold, obtain multiple acceleration planning times and multiple second lateral planning distances.

[0031] In one embodiment, a second planning strategy is generated based on vehicle characteristic information, acceleration planning time, and second lateral planning distance, including:

[0032] Multiple sets of second planning parameters are obtained by permuting and combining multiple accelerated planning times and multiple second lateral planning distances;

[0033] Determine multiple consecutive planning steps within a preset planning time period, and configure multiple sets of second planning parameters for each planning step;

[0034] Based on the multiple sets of second planning parameters corresponding to each planning step, the cruise planning strategies are arranged and combined according to the temporal relationship of each planning step. Each cruise planning strategy contains multiple planning steps continuously acquired within a preset planning time, and each planning step corresponds to one set of second planning parameters.

[0035] Based on the second planning parameters corresponding to each planning step in each cruise planning strategy, calculate the cost parameters corresponding to each planning step in the cruise planning strategy, and further calculate the cost parameters and sum corresponding to each cruise planning strategy.

[0036] The cruise planning strategy that minimizes the cost parameters is used as the second planning strategy.

[0037] Secondly, this application also provides an automatic driving control device. The device includes:

[0038] The obstacle detection module is used to identify target obstacles in the vehicle's current environment.

[0039] The feature detection module is used to acquire vehicle feature information and obstacle feature information of the target obstacle;

[0040] The parameter generation module is used to obtain the longitudinal planning time distance and the first lateral planning distance if the obstacle feature information meets the preset conditions relative to the vehicle feature information.

[0041] The driving planning module is used to generate a first planning strategy based on vehicle feature information, obstacle feature information, longitudinal planning time distance and first lateral planning distance, and control the autonomous driving of the vehicle according to the first planning strategy.

[0042] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0043] Identify the target obstacles in the vehicle's current environment;

[0044] Acquire vehicle feature information and obstacle feature information of the target obstacle;

[0045] If the obstacle feature information meets the preset conditions relative to the vehicle feature information, then the longitudinal planning time distance and the first lateral planning distance are obtained.

[0046] A first planning strategy is generated based on vehicle feature information, obstacle feature information, longitudinal planning time distance, and first lateral planning distance, and the autonomous driving of the vehicle is controlled according to the first planning strategy.

[0047] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0048] Identify the target obstacles in the vehicle's current environment;

[0049] Acquire vehicle feature information and obstacle feature information of the target obstacle;

[0050] If the obstacle feature information meets the preset conditions relative to the vehicle feature information, then the longitudinal planning time distance and the first lateral planning distance are obtained.

[0051] A first planning strategy is generated based on vehicle feature information, obstacle feature information, longitudinal planning time distance, and first lateral planning distance, and the autonomous driving of the vehicle is controlled according to the first planning strategy.

[0052] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0053] Identify the target obstacles in the vehicle's current environment;

[0054] Acquire vehicle feature information and obstacle feature information of the target obstacle;

[0055] If the obstacle feature information meets the preset conditions relative to the vehicle feature information, then the longitudinal planning time distance and the first lateral planning distance are obtained.

[0056] A first planning strategy is generated based on vehicle feature information, obstacle feature information, longitudinal planning time distance, and first lateral planning distance, and the autonomous driving of the vehicle is controlled according to the first planning strategy.

[0057] The aforementioned autonomous driving control method, device, computer equipment, storage medium, and computer program product first identify the target obstacle in the vehicle's current environment, simultaneously acquiring vehicle feature information and obstacle feature information. Based on preset conditions, they determine the required autonomous driving mode for the vehicle. If the obstacle feature information satisfies the preset conditions relative to the vehicle feature information, they acquire the longitudinal planning time distance and the first lateral planning distance. Furthermore, based on the vehicle feature information, obstacle feature information, longitudinal planning time distance, and the first lateral planning distance, they generate an optimal first planning strategy and control the vehicle's autonomous driving according to the first planning strategy. This enables the generation of multiple planning strategies adapted to different driving scenarios under varying road conditions, thereby achieving autonomous driving. Attached Figure Description

[0058] Figure 1 This is an application environment diagram of an autonomous driving control method in one embodiment;

[0059] Figure 2 This is a flowchart illustrating an autonomous driving control method in one embodiment;

[0060] Figure 3 This is a schematic diagram of the Frenet coordinate system in one embodiment;

[0061] Figure 4 This is a schematic diagram illustrating the selection of time intervals for longitudinal planning in one embodiment;

[0062] Figure 5 This is a flowchart illustrating an autonomous driving control method in another embodiment;

[0063] Figure 6 This is a structural block diagram of an autonomous driving control device in one embodiment;

[0064] Figure 7This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] The autonomous driving control method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0067] In one embodiment, such as Figure 2 As shown, an autonomous driving control method is provided. Taking the application of this method to an electronic device as an example, the electronic device can specifically be... Figure 1 The method includes the following steps: (The terminal or server in the system)

[0068] Step 202: Identify the target obstacle in the current environment of the vehicle.

[0069] Among them, the target obstacle refers to the object closest to the vehicle in the direction of vehicle travel. The distance between the target obstacle and the vehicle can be obtained based on the Frenet coordinate system established for the road environment. The target obstacle includes, but is not limited to, vehicles, pedestrians, roadblocks, and guardrails.

[0070] Optionally, the vehicle's electronic equipment uses onboard LiDAR to identify obstacles in the vehicle's direction of travel and selects the nearest obstacle in front of the vehicle as the target obstacle. For example, if the nearest obstacle in front of the current vehicle is the vehicle in front, then the vehicle in front is selected as the target obstacle for the current vehicle.

[0071] Step 204: Obtain vehicle feature information and obstacle feature information of the target obstacle.

[0072] Vehicle feature information is used to characterize the vehicle's position, speed, acceleration, and direction of movement in the current road scene. Obstacle feature information is used to characterize the target obstacle's position, speed, acceleration, and direction of movement in the current road scene. Specifically, when the target obstacle is a moving object, such as a moving vehicle or pedestrian, obstacle feature information is used to characterize the target obstacle's position, speed, acceleration, and direction of movement in the current road scene; when the target obstacle is a stationary object, such as a stationary vehicle, road barrier, or traffic cone, obstacle feature information is used to characterize the target obstacle's position in the current road scene.

[0073] Optionally, while detecting the target obstacle, the vehicle-mounted electronic equipment also detects and acquires information such as the vehicle's current position, current speed, current acceleration, and current direction of movement, and uses this information as the vehicle's characteristic information, and detects and acquires information such as the target obstacle's current position, current speed, current acceleration, and current direction of movement, and uses this information as the target obstacle's obstacle characteristic information.

[0074] Step 206: If the obstacle feature information meets the preset conditions relative to the vehicle feature information, then obtain the longitudinal planning time distance and the first lateral planning distance.

[0075] The longitudinal planning time distance characterizes the target time for the vehicle to catch up with the target obstacle. Multiple different values ​​can be configured for the longitudinal planning time distance, which varies depending on the situation. The first lateral planning distance characterizes the target distance between the vehicle and objects on both sides. Multiple different values ​​can also be configured for the first lateral planning distance, which varies depending on the situation.

[0076] Optionally, the on-board electronic equipment compares obstacle feature information and vehicle feature information, determines the distance between the vehicle and the target obstacle based on the comparison result, and simultaneously determines the distance between the two sides of the target obstacle. If the distance between the vehicle and the target obstacle and the distance between the two sides of the target obstacle both meet the preset conditions, it is determined that the vehicle cannot overtake or bypass the target obstacle. Multiple longitudinal planning time distances and multiple first lateral planning distances are obtained. Each longitudinal planning time distance is a selectable safe distance, and each first lateral planning distance is a selectable lateral distance.

[0077] Step 208: Generate a first planning strategy based on vehicle feature information, obstacle feature information, longitudinal planning time distance and first lateral planning distance, and control the vehicle's autonomous driving according to the first planning strategy.

[0078] The first planning strategy is used to control the vehicle to follow the target obstacle within a preset time period in the future.

[0079] Optionally, the vehicle electronic device arranges and combines multiple longitudinal planning time intervals and multiple first lateral planning distances to obtain multiple sets of planning parameters. Each set of planning parameters includes a longitudinal planning time interval and a first lateral planning distance. Based on each set of planning parameters, vehicle feature information, and obstacle feature information, it predicts multiple driving trajectories of the vehicle in the future for a preset time period, selects the best driving trajectory from the multiple driving trajectories, and determines the best driving trajectory as the first planning strategy.

[0080] In one embodiment, when the electronic device is an in-vehicle terminal, the in-vehicle terminal directly obtains relevant information about the current environment through in-vehicle sensors and other in-vehicle devices to determine the target obstacle in the current environment of the vehicle; obtains vehicle feature information of the vehicle and obstacle feature information of the target obstacle; if the obstacle feature information meets preset conditions relative to the vehicle feature information, it obtains the longitudinal planning time distance and the first lateral planning distance; generates a first planning strategy based on the vehicle feature information, obstacle feature information, longitudinal planning time distance and the first lateral planning distance, and directly controls the autonomous driving of the vehicle based on the first planning strategy.

[0081] In another embodiment, when the electronic device is a server, the vehicle terminal acquires relevant information about the current environment in real time through vehicle sensors and other vehicle-mounted devices and uploads it to the server. The server receives the relevant information uploaded by the vehicle terminal through the network and determines the target obstacle in the current environment of the vehicle; acquires the vehicle's characteristic information and the obstacle's characteristic information; if the obstacle's characteristic information meets preset conditions relative to the vehicle's characteristic information, it acquires the longitudinal planning time distance and the first lateral planning distance; it generates a first planning strategy based on the vehicle characteristic information, obstacle characteristic information, longitudinal planning time distance, and the first lateral planning distance; the server sends the first planning strategy to the vehicle terminal through the network, and then the vehicle terminal controls the vehicle's autonomous driving according to the first planning strategy.

[0082] In the aforementioned autonomous driving control method, the target obstacle is first identified in the vehicle's current environment. Simultaneously, vehicle feature information and obstacle feature information are acquired. Based on preset conditions, the required autonomous driving mode for the vehicle is determined. If the obstacle feature information satisfies the preset conditions relative to the vehicle feature information, the longitudinal planning time distance and the first lateral planning distance are obtained. Furthermore, an optimal first planning strategy is generated based on the vehicle feature information, obstacle feature information, longitudinal planning time distance, and the first lateral planning distance. The vehicle's autonomous driving is then controlled according to this first planning strategy. This method can generate multiple planning strategies adapted to different driving scenarios under varying road conditions, thereby achieving autonomous driving.

[0083] In one embodiment, determining the target obstacle in the current environment of the vehicle includes: establishing a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; and in the Frenet coordinate system, identifying the obstacle closest to the vehicle as the target obstacle.

[0084] Optionally, the onboard electronic equipment uses the lane centerline in the vehicle's current environment as a reference line, with the direction along the reference line as the vertical axis and the direction perpendicular to the reference line as the horizontal axis, to establish a system as follows: Figure 3 The Frenet coordinate system shown in the diagram determines the position (including longitudinal and lateral positions), distance (including longitudinal distance and lateral spacing), and direction of movement of vehicles, target obstacles, and other objects.

[0085] In this embodiment, a Frenet coordinate system is established based on the lane centerline in the vehicle's current environment. Within the Frenet coordinate system, the obstacle closest to the vehicle is designated as the target obstacle. This system can accurately acquire vehicle feature information and obstacle feature information based on the Frenet coordinate system, and it has a wide range of applications, making it suitable for various driving road scenarios.

[0086] In one embodiment, the vehicle feature information includes the vehicle's initial longitudinal position and initial lateral position in the Frenet coordinate system, and the obstacle feature information includes the target obstacle's longitudinal position and lateral position in the Frenet coordinate system.

[0087] If the obstacle feature information meets the preset conditions relative to the vehicle feature information, then the longitudinal planning time distance and the first lateral planning distance are obtained, including: obtaining the longitudinal vehicle distance based on the initial longitudinal position and the longitudinal position of the obstacle, and obtaining the lateral spacing based on the lateral position of the obstacle; if the longitudinal vehicle distance is less than the minimum vehicle distance threshold and the lateral spacing is less than the lane width threshold, then multiple longitudinal planning time distances and multiple first lateral planning distances are obtained.

[0088] The lane width threshold is determined based on the vehicle's current environment, specifically by scanning the road width using an onboard LiDAR.

[0089] Optionally, in the Frenet coordinate system, the initial longitudinal and lateral positions of the vehicle and the longitudinal and lateral positions of the target obstacle are obtained. The longitudinal distance between the vehicle and the target obstacle is calculated based on the initial longitudinal position and the longitudinal position of the obstacle. The lateral distance between the two sides of the target obstacle is calculated based on the lateral position of the obstacle. If the longitudinal distance is less than the minimum distance threshold and the lateral distance is less than the lane width threshold, it is determined that the obstacle feature information meets the preset conditions relative to the vehicle feature information. Multiple longitudinal planning time distances and multiple first lateral planning distances are obtained.

[0090] In this embodiment, the longitudinal distance between the vehicle and the target obstacle, as well as the lateral distances on both sides of the target obstacle, are calculated based on the Frenet coordinate system. The required planning strategy for the vehicle is determined based on these longitudinal and lateral distances, and then the parameters corresponding to the desired planning strategy are selected. This enables the generation of multiple planning strategies adapted to different driving scenarios under varying road conditions, achieving autonomous driving for the vehicle.

[0091] In one embodiment, generating a first planning strategy based on vehicle feature information, obstacle feature information, longitudinal planning time interval, and a first lateral planning distance includes: arranging and combining multiple longitudinal planning time intervals and multiple first lateral planning distances to obtain multiple sets of first planning parameters; determining multiple consecutive planning steps within a preset planning time period, and configuring multiple sets of first planning parameters for each planning step; arranging and combining multiple sets of first planning parameters corresponding to the vehicle at each planning step based on the temporal relationship of each planning step to obtain multiple adaptive planning strategies, wherein each adaptive planning strategy contains multiple consecutive planning steps obtained within a preset planning time period, and each planning step corresponds to one set of first planning parameters; calculating the cost parameter corresponding to each planning step in each adaptive planning strategy based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, and further calculating the sum of cost parameters corresponding to each adaptive planning strategy; and selecting the adaptive planning strategy with the smallest sum of cost parameters as the first planning strategy.

[0092] The planning step size refers to a continuous unit of time within a preset planning length. For example, the preset planning duration can be set to 5 seconds, and the planning step size can be set to 0.1 seconds. Vehicle feature information includes vehicle speed, longitudinal position, and lateral position, while obstacle feature information includes target obstacle speed, longitudinal position, and lateral position.

[0093] Optionally, the current planning time is t, the planning step size is Δt, and the vehicle's longitudinal position in the Frenet coordinate system is s. t The vehicle speed is v t The longitudinal position of the target obstacle is s_lead t The speed is v_lead t .

[0094] d_lead t =s_lead t -s t

[0095] d_des t =d min +h_des*v_lead t

[0096] In the formula, d_lead t d_des represents the actual longitudinal distance between the vehicle and the target obstacle. t d represents the longitudinal distance between the vehicle and the target obstacle. min h_des is the minimum distance between the two vehicles when they are stationary, and is a constant; h_des is the longitudinal planning time interval, and the value of h_des may change with the planning time.

[0097] Δd=d_lead t -d_des t

[0098] Δv=v_lead t -v t

[0099] acc_cmd=k d Δd+k v Δv

[0100] In the formula, acc_cmd is the target acceleration of the vehicle; k d k v To control parameters, configurations are made according to different vehicle models.

[0101] The target speed of the vehicle after one planning step is

[0102] v_cmd t+Δt =v t +acc_cmd*Δt

[0103] The speed of the vehicle after one planned step is

[0104] v t+Δt =(1τ)*v t +τ*v_cmd t+Δt

[0105] In the formula, τ is the first-order hysteresis coefficient.

[0106] The longitudinal position of the vehicle after one planned step is

[0107]

[0108] The lateral position of the vehicle after one planned step is

[0109] l t+Δt =(1-τ)*l t +τ*l_des

[0110] In the formula, l_des is the first lateral planning distance, and the value of l_des may change with the planning time.

[0111] For times t1, t2, t3, t4, ..., t n The values ​​of h_des are shown in the parameter matrix below, with a planning step size between each time step.

[0112]

[0113] At any given moment, there are m parameter values ​​to choose from, so a total of m can be generated. n The strategy for determining the value of h_des. For example... Figure 4 As shown, one generation method is illustrated, where the value of m is 4 and the value of n is 4, resulting in a total of 256 possible values ​​for h_des.

[0114] For a certain strategy, h_des at a certain time t t The value is determined as follows, assuming t is located at t k-1 To t k Between,

[0115]

[0116] x, y∈1,2,3,4,…m.

[0117] For times t1, t2, t3, t4, ..., t n The values ​​of l_des are generated as shown in the parameter matrix below, with a planning step size between each time step.

[0118]

[0119] At any given moment, there are p possible parameter values, so a total of p can be generated. n The strategy for determining the value of l_des.

[0120] For a certain strategy at a certain time t, l_des t The value is determined as follows, assuming t is located at t k-1 To t k Between,

[0121]

[0122] x, y∈1,2,3,4,…p.

[0123] m n The strategy for choosing the value of h_des and p n By arranging and combining the values ​​of l_des according to the same time intervals, multiple adaptive programming strategies can be obtained. Each adaptive programming strategy includes time intervals t1, t2, t3, t4, ..., t n The corresponding vehicle speed, longitudinal position, and lateral position, respectively.

[0124] For each adaptive planning strategy, the cost parameters for each time step are calculated based on the vehicle's speed, longitudinal position, and lateral position at each time step.

[0125] [c t0 c t1 c t2 … c tn ]

[0126] t0 = t, tn = t + n, t k -t k-1 =Δt

[0127] c tk The cost of a certain planning step size.

[0128] And further calculate the total cost of each adaptive planning strategy:

[0129] c tk =∑(c t0 +c t1 +c t2 +c t3 +…+c tn )

[0130] c tk The smallest adaptive planning strategy is chosen as the first planning strategy.

[0131] In this embodiment, multiple sets of first planning parameters are obtained by arranging and combining multiple longitudinal planning time intervals and multiple first lateral planning distances; multiple consecutive planning steps within a preset planning time are determined, and multiple sets of first planning parameters are configured for each planning step; based on the multiple sets of first planning parameters corresponding to the vehicle at each planning step, multiple adaptive planning strategies are obtained by arranging and combining them according to the temporal relationship of each planning step. Each adaptive planning strategy contains multiple consecutive planning steps obtained within a preset planning time, and each planning step corresponds to one set of first planning parameters; based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, the cost parameter corresponding to each planning step in the adaptive planning strategy is calculated, and the sum of the cost parameters corresponding to each adaptive planning strategy is further calculated; the adaptive planning strategy with the smallest sum of cost parameters is taken as the first planning strategy. This allows for the simultaneous generation of multiple adaptive planning strategies when the vehicle cannot overtake or bypass the target obstacle, which is equivalent to generating multiple planned driving trajectories, and selecting the best planned driving trajectory as the final first planning strategy, thus improving the safety of autonomous driving.

[0132] In one embodiment, such as Figure 5 As shown, the method also includes:

[0133] Step 506: If the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then obtain the acceleration planning time and the second lateral planning distance.

[0134] The acceleration planning time characterizes the target time during which vehicle acceleration exists. This acceleration planning time can be configured with multiple different values, and its value varies depending on the situation. The second lateral planning distance characterizes the shortest distance between the vehicle and objects on both sides. This second lateral planning distance can also be configured with multiple different values, and its value varies depending on the situation.

[0135] Optionally, the onboard electronic equipment compares obstacle feature information and vehicle feature information, determines the distance between the vehicle and the target obstacle based on the comparison result, and simultaneously determines the distance between the two sides of the target obstacle. If either the distance between the vehicle and the target obstacle or the distance between the two sides of the target obstacle does not meet the preset conditions, it is determined that the vehicle can drive normally or drive normally after bypassing the target obstacle. Multiple acceleration planning times and multiple second lateral planning distances are obtained. Each acceleration planning time is a selectable acceleration driving mode, and each second lateral planning distance is a selectable lateral distance. This step follows step 204.

[0136] Step 508: Generate a second planning strategy based on vehicle feature information, acceleration planning time, and second lateral planning distance, and control the vehicle's autonomous driving according to the second planning strategy.

[0137] The second planning strategy is used to control the vehicle to drive normally or drive normally after bypassing the target obstacle within a preset time period in the future.

[0138] Optionally, the on-board electronic device arranges and combines multiple acceleration planning times and multiple second lateral planning distances to obtain multiple sets of planning parameters. Each set of planning parameters includes an acceleration planning time and a second lateral planning distance. Based on each set of planning parameters, vehicle feature information, and obstacle feature information, it predicts multiple driving trajectories of the vehicle in the future for a preset time. It selects the best driving trajectory from the multiple driving trajectories and determines the best driving trajectory as the second planning strategy.

[0139] In this embodiment, the target obstacle is first identified in the vehicle's current environment. Simultaneously, vehicle feature information and obstacle feature information are acquired. Based on preset conditions, the required autonomous driving mode for the vehicle is determined. If the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, an acceleration planning time and a second lateral planning distance are obtained. Furthermore, an optimal second planning strategy is generated based on the vehicle feature information, obstacle feature information, acceleration planning time, and second lateral planning distance. The vehicle's autonomous driving is then controlled according to this second planning strategy. This approach enables the generation of multiple planning strategies adapted to different driving scenarios under varying road conditions, thereby achieving autonomous driving.

[0140] In one embodiment, the vehicle feature information includes the vehicle's initial longitudinal position and initial lateral position in the Frenet coordinate system, and the obstacle feature information includes the target obstacle's longitudinal position and lateral position in the Frenet coordinate system.

[0141] If the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then the acceleration planning time and the second lateral planning distance are obtained, including: obtaining the longitudinal distance based on the initial longitudinal position and the longitudinal position of the obstacle, and obtaining the lateral spacing based on the lateral position of the obstacle; if the longitudinal distance is not less than the minimum distance threshold, or the lateral spacing is not less than the lane width threshold, then multiple acceleration planning times and multiple second lateral planning distances are obtained.

[0142] The lane width threshold is determined based on the vehicle's current environment, specifically by scanning the road width using an onboard LiDAR.

[0143] Optionally, in the Frenet coordinate system, the initial longitudinal and lateral positions of the vehicle and the longitudinal and lateral positions of the target obstacle are obtained. The longitudinal distance between the vehicle and the target obstacle is calculated based on the initial longitudinal position and the longitudinal position of the obstacle. The lateral distance between the two sides of the target obstacle is calculated based on the lateral position of the obstacle. If the longitudinal distance is not less than the minimum distance threshold or the lateral distance is not less than the lane width threshold, it is determined that the obstacle feature information does not meet the preset conditions relative to the vehicle feature information. Multiple acceleration planning times and multiple second lateral planning distances are then obtained.

[0144] In this embodiment, the longitudinal distance between the vehicle and the target obstacle, as well as the lateral distances on both sides of the target obstacle, are calculated based on the Frenet coordinate system. The required planning strategy for the vehicle is determined based on these longitudinal and lateral distances, and then the parameters corresponding to the desired planning strategy are selected. This enables the generation of multiple planning strategies adapted to different driving scenarios under varying road conditions, achieving autonomous driving for the vehicle.

[0145] In one embodiment, generating a second planning strategy based on vehicle feature information, acceleration planning time, and second lateral planning distance includes: permuting and combining multiple acceleration planning times and multiple second lateral planning distances to obtain multiple sets of second planning parameters; determining multiple consecutive planning steps within a preset planning duration, and configuring multiple sets of second planning parameters for each planning step; permuting and combining the multiple sets of second planning parameters corresponding to the vehicle at each planning step based on the temporal relationship of each planning step to obtain multiple cruise planning strategies, wherein each cruise planning strategy contains multiple consecutive planning steps acquired within a preset planning duration, and each planning step corresponds to one set of second planning parameters; calculating the cost parameter corresponding to each planning step in each cruise planning strategy based on the second planning parameters corresponding to each planning step in each cruise planning strategy, and further calculating the sum of cost parameters corresponding to each cruise planning strategy; and selecting the cruise planning strategy with the smallest sum of cost parameters as the second planning strategy.

[0146] The planning step size refers to a continuous unit of time within a preset planning length. For example, the preset planning duration can be set to 5 seconds, and the planning step size can be set to 0.1 seconds. Vehicle characteristic information includes vehicle speed, longitudinal position, and lateral position.

[0147] Optionally, the current planning time is t, the planning step size is Δt, and the vehicle's longitudinal position in the Frenet coordinate system is s. t The vehicle speed is v t .

[0148]

[0149] In the formula, acc_cmd is the target acceleration of the vehicle; v_cruise is the cruise speed set by the vehicle; and c_des is the acceleration planning time. The value of c_des may change with the planning time.

[0150] The target speed of the vehicle after one planning step is

[0151] v_cmd t+Δt =v t +acc_cmd*Δ t

[0152] When v_cmd t+Δt > v_cruise, v_cmd t+Δt =v_cruise, acc_cmd=0

[0153] The speed of the vehicle after one planned step is

[0154] v t+Δt =(1τ)*v t +τ*v_cmdt+Δt

[0155] In the formula, τ is the first-order hysteresis coefficient.

[0156] The longitudinal position of the vehicle after one planned step is

[0157]

[0158] The lateral position of the vehicle after one planned step is

[0159] l t+Δt =(1τ)*l t +τ*l_des

[0160] In the formula, l_des is the second lateral planning distance, and the value of l_des may change with the planning time.

[0161] Different acceleration planning times c_des take different values

[0162] [c_des1 c_des2 c_des3 … c_des q ]

[0163] For times t1, t2, t3, t4, ..., t n The values ​​of l_des are generated as shown in the parameter matrix below, with a planning step size between each time step.

[0164]

[0165] At any given moment, there are p possible parameter values, so a total of p can be generated. n The strategy for determining the value of l_des.

[0166] For a certain strategy at a certain time t, l_des t The value is determined as follows, assuming t is located at t k-1 To t k Between,

[0167]

[0168] x, y∈1,2,3,4,…p.

[0169] The strategies for choosing the values ​​of c_des in q ways and p n By permuting and combining the various values ​​of l_des, multiple cruise planning strategies can be obtained. Each cruise planning strategy includes times t1, t2, t3, t4, ..., t n The corresponding vehicle speed, longitudinal position, and lateral position, respectively.

[0170] For each cruise planning strategy, the cost parameters for each moment are calculated based on the vehicle's speed, longitudinal position, and lateral position at each time point:

[0171] [c t0 c t1 c t2 … c tn ]

[0172] t0 = t, tn = t + n, t k -t k-1 =Δt

[0173] c tk The cost of a certain planning step size.

[0174] And further calculate the total cost of each cruise planning strategy:

[0175] c tk =∑(c t0 +c t1 +c t2 +c t3 +…+c tn )

[0176] c tk The smallest cruise planning strategy is used as the second planning strategy.

[0177] In this embodiment, multiple sets of second planning parameters are obtained by arranging and combining multiple acceleration planning times and multiple second lateral planning distances; multiple consecutive planning steps are determined within a preset planning time, and multiple sets of second planning parameters are configured for each planning step; based on the multiple sets of second planning parameters corresponding to the vehicle at each planning step, multiple cruise planning strategies are obtained by arranging and combining them according to the temporal relationship of each planning step. Each cruise planning strategy contains multiple consecutive planning steps obtained within a preset planning time, and each planning step corresponds to one set of second planning parameters; based on the second planning parameters corresponding to each planning step in each cruise planning strategy, the cost parameters corresponding to each planning step in the cruise planning strategy are calculated, and the sum of the cost parameters corresponding to each cruise planning strategy is further calculated; the cruise planning strategy with the smallest sum of cost parameters is taken as the second planning strategy. This allows for the simultaneous generation of multiple cruise planning strategies, equivalent to generating multiple planned driving trajectories, and selecting the optimal planned driving trajectory as the final second planning strategy, thus improving the safety of autonomous driving.

[0178] In one embodiment, an autonomous driving control method includes:

[0179] The vehicle's electronic equipment establishes a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; in the Frenet coordinate system, the obstacle closest to the vehicle is taken as the target obstacle.

[0180] The vehicle-mounted electronic equipment acquires vehicle feature information and obstacle feature information of the target obstacle; the vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and the obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system.

[0181] Based on obstacle and vehicle characteristics, the onboard electronic equipment selects either an adaptive planning strategy mode or a cruise planning strategy mode.

[0182] Adaptive planning strategy pattern:

[0183] The vehicle-mounted electronic equipment obtains the longitudinal distance based on the initial longitudinal position and the longitudinal position of the obstacle, and obtains the lateral spacing based on the lateral position of the obstacle; if the longitudinal distance is less than the minimum distance threshold and the lateral spacing is less than the lane width threshold, it obtains multiple longitudinal planning time distances and multiple first lateral planning distances.

[0184] The onboard electronic equipment arranges and combines multiple longitudinal planning time intervals and multiple first lateral planning distances to obtain multiple sets of first planning parameters; determines multiple consecutive planning steps within a preset planning time, and configures multiple sets of first planning parameters for each planning step; based on the multiple sets of first planning parameters corresponding to each planning step, arranges and combines them according to the temporal relationship of each planning step to obtain multiple adaptive planning strategies. Each adaptive planning strategy contains multiple consecutive planning steps acquired within the preset planning time, and each planning step corresponds to one set of first planning parameters; based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, calculates the cost parameter corresponding to each planning step in the adaptive planning strategy, and further calculates the sum of the cost parameters corresponding to each adaptive planning strategy; the adaptive planning strategy with the smallest sum of cost parameters is taken as the first planning strategy. The vehicle's autonomous driving is controlled according to the first planning strategy.

[0185] Cruise planning strategy mode:

[0186] The vehicle electronic equipment obtains the longitudinal distance based on the initial longitudinal position and the longitudinal position of the obstacle, and obtains the lateral distance based on the lateral position of the obstacle; if the longitudinal distance is not less than the minimum distance threshold, or the lateral distance is not less than the lane width threshold, it obtains multiple acceleration planning times and multiple second lateral planning distances.

[0187] The onboard electronic equipment arranges and combines multiple acceleration planning times and multiple second lateral planning distances to obtain multiple sets of second planning parameters; it determines multiple consecutive planning steps within a preset planning time, and configures multiple sets of second planning parameters for each planning step; based on the multiple sets of second planning parameters corresponding to each planning step, it arranges and combines them according to the temporal relationship of each planning step to obtain multiple cruise planning strategies. Each cruise planning strategy contains multiple consecutive planning steps acquired within a preset planning time, and each planning step corresponds to one set of second planning parameters; based on the second planning parameters corresponding to each planning step in each cruise planning strategy, it calculates the cost parameter corresponding to each planning step in the cruise planning strategy, and further calculates the sum of the cost parameters corresponding to each cruise planning strategy; the cruise planning strategy with the smallest sum of cost parameters is taken as the second planning strategy. The vehicle's autonomous driving is controlled according to the second planning strategy.

[0188] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0189] Based on the same inventive concept, this application also provides an autonomous driving control device for implementing the aforementioned autonomous driving control method. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the autonomous driving control device provided below can be found in the limitations of the autonomous driving control method described above, and will not be repeated here.

[0190] In one embodiment, such as Figure 6 As shown, an autonomous driving control device 600 is provided, including: an obstacle detection module 601, a feature detection module 602, a parameter generation module 603, and a driving planning module 604, wherein:

[0191] The obstacle detection module 601 is used to determine the target obstacle in the current environment of the vehicle.

[0192] The feature detection module 602 is used to acquire vehicle feature information of the vehicle and obstacle feature information of the target obstacle.

[0193] The parameter generation module 603 is used to obtain the longitudinal planning time distance and the first lateral planning distance if the obstacle feature information meets the preset conditions relative to the vehicle feature information.

[0194] The driving planning module 604 is used to generate a first planning strategy based on vehicle feature information, obstacle feature information, longitudinal planning time distance and first lateral planning distance, and control the autonomous driving of the vehicle according to the first planning strategy.

[0195] In one embodiment, the obstacle detection module 601 is further configured to establish a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; in the Frenet coordinate system, the obstacle closest to the vehicle is taken as the target obstacle.

[0196] In one embodiment, the feature detection module 602 is further configured to acquire vehicle feature information of the vehicle and obstacle feature information of the target obstacle. The vehicle feature information includes the vehicle's initial longitudinal and lateral positions in the Frenet coordinate system, and the obstacle feature information includes the target obstacle's longitudinal and lateral positions in the Frenet coordinate system.

[0197] In one embodiment, the parameter generation module 603 is further configured to obtain the longitudinal distance based on the initial longitudinal position and the longitudinal position of the obstacle, and obtain the lateral spacing based on the lateral position of the obstacle; if the longitudinal distance is less than the minimum distance threshold and the lateral spacing is less than the lane width threshold, obtain multiple longitudinal planning time distances and multiple first lateral planning distances.

[0198] In one embodiment, the driving planning module 604 is further configured to: arrange and combine multiple longitudinal planning time intervals and multiple first lateral planning distances to obtain multiple sets of first planning parameters; determine multiple consecutive planning steps within a preset planning time, and configure multiple sets of first planning parameters for each planning step; based on the multiple sets of first planning parameters corresponding to the vehicle at each planning step, arrange and combine them according to the temporal relationship of each planning step to obtain multiple adaptive planning strategies, wherein each adaptive planning strategy contains multiple consecutive planning steps obtained within a preset planning time, and each planning step corresponds to one set of first planning parameters; calculate the cost parameters corresponding to each planning step in each adaptive planning strategy based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, and further calculate the sum of cost parameters corresponding to each adaptive planning strategy; and select the adaptive planning strategy with the smallest sum of cost parameters as the first planning strategy.

[0199] In one embodiment, the parameter generation module 603 is further configured to obtain the acceleration planning time and the second lateral planning distance if the obstacle feature information does not meet the preset conditions relative to the vehicle feature information.

[0200] The driving planning module 604 is used to generate a second planning strategy based on vehicle characteristic information, acceleration planning time, and second lateral planning distance, and to control the autonomous driving of the vehicle according to the second planning strategy.

[0201] In one embodiment, the parameter generation module 603 is further configured to obtain the longitudinal distance between vehicles based on the initial longitudinal position and the longitudinal position of the obstacle, and to obtain the lateral spacing based on the lateral position of the obstacle; if the longitudinal distance between vehicles is not less than the minimum distance threshold, or the lateral spacing is not less than the lane width threshold, to obtain multiple acceleration planning times and multiple second lateral planning distances.

[0202] In one embodiment, the driving planning module 604 is used to arrange and combine multiple acceleration planning times and multiple second lateral planning distances to obtain multiple sets of second planning parameters; determine multiple consecutive planning steps within a preset planning time, and configure multiple sets of second planning parameters for each planning step; based on the multiple sets of second planning parameters corresponding to the vehicle at each planning step, arrange and combine them according to the temporal relationship of each planning step to obtain multiple cruise planning strategies, wherein the cruise planning strategy includes multiple consecutive planning steps obtained within the preset planning time, and each planning step corresponds to one set of second planning parameters; based on the second planning parameters corresponding to each planning step in each cruise planning strategy, calculate the cost parameter corresponding to each planning step in the cruise planning strategy, and further calculate the sum of cost parameters corresponding to each cruise planning strategy; and select the cruise planning strategy with the smallest sum of cost parameters as the second planning strategy.

[0203] Each module in the aforementioned autonomous driving control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0204] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores vehicle characteristic information, obstacle characteristic information data, longitudinal planning time intervals, first lateral planning distances, acceleration planning time, and second lateral planning distances. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an autonomous driving control method.

[0205] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0206] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: determining a target obstacle in the current environment of the vehicle; acquiring vehicle feature information of the vehicle and acquiring obstacle feature information of the target obstacle; if the obstacle feature information satisfies a preset condition relative to the vehicle feature information, acquiring a longitudinal planning time distance and a first lateral planning distance; generating a first planning strategy based on the vehicle feature information, obstacle feature information, longitudinal planning time distance, and first lateral planning distance, and controlling the autonomous driving of the vehicle based on the first planning strategy.

[0207] In one embodiment, when the processor executes the computer program, it also performs the following steps: establishing a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; and in the Frenet coordinate system, identifying the obstacle closest to the vehicle as the target obstacle.

[0208] In one embodiment, when the processor executes the computer program, it further implements the following steps: vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system; longitudinal distance is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and lateral spacing is obtained based on the lateral position of the obstacle; if the longitudinal distance is less than the minimum distance threshold and the lateral spacing is less than the lane width threshold, multiple longitudinal planning time distances and multiple first lateral planning distances are obtained.

[0209] In one embodiment, when the processor executes the computer program, it further performs the following steps: permuting and combining multiple longitudinal planning time intervals and multiple first lateral planning distances to obtain multiple sets of first planning parameters; determining multiple consecutive planning steps within a preset planning time, and configuring multiple sets of first planning parameters for each planning step; based on the multiple sets of first planning parameters corresponding to the vehicle at each planning step, permuting and combining them according to the temporal relationship of each planning step to obtain multiple adaptive planning strategies, wherein each adaptive planning strategy contains multiple consecutive planning steps obtained within a preset planning time, and each planning step corresponds to one set of first planning parameters; based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, calculating the cost parameter corresponding to each planning step in the adaptive planning strategy, and further calculating the sum of cost parameters corresponding to each adaptive planning strategy; and selecting the adaptive planning strategy with the smallest sum of cost parameters as the first planning strategy.

[0210] In one embodiment, when the processor executes the computer program, it further performs the following steps: if the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, it obtains the acceleration planning time and the second lateral planning distance; generates a second planning strategy based on the vehicle feature information, the acceleration planning time, and the second lateral planning distance; and controls the autonomous driving of the vehicle based on the second planning strategy.

[0211] In one embodiment, when the processor executes the computer program, it further implements the following steps: vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system; longitudinal distance is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and lateral spacing is obtained based on the lateral position of the obstacle; if the longitudinal distance is not less than the minimum distance threshold, or the lateral spacing is not less than the lane width threshold, multiple acceleration planning times and multiple second lateral planning distances are obtained.

[0212] In one embodiment, when the processor executes the computer program, it further performs the following steps: permuting and combining multiple acceleration planning times and multiple second lateral planning distances to obtain multiple sets of second planning parameters; determining multiple consecutive planning steps within a preset planning duration, and configuring multiple sets of second planning parameters for each planning step; based on the multiple sets of second planning parameters corresponding to the vehicle at each planning step, permuting and combining them according to the temporal relationship of each planning step to obtain multiple cruise planning strategies, wherein each cruise planning strategy contains multiple consecutive planning steps acquired within a preset planning duration, and each planning step corresponds to one set of second planning parameters; based on the second planning parameters corresponding to each planning step in each cruise planning strategy, calculating the cost parameter corresponding to each planning step in the cruise planning strategy, and further calculating the sum of cost parameters corresponding to each cruise planning strategy; and selecting the cruise planning strategy with the smallest sum of cost parameters as the second planning strategy.

[0213] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it performs the following steps: determining a target obstacle in the current environment of the vehicle; acquiring vehicle feature information of the vehicle and acquiring obstacle feature information of the target obstacle; if the obstacle feature information satisfies a preset condition relative to the vehicle feature information, acquiring a longitudinal planning time distance and a first lateral planning distance; generating a first planning strategy based on the vehicle feature information, obstacle feature information, longitudinal planning time distance and the first lateral planning distance, and controlling the autonomous driving of the vehicle based on the first planning strategy.

[0214] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: establishing a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; and in the Frenet coordinate system, identifying the obstacle closest to the vehicle as the target obstacle.

[0215] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system; longitudinal distance is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and lateral spacing is obtained based on the lateral position of the obstacle; if the longitudinal distance is less than the minimum distance threshold and the lateral spacing is less than the lane width threshold, multiple longitudinal planning time distances and multiple first lateral planning distances are obtained.

[0216] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: permuting and combining multiple longitudinal planning time intervals and multiple first lateral planning distances to obtain multiple sets of first planning parameters; determining multiple consecutive planning steps within a preset planning time, and configuring multiple sets of first planning parameters for each planning step; based on the multiple sets of first planning parameters corresponding to the vehicle at each planning step, permuting and combining them according to the temporal relationship of each planning step to obtain multiple adaptive planning strategies, wherein each adaptive planning strategy contains multiple consecutive planning steps obtained within a preset planning time, and each planning step corresponds to one set of first planning parameters; based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, calculating the cost parameter corresponding to each planning step in the adaptive planning strategy, and further calculating the sum of cost parameters corresponding to each adaptive planning strategy; and selecting the adaptive planning strategy with the smallest sum of cost parameters as the first planning strategy.

[0217] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then the acceleration planning time and the second lateral planning distance are obtained; a second planning strategy is generated based on the vehicle feature information, the acceleration planning time and the second lateral planning distance, and the autonomous driving of the vehicle is controlled according to the second planning strategy.

[0218] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system; longitudinal distance is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and lateral spacing is obtained based on the lateral position of the obstacle; if the longitudinal distance is not less than the minimum distance threshold, or the lateral spacing is not less than the lane width threshold, multiple acceleration planning times and multiple second lateral planning distances are obtained.

[0219] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: permuting and combining multiple acceleration planning times and multiple second lateral planning distances to obtain multiple sets of second planning parameters; determining multiple consecutive planning steps within a preset planning duration, and configuring multiple sets of second planning parameters for each planning step; based on the multiple sets of second planning parameters corresponding to the vehicle at each planning step, permuting and combining them according to the temporal relationship of each planning step to obtain multiple cruise planning strategies, wherein each cruise planning strategy contains multiple consecutive planning steps acquired within a preset planning duration, and each planning step corresponds to one set of second planning parameters; based on the second planning parameters corresponding to each planning step in each cruise planning strategy, calculating the cost parameter corresponding to each planning step in the cruise planning strategy, and further calculating the sum of the cost parameters corresponding to each cruise planning strategy; and selecting the cruise planning strategy with the smallest sum of cost parameters as the second planning strategy.

[0220] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: determining a target obstacle in the current environment of the vehicle; acquiring vehicle feature information of the vehicle and acquiring obstacle feature information of the target obstacle; if the obstacle feature information satisfies a preset condition relative to the vehicle feature information, acquiring a longitudinal planning time distance and a first lateral planning distance; generating a first planning strategy based on the vehicle feature information, obstacle feature information, longitudinal planning time distance, and first lateral planning distance, and controlling the autonomous driving of the vehicle based on the first planning strategy.

[0221] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: establishing a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; and in the Frenet coordinate system, identifying the obstacle closest to the vehicle as the target obstacle.

[0222] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system; longitudinal distance is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and lateral spacing is obtained based on the lateral position of the obstacle; if the longitudinal distance is less than the minimum distance threshold and the lateral spacing is less than the lane width threshold, multiple longitudinal planning time distances and multiple first lateral planning distances are obtained.

[0223] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: permuting and combining multiple longitudinal planning time intervals and multiple first lateral planning distances to obtain multiple sets of first planning parameters; determining multiple consecutive planning steps within a preset planning time, and configuring multiple sets of first planning parameters for each planning step; based on the multiple sets of first planning parameters corresponding to the vehicle at each planning step, permuting and combining them according to the temporal relationship of each planning step to obtain multiple adaptive planning strategies, wherein each adaptive planning strategy contains multiple consecutive planning steps obtained within a preset planning time, and each planning step corresponds to one set of first planning parameters; based on the first planning parameters corresponding to each planning step in each adaptive planning strategy, calculating the cost parameter corresponding to each planning step in the adaptive planning strategy, and further calculating the sum of cost parameters corresponding to each adaptive planning strategy; and selecting the adaptive planning strategy with the smallest sum of cost parameters as the first planning strategy.

[0224] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: if the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then the acceleration planning time and the second lateral planning distance are obtained; a second planning strategy is generated based on the vehicle feature information, the acceleration planning time and the second lateral planning distance, and the autonomous driving of the vehicle is controlled according to the second planning strategy.

[0225] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system; longitudinal distance is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and lateral spacing is obtained based on the lateral position of the obstacle; if the longitudinal distance is not less than the minimum distance threshold, or the lateral spacing is not less than the lane width threshold, multiple acceleration planning times and multiple second lateral planning distances are obtained.

[0226] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: permuting and combining multiple acceleration planning times and multiple second lateral planning distances to obtain multiple sets of second planning parameters; determining multiple consecutive planning steps within a preset planning duration, and configuring multiple sets of second planning parameters for each planning step; based on the multiple sets of second planning parameters corresponding to the vehicle at each planning step, permuting and combining them according to the temporal relationship of each planning step to obtain multiple cruise planning strategies, wherein each cruise planning strategy contains multiple consecutive planning steps acquired within a preset planning duration, and each planning step corresponds to one set of second planning parameters; based on the second planning parameters corresponding to each planning step in each cruise planning strategy, calculating the cost parameter corresponding to each planning step in the cruise planning strategy, and further calculating the sum of the cost parameters corresponding to each cruise planning strategy; and selecting the cruise planning strategy with the smallest sum of cost parameters as the second planning strategy.

[0227] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0228] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0229] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0230] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An automatic driving control method, characterized in that, The method includes: Identify the target obstacles in the vehicle's current environment; Obtain vehicle feature information of the vehicle and obstacle feature information of the target obstacle; Compare obstacle feature information and vehicle feature information, determine the distance between the vehicle and the target obstacle based on the comparison result, and determine the distance between the two sides of the target obstacle. If the distance between the vehicle and the target obstacle and the distance between the two sides of the target obstacle both meet the preset conditions, it is determined that the vehicle cannot pass or go around the target obstacle. Then, multiple longitudinal planning time distances and multiple first lateral planning distances are obtained. Each longitudinal planning time distance is a selectable safe distance. Will The strategy for determining the value of the longitudinal planning time interval and By arranging and combining the first lateral programming distance value strategy according to the same time interval, multiple adaptive programming strategies can be obtained, each of which includes time intervals. , , , , ..., The corresponding vehicle speed, longitudinal position, and lateral position are respectively, where, The steps for determining the value strategy of the longitudinal programming time interval are as follows: For the longitudinal programming time interval, there are m parameter values ​​that can be selected at each time point, thus generating a total of m possible values. Longitudinal planning time interval; The steps for determining the value strategy of the first lateral programming distance are as follows: For the first lateral programming distance, there are p parameter values ​​to choose from at each time step, thus generating a total of p possible values. The first horizontal planning distance; For each adaptive planning strategy, the cost parameters at each time step are calculated based on the vehicle speed, longitudinal position, and lateral position at each time step. The cost parameters at each time step are then summed to obtain the total cost of the adaptive planning strategy. The adaptive planning strategy with the minimum total cost is selected as the first planning strategy. The first planning strategy is used to control the vehicle to follow the target obstacle within a preset time period in the future. The vehicle is controlled to drive automatically according to the first planning strategy.

2. The method according to claim 1, characterized in that, The process of determining the target obstacle in the vehicle's current environment includes: Establish a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; In the Frenet coordinate system, the obstacle closest to the vehicle is taken as the target obstacle.

3. The method according to claim 2, characterized in that, The vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and the obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system. The method further includes: The longitudinal distance between vehicles is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and the lateral distance is obtained based on the lateral position of the obstacle. If the longitudinal vehicle distance is less than the minimum vehicle distance threshold and the lateral spacing is less than the lane width threshold, multiple longitudinal planning time distances and multiple first lateral planning distances are obtained.

4. The method according to claim 2, characterized in that, The method further includes: If the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then the acceleration planning time and the second lateral planning distance are obtained. A second planning strategy is generated based on the vehicle feature information, the acceleration planning time, and the second lateral planning distance, and the autonomous driving of the vehicle is controlled according to the second planning strategy.

5. The method according to claim 4, characterized in that, The vehicle feature information includes the initial longitudinal position and initial lateral position of the vehicle in the Frenet coordinate system, and the obstacle feature information includes the longitudinal position and lateral position of the target obstacle in the Frenet coordinate system. If the obstacle feature information does not meet the preset conditions relative to the vehicle feature information, then the acceleration planning time and the second lateral planning distance are obtained, including: The longitudinal distance between vehicles is obtained based on the initial longitudinal position and the longitudinal position of the obstacle, and the lateral distance is obtained based on the lateral position of the obstacle. If the longitudinal vehicle distance is not less than the minimum vehicle distance threshold, or the lateral spacing is not less than the lane width threshold, multiple acceleration planning times and multiple second lateral planning distances are obtained.

6. The method according to claim 5, characterized in that, The step of generating a second planning strategy based on the vehicle feature information, the acceleration planning time, and the second lateral planning distance includes: The multiple accelerated planning times and the multiple second lateral planning distances are arranged and combined to obtain multiple sets of second planning parameters; Determine multiple consecutive planning steps within a preset planning time period, and configure the multiple sets of second planning parameters for each planning step; Based on the multiple sets of second planning parameters corresponding to each planning step of the vehicle, and based on the temporal relationship of each planning step, multiple cruise planning strategies are obtained by arranging and combining them. The cruise planning strategy includes multiple planning steps continuously acquired within the preset planning time, and each planning step corresponds to one set of second planning parameters. Based on the second planning parameters corresponding to each planning step in each cruise planning strategy, calculate the cost parameters corresponding to each planning step in the cruise planning strategy, and further calculate the cost parameters corresponding to each cruise planning strategy. The cruise planning strategy that minimizes the cost parameters is taken as the second planning strategy.

7. An automatic driving control device, characterized in that, The device includes: The obstacle detection module is used to identify target obstacles in the vehicle's current environment. The feature detection module is used to acquire vehicle feature information of the vehicle and obstacle feature information of the target obstacle; The parameter generation module is used to compare obstacle feature information and vehicle feature information, determine the distance between the vehicle and the target obstacle based on the comparison result, and determine the distance between the two sides of the target obstacle. If the distance between the vehicle and the target obstacle and the distance between the two sides of the target obstacle both meet the preset conditions, it is determined that the vehicle cannot pass or go around the target obstacle. Then, multiple longitudinal planning time distances and multiple first lateral planning distances are obtained. Each longitudinal planning time distance is a selectable safe distance. The driving planning module is used to... The strategy for determining the value of the longitudinal planning time interval and By arranging and combining the first lateral programming distance value strategy according to the same time interval, multiple adaptive programming strategies can be obtained, each of which includes time intervals. , , , , ..., The corresponding vehicle speed, longitudinal position, and lateral position are respectively, where, The steps for determining the value strategy of the longitudinal programming time interval are as follows: For the longitudinal programming time interval, there are m parameter values ​​that can be selected at each time point, thus generating a total of m possible values. Longitudinal planning time interval; The steps for determining the value strategy of the first lateral programming distance are as follows: For the first lateral programming distance, there are p parameter values ​​to choose from at each time step, thus generating a total of p possible values. The first lateral planning distance is calculated; for each adaptive planning strategy, the cost parameters at each time step are calculated based on the vehicle speed, longitudinal position, and lateral position at each time step, and the cost parameters at each time step are further superimposed to obtain the total cost of the adaptive planning strategy; the adaptive planning strategy with the minimum total cost is selected as the first planning strategy; wherein, the first planning strategy is used to control the vehicle to follow the target obstacle within a preset time period in the future; the autonomous driving of the vehicle is controlled according to the first planning strategy.

8. The apparatus according to claim 7, characterized in that, The obstacle detection module is also used to establish a Frenet coordinate system based on the lane centerline in the current environment of the vehicle; in the Frenet coordinate system, the obstacle closest to the vehicle is taken as the target obstacle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images