Travelling control method, travelling control apparatus, and intelligent driving vehicle

Abstract

The present disclosure relates to the field of computers, and particularly relates to the field of intelligent driving. Provided are a travelling control method, a travelling control apparatus, and an intelligent driving vehicle. The travelling control method comprises: in response to an emergency braking decision, determining trajectory points of an intelligent driving vehicle and trajectory points of a target, which triggers the emergency braking decision, within a specified future time period; on the basis of the trajectory points of the intelligent driving vehicle and the trajectory points of the target, which triggers the emergency braking decision, within the specified future time period, determining whether there is a conflict risk between the target and the intelligent driving vehicle; and when it is determined that there is a conflict risk, maintaining the emergency braking decision, and when it is determined that there is no conflict risk, canceling the emergency braking decision. Subsequent to an emergency braking decision, an additional trajectory-based emergency braking decision filtering method is introduced to maintain or cancel the emergency braking decision, thereby avoiding a decision conflict between an AEB system and a PNC system, reducing unintended triggering behaviors of emergency braking of the AEB system, and improving the operating efficiency of an intelligent driving vehicle.

Description

Driving control methods, driving control devices, and intelligent driving vehicles

[0001] Cross-references to related applications

[0002] This application is based on and claims priority to CN application No. 202411959843.4, filed on December 27, 2024, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates to the field of computers, and more particularly to the field of intelligent driving, and especially to driving control methods, driving control devices and intelligent driving vehicles. Background Technology

[0004] Intelligent driving vehicles are used to automatically transport people or goods from one location to another. They collect environmental information through sensors on the vehicle and complete the automated transport. Intelligent driving vehicles controlled by autonomous driving technology greatly improve the convenience of production and daily life, and save labor costs.

[0005] The active safety module is a crucial component of an autonomous driving system. Its Automatic Emergency Braking (AEB) system perceives and makes decisions about the driving environment, issuing emergency braking commands to the vehicle chassis in dangerous situations to ensure vehicle safety. The autonomous driving system also includes a Planning and Control (PNC) system, responsible for planning the vehicle's path and controlling its movements.

[0006] AEB (Autonomous Emergency Braking) and PNC (Parking Control) systems may have conflicting decision-making issues. For example, the AEB system might determine, based on current environmental information, that there is a risk of collision between the vehicle and a target, necessitating emergency braking; however, the PNC system might determine that there is no risk of collision and that obstacle avoidance can maintain normal driving. In this situation, the emergency braking executed by the AEB system is a false trigger, as it was not originally necessary, significantly impacting the operational efficiency of the autonomous vehicle. Summary of the Invention

[0007] This disclosure provides a driving control method in some embodiments, including: in response to an emergency braking decision, determining the trajectory points of an intelligent driving vehicle and a target that triggered the emergency braking decision within a specified future time period; determining whether there is a conflict risk between the target and the intelligent driving vehicle based on the trajectory points of the intelligent driving vehicle and the target that triggered the emergency braking decision within the specified future time period; maintaining the emergency braking decision if a conflict risk is determined, and canceling the emergency braking decision if no conflict risk is determined.

[0008] In some embodiments, determining whether there is a risk of conflict between the target and the intelligent driving vehicle based on the trajectory points of the intelligent driving vehicle and the target that triggers the emergency braking decision within a specified time period in the future includes: if the trajectory point of the target that triggers the emergency braking decision at any time within the specified time period is within the vehicle frame of the intelligent driving vehicle's trajectory point at that time, it is determined that there is a risk of conflict between the target and the intelligent driving vehicle.

[0009] In some embodiments, determining whether there is a conflict risk between the target and the intelligent driving vehicle based on the trajectory points of the intelligent driving vehicle and the target that triggers the emergency braking decision within a specified time period in the future includes: if the line connecting the trajectory points of the target that triggers the emergency braking decision within a specified time period intersects with the line connecting the trajectory points of the intelligent driving vehicle within a specified time period in the future, it is determined that there is a conflict risk between the target and the intelligent driving vehicle.

[0010] In some embodiments, determining whether there is a conflict risk between the intelligent driving vehicle and the target triggering the emergency braking decision based on the trajectory points of the intelligent driving vehicle and the target triggering the emergency braking decision within a specified time period in the future includes: determining whether the trajectory point of the target triggering the emergency braking decision at any time in the specified time period is within the vehicle frame of the intelligent driving vehicle's trajectory point at that time; if the determination result is yes, determining that there is a conflict risk between the target and the intelligent driving vehicle; if the determination result is no, determining whether the line connecting the trajectory points of the target triggering the emergency braking decision within the specified time period intersects with the line connecting the trajectory points of the intelligent driving vehicle within the specified time period in the future; if the determination result is intersection, determining that there is a conflict risk between the target and the intelligent driving vehicle.

[0011] In some embodiments, determining whether there is a conflict risk between the intelligent driving vehicle and the target that triggered the emergency braking decision within a specified future time period, based on the trajectory points of the intelligent driving vehicle and the target within a specified future time period, includes: if no conflict risk is determined based on the trajectory points, then making another emergency braking determination based on the motion state information of the last trajectory point of the intelligent driving vehicle and the target that triggered the emergency braking decision within the specified future time period; if the result of the second determination is still that emergency braking is required, then it is determined that there is a conflict risk between the target and the intelligent driving vehicle; if the result of the second determination is that emergency braking is not required, then it is determined that there is no conflict risk between the target and the intelligent driving vehicle.

[0012] In some embodiments, the determination to perform emergency braking again includes: determining whether there is a risk of conflict between the target and the intelligent driving vehicle based on the target's position, velocity, and acceleration in the intelligent driving vehicle coordinate system at the last trajectory point, as well as the speed and braking attributes of the intelligent driving vehicle; and determining that emergency braking needs to be performed if a risk of conflict is determined.

[0013] In some embodiments, determining whether there is a risk of conflict between the target and the autonomous vehicle includes: determining the relative velocity of the target relative to the autonomous vehicle at the last trajectory point, and determining whether the target is a candidate target for triggering emergency braking based on whether the ray of the target in the relative velocity direction crosses the safe driving range of the autonomous vehicle; if the target is a candidate target for triggering emergency braking, determining whether there is a risk of conflict between the target and the autonomous vehicle based on the position, velocity, and acceleration of the target in the coordinate system of the autonomous vehicle at the last trajectory point, as well as the speed and braking attributes of the autonomous vehicle.

[0014] In some embodiments, determining whether there is a risk of conflict between the target and the autonomous vehicle includes: determining the braking distance of the target and the braking distance of the autonomous vehicle based on the radial components of the target's velocity and acceleration at the last trajectory point, as well as the speed and braking attributes of the autonomous vehicle; determining whether there is a risk of conflict between the target and the autonomous vehicle in the radial direction by comparing the difference between the braking distance of the autonomous vehicle and the braking distance of the target with the radial distance between the target and the autonomous vehicle, wherein the radial distance between the target and the autonomous vehicle is determined based on the radial component of the target's position in the autonomous vehicle's coordinate system.

[0015] In some embodiments, determining whether there is a risk of conflict between the target and the intelligent driving vehicle includes: determining whether the target will move into the width range of the intelligent driving vehicle in the lateral direction based on the target's position, velocity, and lateral acceleration component in the intelligent driving vehicle coordinate system at the last trajectory point and the speed of the intelligent driving vehicle; and determining whether there is a risk of conflict between the target and the intelligent driving vehicle in the lateral direction based on whether the target will move into the width range of the intelligent driving vehicle in the lateral direction.

[0016] Some embodiments of this disclosure provide a driving control device, including: a memory; and a processor coupled to the memory, the processor being configured to execute a driving control method based on instructions stored in the memory.

[0017] Some embodiments of this disclosure provide an intelligent driving vehicle, including: a driving control device configured to perform a driving control method.

[0018] Some embodiments of this disclosure provide a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of a driving control method.

[0019] Some embodiments of this disclosure provide a computer program product including computer instructions that, when executed by a processor, implement the steps of a driving control method. Attached Figure Description

[0020] The accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. This disclosure can be more clearly understood from the following detailed description with reference to the accompanying drawings.

[0021] Obviously, the accompanying drawings described below are merely some embodiments of this disclosure. Those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0022] Figure 1 shows a schematic diagram of the electrical architecture of an intelligent (autonomous) driving vehicle according to some embodiments of the present disclosure.

[0023] Figure 2 shows a schematic diagram of the external structure of an intelligent (autonomous) driving vehicle according to some embodiments of the present disclosure.

[0024] Figure 3 shows a schematic diagram of a neural network for processing point clouds according to some embodiments of the present disclosure.

[0025] Figure 4 illustrates a schematic diagram of decision-making conflicts between the AEB system and the PNC system in some embodiments of this disclosure.

[0026] Figure 5 shows a schematic flowchart of a driving control method according to some embodiments of the present disclosure.

[0027] Figure 6 shows a schematic diagram of a collision risk determination method based on trajectory points according to some embodiments of the present disclosure.

[0028] Figure 7 shows a schematic diagram of a trajectory-based conflict risk determination method according to some embodiments of the present disclosure.

[0029] Figure 8 illustrates a schematic diagram of a conflict risk determination scenario based on emergency braking reassessment according to some embodiments of this disclosure.

[0030] Figure 9 shows a schematic flowchart of a driving control method according to some embodiments of the present disclosure.

[0031] Figure 10 shows a flowchart illustrating an emergency braking decision-making method according to some embodiments of the present disclosure.

[0032] Figure 11 shows a schematic diagram illustrating the determination of whether a target is a candidate target for triggering emergency braking, according to some embodiments of the present disclosure.

[0033] Figures 12, 13 and 14 illustrate schematic diagrams of determining the braking distance of a target and the braking distance of an intelligent driving vehicle under different conditions according to some embodiments of the present disclosure.

[0034] Figure 15 shows a schematic diagram of the structure of a driving control device according to some embodiments of the present disclosure. Detailed Implementation

[0035] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0036] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0037] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0038] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0039] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0040] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0041] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0042] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0043] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0044] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0045] Furthermore, to avoid obscuring this disclosure with unnecessary detail, only processing steps and / or apparatus structures closely related to at least the solutions according to this disclosure are shown in the accompanying drawings, while other details not closely related to this disclosure are omitted. It should also be noted that similar reference numerals and letters in the drawings indicate similar items, and therefore once an item is defined in one drawing, it need not be discussed again in subsequent drawings.

[0046] To address the decision-making conflict between the AEB (Autonomous Emergency Braking) system and the PNC (Parking Control) system, both systems respond correctly based on their respective information, making further optimization difficult. This disclosure proposes an additional trajectory-based emergency braking decision filtering method after the emergency braking decision is made. This method maintains or cancels the emergency braking decision, avoiding decision-making conflicts between the AEB and PNC systems, reducing false triggering of emergency braking by the AEB system, and improving the operational efficiency of the autonomous vehicle.

[0047] Figure 1 shows a schematic diagram of the electrical architecture of an intelligent (autonomous) driving vehicle according to some embodiments of the present disclosure.

[0048] As shown in Figure 1, the intelligent (autonomous) driving vehicle 100 of this embodiment includes, for example, an autonomous driving module 110 and a chassis module 120. Depending on the needs, it may also include a remote monitoring and streaming module 130 and a cargo box module 140. For example, vehicles with remote monitoring requirements include the remote monitoring and streaming module 130; vehicles without remote monitoring requirements may omit it. Similarly, vehicles with cargo-carrying requirements (such as trucks) include the cargo box module 140; vehicles without cargo-carrying requirements (such as passenger cars) may omit it. The intelligent (autonomous) driving vehicle may be, for example, a driverless car, an unmanned delivery vehicle, or an unmanned vending vehicle.

[0049] The autonomous driving module 110 may include, as needed, one or more of the following: a central processing unit (Orin or Xavier module) 111, a traffic light recognition camera 112, a front camera 1131, a rear camera 1132, a left camera 1133, a right camera 1134, a LiDAR 114, a front blind spot radar 1151, a rear blind spot radar 1152, a left blind spot radar 1153, and a right blind spot radar 1154, a positioning module (such as BeiDou, GPS, etc.) 116, an inertial navigation unit 117, and a switch 118. Each camera can communicate with the autonomous driving module. To improve transmission speed and reduce wiring, GMSL (Gigabit Multimedia Serial Links) links can be used for communication. The central processing unit 111 can be implemented using a general-purpose central processing unit, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates, or transistors, etc. The central processing unit 111 can be configured for autonomous driving control.

[0050] The chassis module 120 may include, as needed, one or more of the following: battery 121, power management device 122, chassis controller 123, motor driver 124, drive motor 125, and communication module 126. Battery 121 provides power to the entire autonomous vehicle system. Battery 121 includes a main battery 1211 and a standby battery 1212. When the autonomous vehicle is running, the main battery 1211 powers each module of the autonomous vehicle. When the autonomous vehicle is in standby mode, the standby battery 1212 powers the central processing unit 111 and the communication module 126. The power management device 122 converts the output of battery 121 into different voltage levels usable by each module and controls power-on and power-off. The chassis controller 123 receives motion commands from the autonomous driving module 110 and controls the autonomous vehicle's steering, forward, reverse, and braking. The communication module 126 communicates with a backend server, enabling remote control of the autonomous vehicle by backend operators. The communication module 126 includes a cellular wireless communication device 1261 and a radio frequency communication device 1262. Cellular wireless communication device 1261 communicates using cellular wireless communication technology, such as 2G (second generation), 3G (third generation), 4G (fourth generation), or 5G (fifth generation) cellular wireless communication technology. Radio frequency communication device 1262 communicates using radio frequency communication technology.

[0051] The remote monitoring streaming module 130 may include, as needed, one or more of the following: a front monitoring camera 1311, a rear monitoring camera 1312, a left monitoring camera 1313, a right monitoring camera 1314, and a streaming module 132. The streaming module 132 transmits the video data captured by the monitoring cameras 1311-1314 to the backend server for viewing by backend operators.

[0052] The cargo box module 140 may include a cargo box 141 as needed, which is a cargo-carrying device for the autonomous vehicle. The cargo box module 140 also includes a display and interaction module 142 for interaction between the autonomous vehicle and the user. Users can perform operations such as picking up items, storing goods, and purchasing goods through the display and interaction module 142. The type of cargo box 141 can be changed according to actual needs. For example, in a logistics scenario, the cargo box may include multiple sub-boxes of different sizes, which can be used to load goods for delivery. In a retail scenario, the cargo box can be set as a transparent box so that users can see the products for sale.

[0053] Figure 2 shows a schematic diagram of the external structure of an intelligent (autonomous) driving vehicle according to some embodiments of the present disclosure. Figure 2 shows a schematic diagram of the external structure of an autonomous driving vehicle capable of carrying cargo. Autonomous driving vehicles with different functions can have different external structures. For example, the external structure of an autonomous driving vehicle carrying passengers can be referenced from that of a car. As shown in Figure 2, from the current perspective, the autonomous driving vehicle 200 includes a chassis 210, a cargo box 141, a display and interaction module 142, a right-side camera 1134, a lidar 114, a rear blind spot radar 1152, a left-side blind spot radar 1153, and a right-side blind spot radar 1154.

[0054] The active safety module of the intelligent driving vehicle in this disclosure uses lidar signals as input to perceive surrounding targets and their motion states. LiDAR is denser than millimeter-wave radar, can effectively perceive small targets, and has higher vertical resolution, enabling the separation of static obstacles from the background. Based on the scheme proposed in this disclosure, as described below with reference to Figure 3, the temporal lidar signals can be used to perceive the target's speed, acceleration, and category information. Furthermore, the speed signal predicted by the two-dimensional speed prediction map has high accuracy in both the radial and lateral directions, reflecting the target's true motion state and providing rich and high-quality upstream information for the active safety decisions of the autonomous driving system.

[0055] Figure 3 shows a schematic diagram of a neural network for processing point clouds according to some embodiments of the present disclosure. This point cloud processing neural network can exist in the product shape of a point cloud processing device. As shown in Figure 3, the point cloud processing neural network (point cloud processing device) includes: a feature extraction module 310, configured to extract features from the point cloud data of the current frame of the lidar to obtain a point cloud feature map of the current frame; a temporal fusion module 320, configured to perform temporal fusion processing on the point cloud feature map of the current frame and the fused feature map of the previous frame, that is, to concatenate the point cloud feature map of the current frame and the fused feature map of the previous frame and extract temporal features to obtain a fused feature map of the current frame; and a prediction module 330, configured to predict one or more of the target's velocity, acceleration, and category based on the fused feature map of the current frame to obtain a velocity prediction map, an acceleration prediction map, and a category prediction map.

[0056] The feature extraction module 310 includes, for example, a downsampling network, multiple residual networks, upsampling networks with different step sizes, and a stitching unit. The downsampling network downsamples the point cloud data of the current frame of the LiDAR, outputting a first feature map of the current frame. Multiple cascaded residual networks downsample the first feature map, outputting multiple second feature maps with different downsampling rates. Multiple upsampling networks with different step sizes upsample the multiple second feature maps with different downsampling rates, outputting multiple third feature maps of the same size. The stitching unit stitches together the multiple third feature maps to output the point cloud feature map of the current frame.

[0057] The following is an example of the feature extraction module 310. As shown in Figure 3, the point cloud information of the current frame (time T) is voxelized to form voxelized point cloud data, which serves as the input data. The input data is denoted as [H, W, D], where H, W, and D represent height, width, and depth, respectively. The input data first passes through a downsampling network with a stride of 2 to reduce the feature size and alleviate the computational burden of subsequent networks. The feature map output by the downsampling network is denoted as [H / 2, W / 2, C0], with the height and width reduced to half of their original values, and C0 representing the channel. The structure of the downsampling network is, for example, a convolutional layer with a stride of N (N = 2 in this example) (the convolutional layer performs downsampling), and includes a batch normalization layer and a ReLU (Rectified Linear Unit) activation function layer. Next, the data output by the downsampling network passes through four consecutive residual networks to extract deeper features. These four residual networks all have a convolution stride of, for example, 2, and output feature maps with downsampling rates of 4 / 8 / 16 / 32, denoted as [H / 4,W / 4,C1], [H / 8,W / 8,C2], [H / 16,W / 16,C3], and [H / 32,W / 32,C4], respectively. The height and width are reduced to 1 / 4, 1 / 8, 1 / 16, and 1 / 32 of their original values, respectively. C1, C2, C3, and C4 represent the channels. By introducing cross-layer connections, the input signal is directly added to the output of the residual network, making it easier for the network to propagate gradients during backpropagation, thus solving the gradient vanishing problem in deep network training. Subsequently, the four feature maps from these four residual networks are passed through upsampling networks with strides of 1 / 2 / 4 / 8, outputting four feature maps of the same size with a downsampling rate of 4, denoted as [H / 4, W / 4, C / 4]. The height and width are 1 / 4 of the original, where H, W, and C represent height, width, and channels, respectively. The structure of the upsampling network is, for example, a deconvolutional layer with a stride of N (N=2 in this example) (the deconvolutional layer performs upsampling), along with a batch normalization layer and a ReLU activation function layer. These four upsampled feature maps of the same size represent feature information at different network depths. Shallow features mainly focus on local details and low-level features of the image, which are usually closely related to the image's pixels, including fine-grained information such as color, texture, edges, and corners. Deep features focus on global and high-level features, representing more abstract and complex feature representations, which are usually related to the semantic information of the image. Finally, the multiple feature maps obtained after upsampling are concatenated along the channel dimension by the concatenation unit to obtain the point cloud feature map of the current frame, denoted as [H / 4, W / 4, C].

[0058] The temporal fusion module 320 includes, for example, a coordinate system alignment unit, a stitching unit, and a temporal fusion neural network, and may also include an upsampling network. The coordinate system alignment unit aligns the fused feature map of the previous frame to the coordinate system of the current frame based on the coordinate transformation matrix between the previous and current frames. The stitching unit stitches the aligned fused feature map of the previous frame with the point cloud feature map of the current frame, performing the stitching along the channel dimension. The temporal fusion neural network extracts temporal features from the stitched feature map to obtain the fused feature map of the current frame. The fused feature map of the current frame includes temporal information from all historical frames preceding the current frame, and the fused feature map of the previous frame includes temporal information from all historical frames preceding that previous frame. Specifically, the fused feature map of the initial frame is obtained by extracting temporal features from the point cloud feature map of the initial frame using the temporal fusion neural network. Based on this, through iteration, the fused feature maps of each frame can be obtained. By introducing temporal features, the target motion state can be better perceived. The upsampling network upsamples the fused feature map of the current frame to obtain a fused feature map with the same size as the point cloud data of the current frame.

[0059] The following is an example of the temporal fusion module 320. As shown in Figure 3, the fused feature map of the point cloud of the previous frame (time T-1) (size [H / 4, W / 4, C]) is distorted and aligned to the coordinate system of the current frame (time T) according to the coordinate transformation matrix between the two frames. Then, it is concatenated with the point cloud feature map of the current frame (size [H / 4, W / 4, C]) output by the feature extraction module 310 and input into the temporal fusion neural network. This network compares the point cloud features of the two frames, mines temporal features, and outputs the fused feature map of the current frame (size [H / 4, W / 4, C]). The temporal fusion neural network includes multiple cascaded network blocks (e.g., 3). Each network block includes a convolutional layer (stride of 1), a batch normalization layer, and an activation layer, such as a ReLU activation function layer. After upsampling the fused feature map of the current frame (size [H / 4, W / 4, C]) by a factor of four (step size 4), a fused feature matrix (size [H, W, C]) with the same size as the original image is obtained.

[0060] The prediction module 330 includes, for example, a velocity prediction neural network, an acceleration prediction neural network, and a category prediction neural network. These three neural networks process the fused feature map of the current frame, respectively, and output a velocity prediction map, an acceleration prediction map, and a category prediction map, each with the same dimensions as the original image (original point cloud voxel mesh). The velocity prediction map [H,W,2] has a dimension of 2, representing the radial and lateral components of the target's velocity. In the vehicle's driving plane, radial refers to the vehicle's direction of travel, i.e., the direction of the front of the vehicle, and lateral refers to the direction perpendicular to the vehicle's direction of travel, i.e., the width of the vehicle body. The acceleration prediction map [H,W,1] has a dimension of 1, representing the rate of change of the target's velocity. The category prediction map [H,W,1] has a dimension of 1, representing the one-dimensional index of the target's category. The velocity / acceleration / class prediction neural network consists of multiple cascaded network blocks (e.g., two), each network block including a convolutional layer (with a stride of 1), a batch normalization layer, and an activation layer, such as a ReLU activation function layer, with the last network block cascaded with a convolutional layer (with a stride of 1).

[0061] Point cloud processing neural networks are typically trained before being used for prediction. During training, the velocity and acceleration prediction maps can use the L1 loss function with ground truth for supervision, while the category prediction map can use the Focal Loss function for supervised learning. The coefficients of the three loss functions can be set, for example, to 1.0, 2.0, and 4.0. With this coefficient configuration, velocity, acceleration, and category information can be learned simultaneously, which is beneficial for the convergence of the point cloud processing neural network. Based on the point cloud processing neural network, LiDAR point clouds can be processed to obtain information such as the velocity, acceleration, and category of targets around the autonomous driving vehicle. The target categories include, but are not limited to, vehicles and pedestrians.

[0062] In addition, lidar can calculate the target's position coordinates by measuring the time difference between the emission and reception of the laser pulse, as well as the emission and elevation angles of the laser beam. These position coordinates can be used to describe the target's specific location in space.

[0063] Based on upstream sensing modules, LiDAR, and point cloud processing neural networks (point cloud processing devices), the vehicle can simultaneously perceive motion state information such as the position, speed, acceleration, and category of targets around it.

[0064] As mentioned earlier, in autonomous driving systems, there may be decision conflicts between the AEB (Autonomous Emergency Braking) system and the PNC (Programmable Controller) system. As shown in Figure 4, an obstacle appears directly in front of the autonomous vehicle, which is traveling at a relatively high speed. Based on the current instantaneous motion state, the AEB system is correct to execute emergency braking because the vehicle's speed is high, it is close to the obstacle, and there is insufficient time to brake. However, from the PNC system's perspective, it plans for the vehicle to maneuver to the left around the obstacle in future moments, therefore, the PNC system determines that braking is unnecessary. In the above scenario, both the AEB and PNC systems respond correctly based on their respective information, but this can lead to the AEB system falsely triggering emergency braking in scenarios where "the obstacle can be avoided but there is insufficient time to brake."

[0065] This embodiment of the present disclosure introduces an additional trajectory-based emergency braking decision filtering method (referred to as the "trajectory filtering decision algorithm") after the emergency braking decision, to supplement the emergency braking decision algorithm of the AEB system. If the emergency braking decision algorithm determines that emergency braking is not required, the trajectory filtering decision algorithm does not need to be activated. If the emergency braking decision algorithm determines that emergency braking is required, the trajectory filtering decision algorithm is activated to make another determination in order to maintain or cancel the emergency braking decision. Only the determination of the trajectory filtering decision algorithm can maintain the emergency braking decision triggered by the AEB system.

[0066] The input information of the "trajectory filtering decision algorithm" in this embodiment includes: (1) the motion state information of the target that triggers emergency braking in the upstream AEB system, such as the target's position (x, y), speed (vx, vy), acceleration (ax, ay), and category (optional, set to objType) in the intelligent driving vehicle coordinate system. Based on the motion state information of the target, the trajectory points of the target in a specified time period in the future can be calculated. The intelligent driving vehicle coordinate system is, for example, with the vehicle center as the origin, the direction of the front of the vehicle as the radial direction (x direction), and the direction of the vehicle width as the lateral direction (y direction). It is assumed that the direction of the front of the vehicle is the positive radial direction, the direction of the rear of the vehicle is the negative radial direction, and facing the positive radial direction, the left side is the positive lateral direction, and the right side is the negative lateral direction. (2) The trajectory points of the intelligent driving vehicle (also called the main vehicle) in a specified time period in the future, calculated by the chassis control module. The motion state information of the intelligent driving vehicle, such as the speed (set to ego_speed), is obtained directly from the vehicle chassis in real time, without the need for the perception module to make predictions. Based on the motion state information of the intelligent driving vehicle, the chassis control module can calculate the trajectory points of the intelligent driving vehicle in a specified time period in the future. For example, the intelligent driving vehicle has 8 future trajectory points every 0.15 seconds within the next 1.2 seconds. Each trajectory point contains the following information: the position of the vehicle at this moment (ego_x, ego_y) and speed information (ego_speed, which can be decomposed into ego_vx, ego_vy).

[0067] Based on the various input information obtained above for the "trajectory filtering decision algorithm", the "trajectory filtering decision algorithm" can be executed to perform driving control.

[0068] Figure 5 shows a schematic flowchart of a driving control method according to some embodiments of the present disclosure. As shown in Figure 5, the driving control method of this embodiment includes the following steps. This driving control method can be executed, for example, by a driving control device of an intelligent driving vehicle (hereinafter referred to as "vehicle").

[0069] In step 510, in response to the upstream emergency braking decision, the trajectory points of the intelligent driving vehicle and the target that triggered the emergency braking decision are determined within a specified time period in the future.

[0070] As mentioned earlier, based on the target's motion state information, the target's trajectory points within a specified future time period can be calculated; similarly, based on the autonomous vehicle's motion state information, the autonomous vehicle's trajectory points within a specified future time period can be calculated. Thus, the trajectory points of both the autonomous vehicle and the target that triggered the emergency braking decision can be obtained within the specified future time period.

[0071] In step 520, based on the trajectory points of the intelligent driving vehicle and the target that triggers the emergency braking decision within a specified time period in the future, it is determined whether there is a risk of conflict between the target and the intelligent driving vehicle.

[0072] In some embodiments, step 520 may involve performing one or more of steps 520a, 520b, and 520c to determine whether there is a risk of conflict between the target and the autonomous vehicle. For example, step 520a may be performed first, followed by step 520b, and then step 520c.

[0073] Step 520a, Conflict Risk Determination Method Based on Trajectory Points. As shown in Figure 6, if the trajectory point of the target that triggers the emergency braking decision is located within the vehicle frame of the intelligent driving vehicle's trajectory point at any time within a specified future time period, it is determined that there is a conflict risk between the target and the intelligent driving vehicle.

[0074] Step 520b, Conflict Risk Determination Method Based on Trajectory Lines. As shown in Figure 7, if the line connecting the trajectory points of the target that triggers the emergency braking decision intersects with the line connecting the trajectory points of the autonomous vehicle within the same specified time period, a conflict risk between the target and the autonomous vehicle is determined. This identifies the conflict risk arising from the target "crossing" the autonomous vehicle.

[0075] Step 520c: Conflict risk determination method based on emergency braking re-assessment. As shown in Figure 8, based on the motion state information of the last trajectory point of the autonomous vehicle and the target triggering the emergency braking decision within a specified future time period, an emergency braking assessment is performed again. If the re-assessment result still indicates that emergency braking is required, a conflict risk is determined between the target and the autonomous vehicle; if the re-assessment result indicates that emergency braking is not required, no conflict risk is determined between the target and the autonomous vehicle. This identifies the imminent conflict risk after the specified future time period. Furthermore, the emergency braking decision-making method will be described later with reference to Figure 10.

[0076] In step 530, if a conflict risk is identified, the emergency braking decision is maintained; if no conflict risk is identified, the emergency braking decision is cancelled.

[0077] In this embodiment, after the emergency braking decision, an additional trajectory-based emergency braking decision filtering method is introduced to maintain or cancel the emergency braking decision, avoid decision conflicts between the AEB system and the PNC system, reduce the false triggering behavior of the AEB system in emergency braking, and improve the operating efficiency of intelligent driving vehicles.

[0078] For example, in a scenario where "there is an alternative route but not enough time to brake," emergency braking would be mistakenly triggered before the introduction of a "trajectory filtering decision algorithm." After the introduction of the "trajectory filtering decision algorithm," the emergency braking decision of the AEB system would be canceled, thus avoiding decision conflicts between the AEB system and the PNC system.

[0079] The following describes an example of a driving control method with reference to Figure 9. The steps and their execution order in this example are only one example of driving control, and the steps and their execution order can also be executed using other methods.

[0080] Figure 9 shows a schematic flowchart of a driving control method according to some embodiments of the present disclosure. As shown in Figure 9, the driving control method of this embodiment includes the following steps. This driving control method can be executed, for example, by a driving control device of an intelligent driving vehicle (hereinafter referred to as "vehicle").

[0081] In step 910, in response to the upstream emergency braking decision, the trajectory points of the intelligent driving vehicle and the target that triggered the emergency braking decision are determined within a specified time period in the future.

[0082] In step 920, it is determined whether the trajectory point of the target that triggers the emergency braking decision at any time within a specified future time period is within the vehicle frame of the intelligent driving vehicle's trajectory point at that time. If yes, it is determined that there is a risk of conflict between the target and the intelligent driving vehicle, and step 950a is executed; otherwise, step 930 is executed to continue the determination.

[0083] In step 930, it is determined whether the line connecting the trajectory points of the target that triggers the emergency braking decision over a specified future time period intersects with the line connecting the trajectory points of the autonomous vehicle over the specified future time period. If yes, it is determined that there is a risk of conflict between the target and the autonomous vehicle, and step 950a is executed; otherwise, step 940 is executed to continue the determination.

[0084] In step 940, it is determined whether the result of the emergency braking reassessment still indicates that emergency braking is required. If yes, it is determined that there is a risk of conflict between the target and the intelligent driving vehicle, and step 950a is executed. If no, that is, the result of the reassessment indicates that emergency braking is not required, it is determined that there is no risk of conflict between the target and the intelligent driving vehicle, and step 950b is executed.

[0085] Based on the motion state information of the last trajectory point of the intelligent driving vehicle and the target that triggered the emergency braking decision within a specified time period in the future, the emergency braking judgment is made again.

[0086] In step 950a, if a conflict risk is identified, the emergency braking decision is maintained.

[0087] In step 950b, if it is determined that there is no risk of conflict, the emergency braking decision is cancelled.

[0088] In this embodiment, after the emergency braking decision, an additional trajectory-based emergency braking decision filtering method is introduced to maintain or cancel the emergency braking decision, avoid decision conflicts between the AEB system and the PNC system, reduce the false triggering behavior of the AEB system in emergency braking, and improve the operating efficiency of intelligent driving vehicles.

[0089] The method for determining whether to perform emergency braking again is described below with reference to Figure 10. Figure 10 shows a flowchart of an emergency braking decision method according to some embodiments of the present disclosure. As shown in Figure 10, the emergency braking decision method of this embodiment includes the following steps.

[0090] In step 1010, the position, velocity, and acceleration of the target in the coordinate system of the intelligent driving vehicle, as well as the speed and braking attributes of the intelligent driving vehicle, are obtained at the last trajectory point.

[0091] In step 1020, based on the target's position, velocity, and acceleration in the intelligent driving vehicle coordinate system at the last trajectory point, as well as the intelligent driving vehicle's speed and braking attributes, it is determined whether there is a risk of conflict between the target and the intelligent driving vehicle.

[0092] Therefore, based on the rich information such as the speed and acceleration of the perceived target, it is possible to more accurately determine whether there is a risk of conflict between the target and the intelligent driving vehicle.

[0093] In some embodiments, step 1020 may involve performing steps 1020c and 1020d to determine whether there is a risk of conflict between the target and the intelligent driving vehicle. Alternatively, at least one of steps 1020a and 1020b may be performed first to preliminarily eliminate the risk of conflict before performing steps 1020c and 1020d to verify whether there is a risk of conflict between the target and the intelligent driving vehicle.

[0094] Step 1020a: Preliminary assessment of conflict risk. Based on at least one of the target's position in the autonomous vehicle's coordinate system, the target's velocity, and the autonomous vehicle's velocity, determine whether there is a potential conflict risk between the target and the autonomous vehicle. This simple judgment logic quickly assesses potential conflict risks, eliminating cases where there is clearly no conflict risk. For cases where conflict risk cannot be eliminated, further verification of the conflict risk is conducted through subsequent judgments. If a potential conflict risk is determined, the actual conflict risk between the target and the autonomous vehicle is determined based on the target's position, velocity, and acceleration in the autonomous vehicle's coordinate system, as well as the autonomous vehicle's velocity and braking attributes.

[0095] Step 1020b: Determine if the target is a candidate target for triggering emergency braking. Determine the target's relative velocity to the autonomous vehicle, and determine if the target is a candidate target for triggering emergency braking based on whether the ray from the target in the relative velocity direction crosses the safe driving range of the autonomous vehicle. This will be described later with reference to Figure 11. If the target is not a candidate target for triggering emergency braking, no further determination is needed; if it is a candidate target, the conflict risk can be further verified through subsequent determinations. If the target is a candidate target for triggering emergency braking, determine whether there is a conflict risk between the target and the autonomous vehicle based on the target's position, velocity, and acceleration in the autonomous vehicle's coordinate system, as well as the autonomous vehicle's speed and braking attributes.

[0096] Step 1020c: Determine if there is a risk of conflict in the radial direction. This will be described in conjunction with Figures 12-14 to verify the radial conflict risk.

[0097] Step 1020d: Determine if there is a risk of conflict in the lateral direction in order to verify the lateral conflict risk situation.

[0098] In step 1030, if a conflict risk is identified, it is determined that emergency braking is required. If no conflict risk is identified, emergency braking is not required, and normal driving can continue.

[0099] Therefore, based on the rich information such as the speed and acceleration of the perceived target, it is possible to more accurately determine whether there is a risk of conflict between the target and the intelligent driving vehicle, and thus make an accurate decision on whether emergency braking is necessary.

[0100] The method for the preliminary assessment of conflict risk in step 1020a is described below.

[0101] In some embodiments, the system determines whether the target is located behind or in front of the intelligent driving vehicle based on the radial component of the target's position in the intelligent driving vehicle's coordinate system; compares the radial component of the target's velocity with the velocity of the intelligent driving vehicle; if the target is located behind the intelligent driving vehicle and the radial component of the target's velocity is less than the velocity of the intelligent driving vehicle, it determines that there is no potential conflict risk between the target and the intelligent driving vehicle; if the target is located in front of the intelligent driving vehicle and the radial component of the target's velocity is greater than the velocity of the intelligent driving vehicle, it determines that there is no potential conflict risk between the target and the intelligent driving vehicle.

[0102] For example, if x < front_edge_to_center and vx < ego_speed, it indicates that the target is behind the intelligent driving vehicle and the radial component of the target's speed is less than the speed of the intelligent driving vehicle. At this time, the target is located behind the vehicle and gradually lags behind the vehicle, and the lagging distance gradually increases. It can be determined that there is no potential conflict risk between the target and the intelligent driving vehicle, and emergency braking does not need to be triggered. If x > front_edge_to_center and vx > ego_speed, it indicates that the target is in front of the intelligent driving vehicle and the radial component of the target's speed is greater than the speed of the intelligent driving vehicle. At this time, the target will gradually move away from the host vehicle in the radial direction, and it can be determined that there is no potential conflict risk between the target and the intelligent driving vehicle, and emergency braking does not need to be triggered.

[0103] In some embodiments, according to the lateral component of the target's position in the intelligent driving vehicle coordinate system, it is determined whether the target is on the left or right side of the intelligent driving vehicle; when the target is on the left side of the intelligent driving vehicle and the lateral component of the target's speed is to the left, it is determined that there is no potential conflict risk between the target and the intelligent driving vehicle; when the target is on the right side of the intelligent driving vehicle and the lateral component of the target's speed is to the right, it is determined that there is no potential conflict risk between the target and the intelligent driving vehicle.

[0104] For example, if y > right_edge_to_center and vy > 0, it indicates that the target is on the left side of the intelligent driving vehicle and the lateral component of the target's speed is to the left. At this time, the target will gradually move away from the vehicle in the left lateral direction, and it can be determined that there is no potential conflict risk between the target and the intelligent driving vehicle, and emergency braking does not need to be triggered. If y < -front_edge_to_center and vy < 0, it indicates that the target is on the right side of the intelligent driving vehicle and the lateral component of the target's speed is to the right. At this time, the target will gradually move away from the vehicle in the right lateral direction, and it can be determined that there is no potential conflict risk between the target and the intelligent driving vehicle, and emergency braking does not need to be triggered.

[0105] In some embodiments, according to the radial component of the target's position in the intelligent driving vehicle coordinate system, it is determined whether the target is behind the center point of the intelligent driving vehicle; when the target is behind the center point of the intelligent driving vehicle, it is determined that there is no potential conflict risk between the target and the intelligent driving vehicle.

[0106] For example, if x < 0, it indicates that the target is behind the center point of the intelligent driving vehicle. At this time, the target is behind the vehicle, and it can be determined that there is no potential conflict risk between the target and the intelligent driving vehicle, and emergency braking does not need to be triggered. The active safety module generally only processes targets that are flush with or in front of the vehicle itself, and does not need to process rear targets, otherwise it will cause more false triggers of emergency braking, affecting the vehicle passing efficiency and driving experience.

[0107] Therefore, based on the target's location, and combined with the target's speed and the speed of the autonomous vehicle, potential conflict risks can be quickly assessed through simple judgment logic. Situations where there is clearly no conflict risk can be ruled out. For situations where conflict risk cannot be ruled out, further judgments can be made to verify the conflict risk.

[0108] The method for determining whether a target is a candidate target for triggering emergency braking in step 1020b is described below.

[0109] As shown in Figure 11, the relative speed of the target relative to the autonomous vehicle is determined. Starting from the target's position and pointing in the direction of the relative speed, a ray is drawn. If the ray in the relative speed direction crosses the safe driving range of the autonomous vehicle, it indicates that the target is approaching the vehicle with no risk of conflict, and the target is determined to be a candidate target for triggering emergency braking. If the ray in the relative speed direction does not cross the safe driving range of the autonomous vehicle, the target is determined not to be a candidate target for triggering emergency braking. The safe driving range of the autonomous vehicle can be the bounding box of the autonomous vehicle with a certain safety buffer distance, represented by an expanded box. If the target is not a candidate target for triggering emergency braking, no further judgment is needed; if it is a candidate target for triggering emergency braking, the risk of conflict can be further verified through subsequent judgments.

[0110] The method for determining whether there is a risk of conflict in the radial direction in step 1020c is described below.

[0111] In some embodiments, a risk of conflict between the target and the intelligent driving vehicle in the radial direction is determined based on the radial components of the target's velocity and acceleration at the last trajectory point, the speed and braking attributes of the intelligent driving vehicle, and the radial distance between the target and the intelligent driving vehicle. The radial distance between the target and the intelligent driving vehicle is determined based on the radial component of the target's position in the intelligent driving vehicle's coordinate system.

[0112] Therefore, it is possible not only to accurately determine whether there is a risk of conflict between the target and the intelligent driving vehicle, but also to further determine that the direction of the risk of conflict is radial.

[0113] In some embodiments, the braking distances of the target and the autonomous vehicle are determined based on the radial components of the target's velocity and acceleration, as well as the speed and braking attributes of the autonomous vehicle. By comparing the difference between the braking distance of the autonomous vehicle and the target with the radial distance between the target and the autonomous vehicle, it is determined whether there is a risk of conflict between the target and the autonomous vehicle in the radial direction, in order to verify the radial conflict risk situation. If the difference between the braking distance of the autonomous vehicle and the target is greater than the difference between the radial distance between the target and the autonomous vehicle and the safety buffer distance, it is determined that there is a risk of conflict between the target and the autonomous vehicle in the radial direction. The radial distance between the target and the autonomous vehicle is determined based on the radial component of the target's position in the autonomous vehicle's coordinate system.

[0114] Due to system transmission delay, the autonomous vehicle first travels at the current speed for the duration of the system transmission delay (time_delay), and then performs emergency braking according to the slope of the maximum braking deceleration (ego_max_dec)d. The braking distance of the autonomous vehicle is the area enclosed by the solid line and the x-axis from t=0 to t=t_ego. If the target is traveling with a certain acceleration, the target's braking distance is the area enclosed by the dashed line and the x-axis from t=0 to t=t_target, with positive values ​​above the x-axis and negative values ​​below. The following sections determine the target's braking distance and the autonomous vehicle's braking distance in three different scenarios.

[0115] The first scenario: As shown in Figure 12, the target's initial velocity is in the same direction as the autonomous vehicle (vx>0), and the two velocities will not reach the same level at any given moment during the autonomous vehicle's deceleration to 0. In this case, t_ego is the moment when the autonomous vehicle decelerates to 0, t_target is the moment when the target decelerates to 0, and the slope (acceleration) of the velocity v-time t graph is the target's acceleration.

[0116] If the radial components of the velocity of the target and the autonomous vehicle are in the same direction, and if the velocities of the autonomous vehicle and the target will not reach the same at any time during the deceleration process of the autonomous vehicle at its maximum braking deceleration, the distance traveled by the autonomous vehicle from its current speed to zero at its maximum braking deceleration is determined as the braking distance of the autonomous vehicle, and the distance traveled by the target from its current speed radial component to zero at its acceleration radial component is determined as the braking distance of the target.

[0117] The second scenario: As shown in Figure 13, the target's initial velocity is in the same direction as the autonomous vehicle (vx>0), and during the autonomous vehicle's deceleration to 0, their velocities will reach the same point at some moment. In this case, t_ego and t_target represent the moment when their velocities reach the same point, and the slope (acceleration) of the velocity v-time t graph is the target's acceleration.

[0118] When the radial components of the target's and the autonomous vehicle's velocities are in the same direction, if the speeds of the autonomous vehicle and the target reach the same point at a certain moment during the autonomous vehicle's deceleration at its maximum braking deceleration, the distance traveled by the autonomous vehicle from its current speed to the moment when its speeds are the same is determined as the braking distance of the autonomous vehicle, and the distance traveled by the target from its current speed radial component to the moment when its speeds are the same is determined as the braking distance of the target.

[0119] The third scenario: As shown in Figure 14, the target's initial velocity is in the opposite direction to the autonomous vehicle (vx < 0). In this case, t_ego represents the moment the autonomous vehicle decelerates to 0, and t_target represents the moment the target decelerates to 0. The slope (acceleration) of the target's velocity-time t graph can be a pre-set maximum deceleration target_max_dec, rather than the perceived deceleration of the target's actual motion. This is because the situation of the target traveling in the opposite direction is special, requiring the assumption that the other party immediately brakes at the maximum deceleration. If there is a danger under this assumption, the autonomous vehicle needs to take emergency braking measures.

[0120] When the radial component of the target's velocity is opposite to that of the autonomous driving vehicle, the distance traveled by the autonomous driving vehicle during the process of decelerating from the current speed to zero according to the maximum braking deceleration is determined as the braking distance of the autonomous driving vehicle, and the distance traveled by the target during the process of decelerating from the current speed radial component to zero according to the preset maximum deceleration is determined as the braking distance of the target.

[0121] After determining the braking distances of the autonomous vehicle and the target, if the difference between their braking distances is greater than the difference between the radial distance between the target and the autonomous vehicle and the safety buffer distance, a radial collision risk is identified between the target and the autonomous vehicle. The radial distance between the target and the autonomous vehicle is determined based on the radial component of the target's position in the autonomous vehicle's coordinate system. That is, if "autonomous vehicle braking distance - target braking distance > target radial distance (x) - safety buffer distance," a radial collision risk is identified, and further assessment of lateral collision risk is required. Otherwise, no radial collision risk is identified, and emergency braking is not triggered.

[0122] The method for determining whether there is a risk of conflict in the lateral direction in step 1020d is described below.

[0123] In some embodiments, the risk of conflict between the target and the intelligent driving vehicle in the lateral direction is determined based on the target's position, velocity, and lateral acceleration components in the intelligent driving vehicle coordinate system at the last trajectory point, as well as the speed and width range of the intelligent driving vehicle.

[0124] Therefore, it is possible not only to accurately determine whether there is a risk of conflict between the target and the intelligent driving vehicle, but also to further determine that the direction of the conflict risk is from the lateral direction.

[0125] In some embodiments, based on the target's position, velocity, and lateral acceleration components in the autonomous vehicle's coordinate system, and the autonomous vehicle's velocity, it is determined whether the target will move into the width range of the autonomous vehicle in the lateral direction. Based on whether the target will move into the width range of the autonomous vehicle in the lateral direction, it is determined whether there is a risk of conflict between the target and the autonomous vehicle in the lateral direction, in order to verify the lateral conflict risk situation. If the target will move into the width range of the autonomous vehicle in the lateral direction, it is determined that there is a risk of conflict between the target and the autonomous vehicle in the lateral direction.

[0126] In some embodiments, the method for determining whether a target will move into the width range of an intelligent driving vehicle in the lateral direction includes: determining the time of conflict between the target and the intelligent driving vehicle in the radial direction according to the radial distance between the target and the intelligent driving vehicle, and the difference between the speed ego_speed of the intelligent driving vehicle and the radial component vx of the target's speed. The radial distance between the target and the intelligent driving vehicle is determined according to the radial component x of the target's position in the coordinate system of the intelligent driving vehicle. That is, the time of conflict t in the radial direction is calculated according to t = x / (ego_speed - vx); determining the lateral component of the target's position at the time of conflict according to the current lateral component y, the lateral component of the speed vy, and the lateral component of the acceleration ay of the target in the coordinate system of the intelligent driving vehicle, and the time of conflict t. That is, the lateral component of the target's position y' at the time of conflict is determined according to y' = y + vy × t + ay × t × t / 2; determining whether the target will move into the width range of the intelligent driving vehicle in the lateral direction according to the lateral component of the target's position at the time of conflict. That is, if y' > -right_edge_to_center and y' < left_edge_to_center, it means that the target will appear within the width range of the intelligent driving vehicle.

[0127] FIG. 15 shows a schematic structural diagram of a driving control device according to some embodiments of the present disclosure. The intelligent driving vehicle includes a driving control device, and the driving control device can execute the driving control method in each embodiment.

[0128] As shown in FIG. 15, the driving control device 1500 of this embodiment includes: a memory 1510 and a processor 1520 coupled to the memory 1510. The processor 1520 is configured to execute the driving control method in any of the foregoing embodiments based on the instructions stored in the memory 1510.

[0129] The driving control device 1500 may further include an input / output interface 1530, a network interface 1540, a storage interface 1550, etc. These interfaces 1530, 1540, 1550 and the memory 1510 and the processor 1520 may be connected, for example, through a bus 1560.

[0130] Among them, the memory 1510 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory stores, for example, an operating system, application programs, a boot loader (Boot Loader), and other programs.

[0131] The processor 1520 can be implemented using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates, or transistors, or other discrete hardware components.

[0132] The input / output interface 1530 provides a connection interface for input / output devices such as monitors, mice, keyboards, and touchscreens. The network interface 1540 provides a connection interface for various networked devices. The storage interface 1550 provides a connection interface for external storage devices such as SD cards and USB flash drives. The bus 1560 can use any bus architecture from a variety of bus structures. For example, bus architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, and Peripheral Component Interconnect (PCI) bus.

[0133] The driving control schemes of the various embodiments of this disclosure can be applied, for example, to new energy vehicles or other intelligent driving vehicles, for emergency braking decisions under new energy driving modes such as plug-in hybrid drive, pure electric drive and fuel cell drive.

[0134] This disclosure provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement a driving control method.

[0135] This disclosure provides a computer program product including computer instructions that, when executed by a processor, implement a driving control method.

[0136] This disclosure provides a computer program comprising: instructions that, when executed by a processor, cause the processor to perform a driving control method.

[0137] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more (non-transitory) computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, cloud storage, etc.) containing computer program code. A computer program product should be understood as a software product that primarily implements its solution through a computer program.

[0138] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0139] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0140] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0141] The above description is only a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A driving control method, comprising: In response to an emergency braking decision, determine the trajectory points of the intelligent driving vehicle and the target that triggered the emergency braking decision within a specified future time period; Based on the trajectory points of the intelligent driving vehicle and the target that triggers the emergency braking decision within a specified time period in the future, determine whether there is a risk of conflict between the target and the intelligent driving vehicle. If a risk of conflict is identified, maintain the emergency braking decision; if no risk of conflict is identified, cancel the emergency braking decision.

2. The driving control method according to claim 1, wherein, Based on the trajectory points of the autonomous vehicle and the target that triggers the emergency braking decision over a specified future time period, determine whether there is a risk of conflict between the target and the autonomous vehicle, including: If the trajectory point of the target that triggers the emergency braking decision is located within the vehicle frame of the intelligent driving vehicle at any time within a specified future time period, it is determined that there is a risk of conflict between the target and the intelligent driving vehicle.

3. The driving control method according to claim 1, wherein, Based on the trajectory points of the autonomous vehicle and the target that triggers the emergency braking decision over a specified future time period, determine whether there is a risk of conflict between the target and the autonomous vehicle, including: If the line connecting the trajectory points of the target that triggers the emergency braking decision intersects with the line connecting the trajectory points of the autonomous vehicle within the same specified time period, it is determined that there is a risk of conflict between the target and the autonomous vehicle.

4. The driving control method according to claim 1, wherein, Based on the trajectory points of the autonomous vehicle and the target that triggers the emergency braking decision over a specified future time period, determine whether there is a risk of conflict between the target and the autonomous vehicle, including: Determine whether the trajectory point of the target that triggers the emergency braking decision is within the vehicle frame of the intelligent driving vehicle at any time within a specified future time period. If the judgment result is yes, it is determined that there is a risk of conflict between the target and the intelligent driving vehicle. If the judgment result is negative, it is determined whether the line connecting the trajectory points of the target that triggered the emergency braking decision in the future intersects with the line connecting the trajectory points of the intelligent driving vehicle in the future specified time period. If the judgment result is that they intersect, it is determined that there is a risk of conflict between the target and the intelligent driving vehicle.

5. The driving control method according to any one of claims 1-4, wherein, Based on the trajectory points of the autonomous vehicle and the target that triggers the emergency braking decision over a specified future time period, determine whether there is a risk of conflict between the target and the autonomous vehicle, including: If no conflict risk is determined based on the trajectory points, the emergency braking decision is made again based on the motion state information of the last trajectory point of the intelligent driving vehicle and the target that triggers the emergency braking decision within a specified time period in the future. If the assessment result is still that emergency braking is required, it is determined that there is a risk of conflict between the target and the autonomous vehicle. If the assessment result is that emergency braking is not required, it is determined that there is no risk of conflict between the target and the autonomous vehicle.

6. The driving control method according to claim 5, wherein, The determination to apply emergency braking again includes: Based on the target's position, velocity, and acceleration in the autonomous vehicle's coordinate system at the last trajectory point, as well as the autonomous vehicle's speed and braking attributes, determine whether there is a risk of conflict between the target and the autonomous vehicle. If a risk of conflict is identified, it is determined that emergency braking is necessary.

7. The driving control method according to claim 6, wherein, Determining whether there is a conflict risk between the target and the autonomous vehicle includes: The relative speed of the target with respect to the autonomous vehicle at the last trajectory point is determined, and whether the target is a candidate target for triggering emergency braking is determined based on whether the ray of the target in the direction of relative speed crosses the safe driving range of the autonomous vehicle. When the target is a candidate target that could trigger emergency braking, the system determines whether there is a risk of conflict between the target and the autonomous vehicle based on the target's position, velocity, and acceleration in the autonomous vehicle's coordinate system at the last trajectory point, as well as the autonomous vehicle's speed and braking attributes.

8. The driving control method according to any one of claims 6-7, wherein, Determining whether there is a conflict risk between the target and the autonomous vehicle includes: Based on the radial components of the target's velocity and acceleration at the last trajectory point, as well as the speed and braking properties of the autonomous vehicle, determine the target's braking distance and the autonomous vehicle's braking distance. By comparing the difference between the braking distance of the autonomous vehicle and the braking distance of the target with the radial distance between the target and the autonomous vehicle, it is determined whether there is a risk of conflict between the target and the autonomous vehicle in the radial direction. The radial distance between the target and the autonomous vehicle is determined based on the radial component of the target's position in the autonomous vehicle's coordinate system.

9. The driving control method according to any one of claims 6-8, wherein, Determining whether there is a conflict risk between the target and the autonomous vehicle includes: Based on the target's position, velocity, and lateral acceleration components in the autonomous vehicle's coordinate system at the last trajectory point, as well as the autonomous vehicle's velocity, determine whether the target will move into the width range of the autonomous vehicle in the lateral direction. Based on whether the target will move into the width range of the intelligent driving vehicle in the lateral direction, determine whether there is a risk of conflict between the target and the intelligent driving vehicle in the lateral direction.

10. A driving control device, comprising: Memory; And a processor coupled to the memory, the processor being configured to execute the driving control method of any one of claims 1-9 based on instructions stored in the memory.

11. An intelligent driving vehicle, comprising: A driving control device is configured to perform the driving control method according to any one of claims 1-9.

12. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the steps of the driving control method according to any one of claims 1-9.

13. A computer program product comprising computer instructions that, when executed by a processor, implement the steps of the driving control method according to any one of claims 1-9.

Images