Autonomous driving method and apparatus, and vehicle

Abstract

An autonomous driving method and apparatus, and a vehicle. The method comprises: acquiring traffic light sensing information, road sensing information, and navigation information, wherein the traffic light sensing information indicates a state of a target traffic light that an ego vehicle is required to follow within a past period of time, the road sensing information indicates intersection guidance supported by a lane where the ego vehicle is located, and the position of at least one vehicle in front of the ego vehicle, and the navigation information indicates a target traveling direction of the ego vehicle at a nearest intersection; and when the traffic light sensing information indicates that a state of the target traffic light within the current period of time is an unknown state, on the basis of the road sensing information and the navigation information, controlling the ego vehicle to follow a preceding vehicle on the current lane to travel into the nearest intersection or controlling the ego vehicle to temporarily stop. The present solution can be applied to the field of intelligent driving, and when the ego vehicle cannot acquire traffic light information due to shielding, the vehicle can determine whether to follow the preceding vehicle to travel into an intersection, thereby being conducive to considering both the traffic efficiency and driving safety of the vehicle at the intersection.

Description

Autonomous driving methods, devices and vehicles

[0001] This application claims priority to Chinese Patent Application No. 202411984057.X, filed on December 16, 2024, entitled "Autonomous Driving Method, Apparatus and Vehicle", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of intelligent driving, and more specifically, to an autonomous driving method, device, and vehicle. Background Technology

[0003] With the rapid development of the automotive industry, many driver assistance and autonomous driving technologies have emerged, which can reduce driving stress and improve safety and traffic efficiency. However, the sensing range of vehicle sensors is limited. For example, when a vehicle approaches an intersection, if the sensors are blocked, the vehicle may be unable to perceive the status of traffic lights, and the vehicle may slow down or even stop, thus affecting the traffic efficiency at the intersection.

[0004] Therefore, an autonomous driving solution that can improve the efficiency and safety of vehicles at intersections is urgently needed. Summary of the Invention

[0005] This application provides an autonomous driving method, device, and vehicle. When the vehicle cannot obtain traffic light information due to obstruction by a vehicle in front, the vehicle can determine whether to follow the vehicle in front into the intersection based on the road information perceived by the vehicle and navigation information, which helps to balance the traffic efficiency and driving safety at the intersection.

[0006] In one aspect, an autonomous driving method is provided, which can be executed by a vehicle, for example, by the vehicle's computing platform, or by chips or circuits used in the vehicle.

[0007] The method includes: acquiring traffic light perception information and road perception information; wherein the traffic light perception information at least indicates the state of a first traffic light within a first time period, the first traffic light being the traffic light that a vehicle must follow when passing through the nearest adjacent intersection, the end time of the first time period being earlier than the current time, and the time interval between the end time and the current time being less than a duration threshold; the road perception information at least indicates the intersection guidance supported by the first lane in which the vehicle is located, and the position of at least one vehicle located ahead of the vehicle's direction of travel; acquiring navigation information, the navigation information indicating the target direction of travel for the vehicle at the nearest adjacent intersection; when the traffic light perception information indicates that the state of the first traffic light in the current time period is unknown, controlling the vehicle to follow the first vehicle into the nearest adjacent intersection, or controlling the vehicle to temporarily stop, based on the road perception information and the navigation information; wherein the first vehicle is located in the first lane, and at least one vehicle includes the first vehicle.

[0008] In some implementations, the traffic light sensing information indicates that the state of the first traffic light in the current time period is unknown, which can be understood as: the vehicle's sensing system has not detected the first traffic light in the current time period.

[0009] In the above technical solution, when the vehicle cannot perceive the status of the traffic light due to the obstruction of the vehicle in front, the vehicle can determine whether to follow the vehicle in front into the intersection based on the intersection guidance supported by the lane in which the vehicle is located and the target driving direction. This helps to balance the traffic efficiency and driving safety of the vehicle at the intersection, avoid the vehicle from indiscriminately slowing down in the scenario where the traffic light is obstructed, and help to improve the human-like nature of the vehicle in the process of autonomous driving.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, based on road perception information and navigation information, controlling the vehicle to follow the first vehicle into the nearest intersection, or controlling the vehicle to temporarily stop, includes: based on the matching of the intersection guidance supported by the first lane and the target driving direction, and / or the matching of the predicted driving direction of the first vehicle at the nearest intersection with the target driving direction, controlling the vehicle to follow the first vehicle into the nearest intersection, or controlling the vehicle to temporarily stop.

[0011] In some implementations, when the intersection guidance supported by the first lane matches the target driving direction, and / or when the predicted driving direction of the first vehicle at the nearest intersection matches the target driving direction, the vehicle is controlled to follow the first vehicle into the nearest intersection.

[0012] In the above technical solutions, when the intersection guidance and target driving direction are matched according to the lane support, or when the predicted driving direction of the preceding vehicle is matched with the driving direction of the vehicle itself, the vehicle is controlled to follow the preceding vehicle into the nearest intersection, which helps to improve the vehicle's passage efficiency at the intersection; otherwise, the vehicle is controlled to stop outside the intersection boundary to wait for the vehicle to re-perceive the traffic lights, reducing the risk of the vehicle violating traffic rules and colliding with other road traffic participants.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the road perception information further includes turn indicator information of each vehicle in at least one vehicle, the turn indicator information indicating the orientation of each vehicle at the nearest intersection; the method further includes: predicting the predicted driving direction of the first vehicle at the nearest intersection based on the turn indicator information of the first vehicle and / or the heading angle information of the first vehicle.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, controlling the vehicle to follow the first vehicle into the nearest intersection includes: when the intersection guidance supported by the first lane is consistent with the target driving direction, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, the first lane is included in the first road, and the first road is a one-way road.

[0016] In the above technical solution, when the road where the vehicle is located contains one or more lanes, and the one or more lanes only support one direction at the nearest intersection, since the vehicle in front of the vehicle in the lane will not travel in other directions at the nearest intersection, controlling the vehicle to follow the vehicle in front can reduce the risk of the vehicle violating traffic rules (such as running red lights) and improve the vehicle's traffic efficiency at the intersection.

[0017] In conjunction with the first aspect, in some implementations of the first aspect, the first lane is included in the second road, and the second road is a single-lane road; controlling the vehicle to follow the first vehicle into the nearest intersection includes: when the predicted driving direction and the target driving direction of the first vehicle at the nearest intersection follow the same traffic light signal, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0018] In the aforementioned technical solution, when the road where the vehicle is located contains a single lane, and that single lane supports multiple directions at the nearest intersection, controlling the vehicle to follow the preceding vehicle when the predicted driving direction of the preceding vehicle and the target driving direction of the vehicle follow the same traffic light helps reduce the risk of traffic violations and improves the vehicle's traffic efficiency at the intersection. For example, generally speaking, when the road contains a single lane, there may only be one traffic light at the intersection indicating the traffic flow in that lane, used to indicate whether vehicles in that lane are allowed to go straight or turn left, or not allowed to go straight or turn left. This traffic light is not used to restrict right-turning vehicles. Therefore, when the predicted driving direction of the preceding vehicle is left-turning or straight, and the target driving direction of the vehicle is left-turning or straight, the vehicle can follow the preceding vehicle; or, when the predicted driving direction of the preceding vehicle is right-turning, and the target driving direction of the vehicle is right-turning, the vehicle can follow the preceding vehicle.

[0019] In conjunction with the first aspect, in some implementations of the first aspect, the road perception information also indicates the intersection guidance supported by the second lane, wherein the second lane is a lane in the same direction adjacent to the first lane, and controlling the vehicle to follow the first vehicle into the nearest intersection includes: when the intersection guidance supported by the first lane includes the target driving direction, and the intersection guidance supported by the second lane is consistent with the target driving direction, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, at least one vehicle includes a second vehicle in a second lane, and controlling the vehicle to follow the first vehicle into the nearest intersection includes: when the first vehicle is in motion and the second vehicle is also in motion, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0021] Generally speaking, at an intersection, if the vehicle in front in the adjacent lane is in motion, it means that the traffic light indicating the traffic flow in that lane is in a state where vehicles are allowed to pass (such as the green light being on). Therefore, when the intersection guidance supported by the adjacent lane of your vehicle is consistent with your vehicle's target direction of travel, and when both the vehicle in front in your lane and the vehicle in front in the adjacent lane are in motion, controlling your vehicle to follow the vehicle in front helps to reduce the risk of your vehicle violating traffic rules and improve your vehicle's traffic efficiency at the intersection.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, controlling a vehicle to follow a first vehicle into the nearest intersection includes: when the vehicle body encroachment is greater than or equal to an encroachment threshold and the distance between the vehicle and the first vehicle is less than or equal to a distance threshold, controlling the vehicle to follow the first vehicle into the nearest intersection; wherein, the vehicle body encroachment indicates the ratio of the portion of the first vehicle's body that is in the first lane to the entire body of the first vehicle.

[0023] In the above technical solution, when the encroachment of the preceding vehicle is greater than or equal to a certain threshold, it indicates that the preceding vehicle has no intention of illegally changing lanes. Therefore, the reliability of predicting the preceding vehicle's direction of travel at the intersection is relatively high. In this case, the probability of violating traffic rules when following the preceding vehicle is low. When the distance between the vehicle and the preceding vehicle is less than or equal to a certain threshold, the risk of running a red light when following the preceding vehicle into the intersection can be reduced.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: predicting the state of the first traffic light in a second time period based on the state of the first traffic light in a first time period, the second time period including the time period during which the vehicle enters the nearest adjacent intersection; controlling the vehicle to follow the first vehicle into the nearest adjacent intersection, including: when the state of the first traffic light in the second time period indicates that passage is possible, controlling the vehicle to follow the first vehicle into the nearest adjacent intersection.

[0025] In the above technical solution, when the target traffic light is in a state indicating that the vehicle can pass during the predicted process of the vehicle entering the intersection, controlling the vehicle to enter the intersection according to the vehicle in front helps to reduce the risk of the vehicle running a red light, thereby improving the vehicle's driving safety.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining a first boundary of the nearest intersection, the first boundary indicating the position where the first lane and the nearest intersection meet; controlling the vehicle to temporarily stop, including: controlling the vehicle to temporarily stop outside the first boundary of the nearest intersection.

[0027] In the above technical solution, controlling the vehicle to temporarily stop outside the boundary of the nearest intersection can avoid vehicle violations and help reduce the risk of vehicle collisions.

[0028] Secondly, an autonomous driving device is provided, comprising an acquisition unit and a processing unit. The acquisition unit is configured to: acquire traffic light perception information and road perception information; wherein the traffic light perception information at least indicates the state of a first traffic light within a first time period, the first traffic light being the traffic light that a vehicle must follow when passing through the nearest adjacent intersection, the end time of the first time period being earlier than the current time, and the time interval between the end time and the current time being less than a duration threshold; the road perception information at least indicates the intersection guidance supported by the first lane in which the vehicle is located, and the position of at least one vehicle located ahead of the vehicle's direction of travel; the acquisition unit is further configured to: acquire navigation information, the navigation information indicating the target direction of travel for the vehicle at the nearest adjacent intersection; the processing unit is configured to: when the traffic light perception information indicates that the state of the first traffic light in the current time period is unknown, control the vehicle to follow a first vehicle into the nearest adjacent intersection, or control the vehicle to temporarily stop, based on the road perception information and the navigation information; wherein the first vehicle is located in the first lane, and at least one vehicle includes the first vehicle.

[0029] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to: control the vehicle to follow the first vehicle into the nearest intersection, or control the vehicle to temporarily stop, based on the matching of the intersection guidance and target driving direction supported by the first lane, and / or the matching of the first vehicle's driving direction at the nearest intersection with the target driving direction.

[0030] In conjunction with the second aspect, in some implementations of the second aspect, the road perception information also includes turn signal information of each vehicle in at least one vehicle, the turn signal information indicating the direction of each vehicle at the nearest intersection; the processing unit is further configured to: predict the predicted driving direction of the first vehicle at the nearest intersection based on the turn signal information of the first vehicle and / or the heading angle information of the first vehicle.

[0031] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to: control the vehicle to follow the first vehicle into the nearest intersection when the intersection guidance supported by the first lane is consistent with the target driving direction.

[0032] In conjunction with the second aspect, in some implementations of the second aspect, the first lane is included in the first road, and the first road is a one-way road.

[0033] In conjunction with the second aspect, in some implementations of the second aspect, the first lane is contained within the second road, and the second road is a single-lane road; the processing unit is used to: control the vehicle to follow the first vehicle into the nearest intersection when the predicted driving direction and the target driving direction of the first vehicle follow the same traffic light signal at the nearest intersection.

[0034] In conjunction with the second aspect, in some implementations of the second aspect, the road perception information also indicates the intersection guidance supported by the second lane, the second lane being a lane in the same direction adjacent to the first lane, and the processing unit is used to: control the vehicle to follow the first vehicle into the nearest intersection when the intersection guidance supported by the first lane includes the target driving direction and the intersection guidance supported by the second lane is consistent with the target driving direction.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, at least one vehicle includes a second vehicle in the second lane, and the processing unit is configured to: when the first vehicle is in motion and the second vehicle is also in motion, control the vehicle to follow the first vehicle into the nearest intersection.

[0036] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is used to: control the vehicle to follow the first vehicle into the nearest intersection when the body encroachment of the first vehicle is greater than or equal to an encroachment threshold and the distance between the vehicle and the first vehicle is less than or equal to a distance threshold; wherein, the body encroachment indicates the ratio of the portion of the first vehicle's body that is in the first lane to the entire body of the first vehicle.

[0037] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: predict the state of the first traffic light in a second time period based on the state of the first traffic light in a first time period, the second time period including the time period during which vehicles enter the nearest adjacent intersection; and control the vehicle to follow the first vehicle into the nearest adjacent intersection when the state of the first traffic light in the second time period indicates that passage is permitted.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is also used to: determine the first boundary of the nearest intersection, the first boundary indicating the position where the first lane and the nearest intersection meet; and control the vehicle to temporarily stop outside the first boundary of the nearest intersection.

[0039] Thirdly, an autonomous driving device is provided, the device comprising: a processor for executing a computer program stored in the memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0040] In conjunction with the third aspect, in some implementations of the third aspect, the device also includes a memory.

[0041] Fourthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer or processor, causes the computer or processor to perform the method in any possible implementation of the first aspect.

[0042] It should be noted that the above computer program code can be stored in whole or in part on a storage medium, which can be packaged together with the processor or packaged separately from the processor.

[0043] Fifthly, a computer-readable storage medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0044] In a sixth aspect, a chip is provided that includes circuitry for performing the method in any of the possible implementations of the first aspect described above.

[0045] In a seventh aspect, a vehicle is provided that includes means as in any possible implementation of the second or third aspect, or the vehicle includes a computer-readable storage medium as in any possible implementation of the fifth aspect, or the vehicle includes a chip as in any possible implementation of the sixth aspect, or the vehicle is loaded with a computer program product as in any possible implementation of the fourth aspect.

[0046] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the vehicle is a vehicle in a broad sense, such as a means of transportation (e.g., commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (e.g., forklifts, trailers, tractors, etc.), engineering vehicles (e.g., excavators, bulldozers, cranes, etc.), agricultural equipment (e.g., lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. In practical implementation, the vehicle can also be a road vehicle, a water vehicle, an air vehicle, industrial equipment, agricultural equipment, or other intelligent driving equipment such as entertainment equipment. Attached Figure Description

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

[0048] Figure 2 is a schematic diagram of the autonomous driving system architecture provided in an embodiment of this application;

[0049] Figure 3 is a schematic diagram of the application scenario of the autonomous driving solution provided in the embodiments of this application;

[0050] Figure 4 is a schematic flowchart of the autonomous driving method provided in an embodiment of this application;

[0051] Figure 5 is a schematic diagram of the road surface markings for indicating intersection directions provided in an embodiment of this application;

[0052] Figure 6 is a schematic diagram of the application scenarios involved in the embodiments of this application;

[0053] Figure 7 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0054] Figure 8 is a schematic diagram of determining the vehicle body encroachment degree provided in an embodiment of this application;

[0055] Figure 9 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0056] Figure 10 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0057] Figure 11 is a schematic diagram of a prompt for the nearest neighbor vehicle involved in an embodiment of this application;

[0058] Figure 12 is another schematic flowchart of the autonomous driving method provided in the embodiments of this application;

[0059] Figure 13 is a schematic block diagram of an autonomous driving device provided in an embodiment of this application;

[0060] Figure 14 is another schematic block diagram of the autonomous driving device provided in the embodiments of this application. Detailed Implementation

[0061] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0062] Figure 1 is a functional block diagram of a vehicle provided in an embodiment of this application. As shown in Figure 1, the vehicle 100 may include a sensing system 120, a display device 130, and a computing platform 150. The sensing system 120 may include several sensors for sensing information about the environment surrounding the vehicle 100. For example, the sensing system 120 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou system, or another positioning system. As another example, the sensing system 120 may also include one or more of the following: an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0063] Display devices 130 are mainly divided into two categories: the first is in-vehicle displays; the second is projection displays, such as head-up displays (HUDs). In-vehicle displays are physical displays and an important component of in-vehicle infotainment systems. Multiple displays can be installed in the cabin, such as digital instrument cluster displays and central control screens. In some possible implementations, one or more of the aforementioned in-vehicle displays can be human-machine interfaces (HMIs), for example, the central control screen can be an HMI. Head-up displays, also known as head-up display systems, are mainly used to display driving information such as speed and navigation on a display device in front of the driver (e.g., the windshield). This reduces the driver's eye-shifting time, avoids pupil changes caused by eye-shifting, and improves driving safety and comfort. HUDs include, for example, combiner-HUD (C-HUD) systems, windshield-HUD (W-HUD) systems, and augmented reality HUD (AR-HUD) systems.

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

[0065] The computing platform 150 can control the operation of the intelligent driving system, which may include an advanced driving assistance system (ADAS) and an autonomous driving system (ADS). The intelligent driving system utilizes various sensors on the vehicle (including but not limited to: LiDAR, millimeter-wave radar, cameras, ultrasonic sensors, GPS, and inertial measurement units) to acquire information from the vehicle's surroundings, and analyzes and processes this information to achieve functions such as obstacle perception, target recognition, vehicle localization, path planning, and driver monitoring / alerts, thereby improving the safety, automation, and comfort of driving the vehicle.

[0066] At different levels of autonomous driving (or intelligent driving levels, ranging from L0 to L5, totaling six levels), intelligent driving systems can achieve different levels of automated driving assistance based on artificial intelligence algorithms and information acquired by multiple sensors. These levels of autonomous driving are based on the classification standards of the Society of Automotive Engineers (SAE). Specifically, L0 is no automation; L1 is driver assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At levels L1 to L3, the task of monitoring road conditions and reacting is jointly completed by the driver and the system, requiring the driver to take over dynamic driving tasks. Levels L4 and L5 allow the driver to completely transform into a passenger. Currently, the functions that intelligent driving systems can achieve mainly include, but are not limited to: adaptive cruise control, automatic emergency braking, automatic parking, blind spot monitoring, forward cross-traffic alert / braking, rear cross-traffic alert / braking, forward collision warning, lane departure warning, lane keeping assist, rear collision warning, traffic sign recognition, traffic jam assist, and highway assist. It should be understood that the above-mentioned functions can have specific modes at different levels of autonomous driving (L0-L5). The higher the level of autonomous driving, the more intelligent the corresponding mode.

[0067] In this application, the perception system 120 can collect information about traffic lights at an intersection, as well as the motion status information of other vehicles located in front of the vehicle 100 in the direction of travel. When the perception system 120 is unable to perceive the status of the target traffic light at the intersection due to obstruction by the vehicle in front, the computing platform 150 can determine whether to control the vehicle 100 to follow the vehicle in front through the intersection based on the status of the traffic light during the period before obstruction and the motion status of the vehicle in front.

[0068] The roles of the perception system 120 and the computing platform 150 in this application are explained in detail below with reference to Figure 2. Figure 2 shows a schematic block diagram of the autonomous driving system architecture provided in an embodiment of this application. The system includes a perception module 210, a navigation information acquisition module 220, an occlusion following module 230, and a planning and control module 240. The perception module 210 may include one or more camera devices in the perception system 120 shown in Figure 1, or it may also include one or more radars in the perception system 120; the navigation information acquisition module 220, the occlusion following module 230, and the planning and control module 240 may each include one or more processors in the computing platform 150 shown in Figure 1. The roles of each module in the system shown in Figure 2 are described in items (a) to (iv) below.

[0069] (i) Perception Module 210: Used to acquire environmental information around the vehicle and send it to the occlusion following module 230. This environmental information includes road information and intersection information. Road information may include the road boundaries, lane lines, and lane guidance (or intersection guidance, i.e., the possible driving directions supported by the lane at the intersection). Intersection information may include the detection results of traffic lights at the intersection (e.g., traffic lights detected, traffic lights not detected, the time period during which traffic lights were detected), and the status of the traffic lights (e.g., color, remaining duration). For example, perception module 210 may also include one or more processors to process the acquired perception information to obtain environmental information. For instance, taking an image as the perception information, one or more processors in perception module 210 can extract information such as road boundaries, lane lines, and lane guidance from the acquired image.

[0070] (II) Navigation Information Acquisition Module 220: This module determines the navigation information between the vehicle's current location and the target location. The navigation information indicates the driving direction at intersections the vehicle passes through while traveling towards the target location, such as going straight, turning left, turning right, merging into the main road, or entering a ramp. For example, the navigation information can be determined based on a standard definition (SD) map, an electronic horizon map, or other maps. Further, the navigation information acquisition module 220 sends this navigation information to the occlusion following module 230.

[0071] (III) The occlusion following module 230 includes a traffic light status recognition module 231, a guidance matching module 232, a vehicle-followable recognition module 233, and a following condition judgment module 234. Wherein:

[0072] The traffic light status recognition module 231 is used to: determine the detection result and status of the target traffic light based on the perception information collected by the perception module 210. When the target traffic light changes from detected to undetected, it can predict the status of the target traffic light during the period when the target traffic light was not detected, based on the status of the target traffic light during the period when the target traffic light was detected. The target traffic light is the traffic light that vehicles must follow when passing through the intersection. The traffic light status recognition module 231 inputs its recognition result to the guidance matching module 232.

[0073] For example, in the scenario shown in Figure 3, vehicle 301 is in a lane that supports going straight and turning left, and vehicle 301 needs to follow the instructions of traffic light a (i.e., an example of the target traffic light) in traffic light 303 to pass through the intersection. However, due to the obstruction of vehicle 302, vehicle 301 may not be able to collect the information of traffic light a when it is near the intersection, which makes it impossible for vehicle 301 to determine the color and remaining time of the traffic light. At this time, the traffic light status recognition module 231 can predict the status of traffic light a in the current time period based on the status of the traffic light during the time period in which traffic light a is detected.

[0074] The guidance matching module 232 is used to: determine whether the intersection guidance supported by the vehicle's current lane is consistent with the driving direction indicated by the navigation information when the detection result of the target traffic light changes from detected to undetected. When the intersection guidance supported by the vehicle's current lane is consistent with the driving direction indicated by the navigation information, it can be determined that the vehicle can follow the vehicle in front through the intersection when the following conditions are met; when the intersection guidance supported by the vehicle's current lane is not completely consistent with the driving direction indicated by the navigation information, and the intersection guidance supported by the vehicle's current lane includes the driving direction indicated by the navigation information, it can determine whether the vehicle can follow the vehicle in front through the intersection based on the intersection guidance supported by the adjacent lanes of the vehicle's current lane.

[0075] The vehicle-followable identification module 233 is used to determine whether there is a vehicle that can be followed. For example, the vehicle-followable identification module 233 can determine whether the nearest neighbor vehicle is a vehicle that can be followed based on one or more of the following: the degree of encroachment of the nearest neighbor vehicle on its own lane, the distance between the nearest neighbor vehicle and the vehicle, the predicted state of the traffic light, and the predicted direction of travel of the vehicle in front at the intersection.

[0076] The following condition judgment module 234 is used to: when there is a vehicle that can be followed, determine whether it is possible to follow the vehicle based on the distance between the vehicle and the vehicle that can be followed, as well as the estimated state of the traffic light.

[0077] Understandably, when the target traffic light is always detectable, the vehicle's movement can be controlled based on the target traffic light's status without triggering the following procedure. That is, the guidance matching module 232, the followable vehicle recognition module 233, and the following condition judgment module 234 do not need to perform related operations. If the navigation matching module 232 cannot determine that the intersection guidance supported by the vehicle's lane is completely inconsistent with the driving direction indicated by the navigation information, or if the intersection guidance supported by the vehicle's lane is not completely consistent with the driving direction indicated by the navigation information, and based on the intersection guidance supported by the adjacent lanes, it cannot be determined whether the driving direction of the vehicle in front at the intersection is consistent with the vehicle's, the following procedure is not triggered, and the followable vehicle recognition module 233 and the following condition judgment module 234 cannot perform related operations. If the followable vehicle recognition module 233 determines that there is no vehicle to follow, the following procedure is not triggered, and the following condition judgment module 234 cannot perform related operations.

[0078] (iv) Regulation and Control Module 240: Used to control the vehicle based on the results from the Obstruction Following Module 230. In one example, when the Obstruction Following Module 230 determines that following is necessary and indicates that it is permissible to follow the vehicle in front, the Regulation and Control Module 240 calculates the control quantity for controlling the vehicle to follow based on the speed of the vehicle in front, and outputs the control quantity to the actuator. When the actuator executes the control quantity, it controls the vehicle to follow the vehicle in front. In another example, when the Obstruction Following Module 230 determines that following is not necessary, the Regulation and Control Module 240 controls the vehicle's movement based on information such as the position and speed of obstacles around the vehicle. Exemplarily, the actuator may include a steering and braking control system in the vehicle 100.

[0079] It should be understood that the above modules are only an example, and in actual applications, these modules may be added or removed as needed. For example, in the system architecture shown in Figure 2, the occlusion following module 230 and the traffic control module 240 can be merged into one module.

[0080] The above describes the autonomous driving system architecture provided in the embodiments of this application. The following details the process of implementing the autonomous driving method provided in the embodiments of this application based on the autonomous driving system shown in Figure 2.

[0081] Figure 4 shows a schematic flowchart of an autonomous driving method provided in an embodiment of this application. This method 400 can be applied to the vehicle shown in Figure 1, or it can be executed by the system shown in Figure 2. More specifically, this method 400 can be executed by the occlusion following module 230, and it may include some or all of the steps in S401 to S410 below.

[0082] S401, Obtain traffic light status information, which indicates the detection result of the target traffic light and / or the status of the target traffic light.

[0083] For example, the detection result of the target traffic light indicates whether the target traffic light has been detected; the state of the target traffic light may include the color of the target traffic light, or the state of the target traffic light may also include the duration between the current time and the time when the color of the target traffic light changes.

[0084] For example, traffic light status information can be obtained by processing images captured by a vehicle's camera.

[0085] S402, Determine whether the target traffic light is in an unknown state.

[0086] An unknown state refers to a situation where the vehicle's perception system cannot detect the state of the traffic light. In one example, if the traffic light state information indicates that the current frame of perception information does not include information about the target traffic light, and the previous frame of perception information does include information about the target traffic light, then the target traffic light is determined to be in an unknown state. In another example, if the perception system detects the target traffic light, and then for n consecutive frames the perception information does not include information about the target traffic light, then the target traffic light is determined to be in an unknown state.

[0087] Specifically, if the target traffic light is in an unknown state, execute S403; otherwise, execute S410.

[0088] S403 determines whether the road the vehicle is currently on has only one lane.

[0089] For example, the number of lanes on the road where the vehicle is currently located can be determined based on SD map information; or, the number of lanes on the road where the vehicle is currently located can also be determined based on perception information collected by the perception system.

[0090] It should be noted that "the road where the vehicle is located has only one lane" can be understood as: the road supports only one lane for travel direction 1, and travel direction 1 is the same as the direction the vehicle travels on that road. In actual implementation, the road may only support one travel direction. For example, if the road has a first end and a second end, then the vehicle can only travel from the first end to the second end, and the road may include only one lane. Alternatively, the road may support two opposite travel directions. For example, if the road has a first end and a second end, then the vehicle can travel from the first end to the second end, or vice versa. Furthermore, taking travel direction 1 as traveling from the first end to the second end, there can be one lane supporting travel from the first end to the second end, and there can be one or more lanes supporting travel from the second end to the first end.

[0091] Specifically, if the road currently in which the vehicle is located supports more than one lane for the driving direction 1, then execute S404; otherwise, execute S407.

[0092] S404 determines whether the intersection guidance supported by the vehicle's current lane is consistent with the navigation direction.

[0093] For example, the navigation direction can be determined based on SD map navigation information; the intersection guidance supported by the vehicle's current lane can be determined based on perception information collected by the vehicle's perception system, or it can be obtained through roadside equipment or a cloud server. For example, Figures 5(a) to (j) show several possible schematic diagrams of the intersection guidance supported by the vehicle's current lane.

[0094] For example, if the lane currently occupied by the vehicle supports an intersection guide and the intersection guide and the navigation direction are the same, then the intersection guide and the navigation direction are determined to be consistent; otherwise, the intersection guide and the navigation direction are determined to be inconsistent or not completely consistent. For example, if the intersection guide supported by the lane currently occupied by the vehicle is shown in Figure 6(a), and the navigation direction indicates a left turn, then the intersection guide supported by the lane currently occupied by the vehicle is determined to be consistent with the navigation direction; as another example, if the intersection guide supported by the lane currently occupied by the vehicle is shown in Figure 6(b), and the navigation direction indicates going straight, then the intersection guide supported by the lane currently occupied by the vehicle is determined to be consistent with the navigation direction; as yet another example, if the intersection guide supported by the lane currently occupied by the vehicle is shown in Figure 6(c), and the navigation direction indicates a right turn, then the intersection guide supported by the lane currently occupied by the vehicle is determined to be consistent with the navigation direction. Furthermore, if the intersection guide supported by the lane currently occupied by the vehicle is shown in Figure 6(a), and the navigation direction indicates going straight or turning right, then the intersection guide supported by the lane currently occupied by the vehicle is determined to be inconsistent with the navigation direction. For example, if the intersection guidance supported by the current lane of the vehicle is as shown in (d) or (e) in Figure 6, and the navigation direction indicates a left turn or a straight ahead, then it is determined that the intersection guidance supported by the current lane of the vehicle is not completely consistent with the navigation direction.

[0095] Specifically, if the direction of the intersection supported by the vehicle's current lane is consistent with the navigation direction, then execute S408; otherwise, execute S405.

[0096] S405 determines whether the intersection guidance supported by the vehicle's current lane includes the navigation direction.

[0097] For example, if one of the multiple intersection directions supported by the vehicle's current lane is the same as the navigation direction, then the intersection direction supported by the vehicle's current lane is determined to include the navigation direction; otherwise, the intersection direction supported by the vehicle's current lane is determined to not include the navigation direction. For instance, if the intersection direction supported by the vehicle's current lane is as shown in (d) or (e) of Figure 6, and the navigation direction indicates a left turn or straight ahead, then the intersection direction supported by the vehicle's current lane is determined to include the navigation direction; as another example, if the intersection direction supported by the vehicle's current lane is as shown in (f) of Figure 6, and the navigation direction indicates a right turn, then the intersection direction supported by the vehicle's current lane is determined to include the navigation direction. Yet another example, if the intersection direction supported by the vehicle's current lane is as shown in (d) of Figure 6, and the navigation direction indicates a right turn, then the intersection direction supported by the vehicle's current lane is determined to not include the navigation direction.

[0098] Specifically, if the lane currently occupied by the vehicle supports intersection guidance including the navigation direction, execute S406; otherwise, execute S410.

[0099] In some implementations, S405 can be executed before S404. In this case, if it is determined in S405 that the intersection guidance supported by the vehicle's current lane includes the navigation direction, then S404 is executed. Furthermore, if it is determined in S404 that the intersection guidance supported by the vehicle's current lane is consistent with the navigation direction, then S407 is executed; otherwise, S406 is executed.

[0100] S406, determine whether the intersection guidance and navigation direction supported by the adjacent lanes of the vehicle are consistent.

[0101] Specifically, if the intersection guidance and navigation direction supported by the adjacent lanes of the vehicle are consistent, execute S408; otherwise, execute S407.

[0102] In one example, as shown in (d) to (f) of Figure 6, the navigation directions of the vehicle are left turn, straight and right turn, respectively. Correspondingly, the intersection directions supported by the adjacent lanes are left turn, straight and right turn, respectively. Therefore, it can be determined that the intersection directions supported by the adjacent lanes of the vehicle are consistent with the navigation directions.

[0103] In another example, as shown in Figure 6(g), the vehicle's navigation direction is straight, and the two adjacent lanes of the vehicle's lane support left turn and right turn respectively. Therefore, it can be determined that the adjacent lanes of the vehicle support intersection guidance and navigation direction are inconsistent. Therefore, S407 is executed.

[0104] In another example, as shown in (h) of Figure 6, the navigation direction of the vehicle is left turn, and the intersection guidance supported by the adjacent lanes of the vehicle includes both straight and left turn. Therefore, it can be determined that the intersection guidance supported by the adjacent lanes of the vehicle is not completely consistent with the navigation direction. Therefore, S407 is executed.

[0105] S407, determine if there is a vehicle to follow.

[0106] In some implementations, when the road where the vehicle is currently located has only one lane and the lane where the vehicle is located supports a single intersection guide, it can be determined that there is a vehicle that can be followed, and the vehicle that can be followed is the nearest neighbor vehicle of the vehicle located in the lane where the vehicle is located, and then S408 is executed.

[0107] In some other implementations, when the lane in which the vehicle is located supports multiple intersection guidance, the driving direction of the vehicle in front at the intersection is predicted based on the turn signal and / or heading angle of the vehicle in front in the lane in which the vehicle is located. If the driving direction of the vehicle in front matches the navigation direction of the vehicle in the lane, the vehicle in front in the lane in which the vehicle is located is determined to be a vehicle that can be followed, and then S408 is executed; otherwise, it is determined that there is no vehicle that can be followed, and then S410 is executed.

[0108] Among them, the direction of travel of the vehicle in front and the navigation direction of the vehicle in front match, including: the direction of travel of the vehicle in front and the navigation direction of the vehicle in front are the same, or the direction of travel of the vehicle in front and the navigation direction of the vehicle in front must follow the same traffic light.

[0109] In one example, if the navigation direction of the vehicle at the intersection is straight and the vehicle in front does not use its turn signal while moving forward, it can be predicted that the vehicle in front is going straight, that is, the vehicle in front is traveling in the same direction as the vehicle's navigation direction, and in this case, the vehicle in front is determined to be a vehicle that can be followed. Alternatively, if the navigation direction of the vehicle at the intersection is right turn (or left turn) and the right (or left) turn signal of the vehicle in front is flashing, it can be predicted that the vehicle in front is right turn (or left turn), that is, the vehicle in front is traveling in the same direction as the vehicle's navigation direction, and in this case, the vehicle in front is determined to be a vehicle that can be followed.

[0110] In another example, if the navigation direction of your vehicle at the intersection is either straight or left turn, and the left turn signal of the vehicle in front is flashing, you can predict that the vehicle in front is turning left. When you determine that vehicles going straight and turning left at the intersection follow the same traffic light, you can determine that the direction of travel of the vehicle in front matches the navigation direction of your vehicle, and therefore you can determine that the vehicle in front is a vehicle you can follow. For example, if the road where your vehicle is located has only one lane, and the intersection directions supported by your lane include straight, left turn, and right turn, then going straight and turning left generally follow the same traffic light.

[0111] In another example, the predicted path of the preceding vehicle based on its heading angle is shown by the dashed line in Figure 7. Each point on the dashed line indicates the position of the preceding vehicle at different times. Further, the vehicle's navigation direction is used as vector 'a', with the preceding vehicle's current position as the starting point and the predicted position of the preceding vehicle n seconds later as the ending point, forming vector 'b'. The angle between vectors 'a' and 'b' determines whether the preceding vehicle's direction matches the vehicle's navigation direction. For example, if the preceding vehicle's direction and the vehicle's navigation direction follow the same traffic light, then if vector 'b' is within 90° to the left of vector 'a' and within 5° to the right of vector 'a', the preceding vehicle's direction matches the vehicle's navigation direction.

[0112] It should be noted that the aforementioned "left side" (or "right side") refers to the left (or right) side relative to the vehicle. The left and right sides of the vehicle can be relative; for example, they can be defined based on a vehicle coordinate system. The origin O of the vehicle coordinate system can be located at the projection point of the rear axle center onto the ground. The positive directions of the X-axis and Z-axis are the direction of the vehicle's front and the direction perpendicular to the vehicle's plane, respectively. The side of the vehicle located in the positive direction of the Y-axis can be considered the left side of the vehicle, and the side located in the negative direction of the Y-axis can be considered the right side of the vehicle.

[0113] S408, determine whether the vehicle in front meets the following conditions.

[0114] In some implementations, when the vehicle to be followed is the nearest neighbor vehicle in the lane where the vehicle is located, the following condition is met if the vehicle's encroachment is greater than or equal to a proportional threshold, and the distance between the vehicle and the vehicle is less than or equal to a distance threshold. The vehicle encroachment can be the ratio of the portion of the vehicle's body within its lane to the total vehicle body. For example, as shown in Figures 8(a) and (b), the vehicle encroachment can be the ratio of the shaded portion to the total vehicle body. Exemplarily, the proportional threshold can be a value between 50% and 60%, or it can be any other value. The distance threshold can be a value between 20 meters and 30 meters, or it can be any other value. For example, the distance threshold can be determined based on the speed of the vehicle and / or the vehicle in front, and it increases with increasing speed.

[0115] In some implementations, when the lane in which the vehicle is located supports multiple intersection guidances, and the intersection guidances supported by the adjacent lanes of the vehicle's lane are consistent with the vehicle's navigation direction, the vehicles that can be followed include the nearest neighbor vehicle in the vehicle's own lane and the nearest neighbor vehicle in the adjacent lane. For example, as shown in any of (d) to (f) in Figure 6, the vehicle in front of the vehicle in the dashed line is a vehicle that can be followed. Further, when the vehicle's body encroachment is greater than or equal to a proportional threshold, the distance between the vehicle and the vehicle is less than or equal to a distance threshold, and when the nearest neighbor vehicle in the vehicle's own lane is in motion, and the nearest neighbor vehicle in the adjacent lane is also in motion, the vehicle that can be followed is determined to meet the following conditions.

[0116] In some implementations, S407 and S408 can be executed simultaneously, or S408 can be executed before S407. When S408 is executed before S407, if it is determined that the preceding vehicle does not meet the following conditions, S407 can be skipped, and execution can jump to S410.

[0117] In some other implementations, if it is determined in S404 that the intersection guidance supported by the current lane of the vehicle is consistent with the navigation direction, or if it is determined in S406 that the intersection guidance supported by the adjacent lane of the vehicle is consistent with the navigation direction, S407 can be executed first, and S408 can be executed only when it is determined that there is a vehicle to follow.

[0118] S409, controls the vehicle to follow the vehicle in front.

[0119] In some implementations, when the predicted state of the target traffic light indicates that passage is possible, the vehicle is controlled to follow the vehicle in front. For example, the state of the target traffic light is predicted based on the state at the last time it was perceived, and the duration between the last time the target traffic light was perceived and the current time. Using the time of the most recently acquired frame of perceived information (such as an image or laser point cloud) as the representation, the duration between the last time the target traffic light was perceived and the current time is N*t seconds, where N is the number of frames between the last frame containing the target traffic light and the most recently acquired frame, and t is the time difference between two adjacent frames of perceived information. Further, taking t as 0.1 seconds and the time difference between the current time and the moment the vehicle enters the intersection as 2 seconds as an example, the state of the last perceived target traffic light and the predicted state of the target traffic light can be shown in Table 1.

[0120] Table 1

[0121] It should be understood that the cases listed in Table 1 are for illustrative purposes only. In actual implementation, other scenarios may also exist.

[0122] For example, the state of the target traffic light can be determined by processing the last frame of the image including the pixels of the target traffic light, or the state of the target traffic light can be determined based on the last frame of the image and one or more frames of images preceding it. For example, if, based on the last frame of the image and several frames preceding it, it is determined that the last perceived color of the target traffic light was green and not flashing, and the remaining time of the target traffic light cannot be determined from the image, for the sake of conservatism, it can be determined that the last perceived color of the target traffic light was green and the remaining duration was 3 seconds, that is, assuming that the target traffic light starts flashing in the next frame after the last perceived color of the target traffic light. Furthermore, if the last perceived color of the target traffic light was red, to reduce the probability of the vehicle running a red light, the color of the target traffic light when the vehicle enters the intersection can be inferred based on the green light duration of M seconds at the intersection. For example, M can be 10 seconds, 15 seconds, or other durations.

[0123] It should be noted that the aforementioned last frame of perceived information is an image or laser point cloud containing target traffic light information that is stored in the vehicle's current journey and associated with the current intersection.

[0124] S410, does not trigger following vehicle driving.

[0125] In some implementations, without triggering follow-me functionality, a virtual wall is set between the vehicle's current location and the nearest intersection boundary, or at the nearest intersection boundary. The vehicle is then controlled to move to the virtual wall and brake, stopping before the intersection. The virtual wall is deactivated when the vehicle can perceive the target traffic light's status. The virtual wall indicates a location the vehicle cannot cross; it can be a set of parameters used to control the vehicle, not a physical entity.

[0126] Figures 9 and 10 illustrate application scenarios of the autonomous driving method provided in this application. As shown in Figure 9, when the vehicle is traveling in the left lane, it must follow the instructions of traffic light 901. For example, as shown by ground marking 902, the left lane allows vehicles to go straight or turn left at the intersection. In the scenario shown in Figure 9, when the vehicle reaches the stop line, if traffic light 901 is green, the vehicle can go straight or turn left; otherwise, the vehicle stops and waits at the stop line. As shown in Figure 10, if the vehicle cannot perceive traffic light 901 due to obstruction by vehicle 903, the aforementioned method 400 can be executed to determine whether to follow vehicle 903 into the intersection ahead.

[0127] In some implementations, when the vehicle determines that it can follow the vehicle in front into the intersection, a prompting device can be used to inform the user that the vehicle is currently in a state of "following the vehicle when the traffic light is obscured." This prompting device may include the display device 130 and / or a sound-emitting device (such as a speaker, audio system, etc.) as described in the preceding embodiments.

[0128] In some implementations, when a vehicle determines it can follow another vehicle into an intersection, a display device can be used to alert the user to the vehicle being followed. In one example, using a head-up display (HUD), when the vehicle being followed is determined to be the nearest neighbor in the vehicle's lane, the HUD can be used to enhance the display of that nearest neighbor, for example, by highlighting it, as shown in Figure 11(a). The enhancement effect of the nearest neighbor can be as shown in 904. Alternatively, when the vehicle being followed includes both the nearest neighbor in the vehicle's lane and the nearest neighbor in adjacent lanes, the HUD can be used to enhance the display of the aforementioned nearest neighbor, as shown in Figure 11(b). The enhancement effect of the nearest neighbor can be as shown in 905. In yet another example, using a central control screen, the screen can display a virtual driving scene constructed based on perceived environmental information around the vehicle. Different colors can be used to display icons indicating vehicles that can be followed and icons indicating other non-followable vehicles to indicate vehicles that can be followed, thus informing the user of the vehicles that can be followed. The method for determining whether it is appropriate to follow the vehicle in front can be found in the description in method 400, and will not be repeated here.

[0129] Figure 12 shows another schematic flowchart of the autonomous driving method provided in this application embodiment. The method can be executed by the vehicle 100 shown in Figure 1, or it can be executed by the control module 240 shown in Figure 2. The method 1200 includes:

[0130] S1210, acquire traffic light perception information and road perception information.

[0131] The traffic light perception information indicates at least the status of the first traffic light within a first time period. The first traffic light is the traffic light that a vehicle must follow when passing through the nearest intersection. The end time of the first time period is earlier than the current time, and the time interval between the end time and the current time is less than the duration threshold. The road perception information indicates at least the intersection guidance supported by the first lane in which the vehicle is located, and the position of at least one vehicle located ahead of the vehicle in the direction of travel.

[0132] For example, the traffic light perception information may be the traffic light status information in method 400, or it may be other information indicating the perception result of the traffic light; the first traffic light may be the target traffic light of method 400; the road perception information may include an image containing road markings and pixels of the preceding vehicle and / or point cloud data containing road markings and point clouds of the preceding vehicle.

[0133] S1220, Obtain navigation information, which indicates the target driving direction of the vehicle at the nearest intersection.

[0134] For example, the target driving direction can be the navigation direction in method 400. The method for obtaining navigation information can be referred to the description of the corresponding part of the navigation information acquisition module 220 in Figure 2, which will not be repeated here.

[0135] S1230: When the traffic light perception information indicates that the state of the first traffic light in the current time period is unknown, the vehicle is controlled to follow the first vehicle into the nearest intersection, or the vehicle is controlled to temporarily stop, based on the road perception information and navigation information.

[0136] The first vehicle is located in the first lane, and at least one vehicle includes the first vehicle.

[0137] For example, the traffic light sensing information indicates that the state of the first traffic light in the current time period is unknown. This can be understood as: the vehicle's sensing system does not detect the first traffic light in the current time period, but the state of the first traffic light in the current time period can be deduced based on the state of the first traffic light in the first time period indicated by the traffic light sensing information.

[0138] In some implementations, S1230 can be further refined as follows: based on the matching of the intersection guidance and the target driving direction supported by the first lane, and / or the matching of the predicted driving direction of the first vehicle with the target driving direction at the nearest intersection, control the vehicle to follow the first vehicle into the nearest intersection, or control the vehicle to temporarily stop.

[0139] The matching of the intersection guidance and the target driving direction supported by the first lane can be: the intersection guidance supported by the first lane is consistent with the target driving direction, or the intersection guidance supported by the first lane includes the target driving direction; the matching of the predicted driving direction of the first vehicle at the nearest adjacent intersection with the target driving direction can be: the predicted driving direction of the first vehicle at the nearest adjacent intersection is consistent with the target driving direction, or the predicted driving direction of the first vehicle at the nearest adjacent intersection and the target driving direction correspond to the same traffic light.

[0140] For example, the specific implementation of determining the matching between the intersection guidance and the target driving direction of the first lane can be referred to the descriptions in S404 and S405, and will not be repeated here.

[0141] In some implementations, the road perception information also includes turn signal information for each of at least one vehicle, which indicates the orientation of each vehicle at the nearest intersection; the method further includes: predicting the predicted driving direction of the first vehicle at the nearest intersection based on the turn signal information of the first vehicle and / or the heading angle information of the first vehicle.

[0142] For example, the specific implementation of predicting the predicted driving direction of the first vehicle can be referred to in the description in S407, and will not be repeated here.

[0143] In some implementations, controlling a vehicle to follow a first vehicle into the nearest intersection includes: when the intersection guidance supported by the first lane is consistent with the target driving direction, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0144] In this scenario, the intersection guidance supported by the first lane is consistent with the target driving direction. This can be understood as: the first lane is a single-direction vehicle, meaning it only supports one type of intersection guidance. In this case, the road containing the first lane may also include other lanes, and the intersection guidance supported by the other lanes may differ from that supported by the first lane. Assuming the vehicle in front will not violate any rules, the vehicle can be controlled to follow the vehicle in front, provided that the following conditions are met.

[0145] For example, the method for determining whether the intersection guidance supported by the first lane is consistent with the target driving direction can be referred to in S404, and will not be repeated here.

[0146] In some implementations, the first lane is contained within the first road, and the first road is a one-way road.

[0147] If a road including the first lane also includes other lanes, and the intersection directions supported by the other lanes differ from those supported by the first lane, the vehicle in front of your vehicle may not be following the intersection directions. In this case, following the vehicle in front may violate traffic regulations. However, if the first road is a one-way road, meaning it only supports one intersection direction, the vehicle in front cannot travel in any other direction at the intersection. Therefore, if the first road is a one-way road and the first lane supports only one direction, you can control your vehicle to follow the vehicle in front, provided the following conditions are met.

[0148] In some implementations, the first lane is contained in the second road, and the second road is a single-lane road; controlling the vehicle to follow the first vehicle into the nearest intersection includes: when the predicted driving direction and the target driving direction of the first vehicle at the nearest intersection follow the same traffic light signal, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0149] When a road containing the first lane has a single lane and the first lane includes multiple intersection directions, the direction of travel of the vehicle in front may differ from the target direction of travel of the vehicle itself. In this case, if the predicted and target directions of travel of the vehicle in front follow the same traffic light, the vehicle can be controlled to follow the vehicle in front, provided that the following conditions are met. The method for determining whether the predicted and target directions of travel of the vehicle in front follow the same traffic light can be found in the description in S407, and will not be repeated here.

[0150] In some implementations, the road perception information also indicates the intersection guidance supported by the second lane, which is a lane in the same direction adjacent to the first lane. Controlling the vehicle to follow the first vehicle into the nearest intersection includes: when the intersection guidance supported by the first lane includes the target driving direction, and the intersection guidance supported by the second lane is consistent with the target driving direction, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0151] In some implementations, at least one vehicle includes a second vehicle in the second lane, and controlling the vehicle to follow the first vehicle into the nearest intersection includes: when the first vehicle is in motion and the second vehicle is also in motion, controlling the vehicle to follow the first vehicle into the nearest intersection.

[0152] In some implementations, controlling a vehicle to follow a first vehicle into the nearest intersection includes: when the vehicle body encroachment is greater than or equal to an encroachment threshold and the distance between the vehicle and the first vehicle is less than or equal to a distance threshold, controlling the vehicle to follow the first vehicle into the nearest intersection; wherein, the vehicle body encroachment indicates the ratio of the portion of the first vehicle's body that is in the first lane to the entire body of the first vehicle.

[0153] For example, the invasiveness threshold can be the proportion threshold in S408, and the distance threshold can be the distance threshold in S408.

[0154] In some implementations, the method further includes: predicting the state of the first traffic light in a second time period based on the state of the first traffic light in a first time period, the second time period including the time period during which the vehicle enters the nearest adjacent intersection; controlling the vehicle to follow the first vehicle into the nearest adjacent intersection, including: controlling the vehicle to follow the first vehicle into the nearest adjacent intersection when the state of the first traffic light in the second time period indicates that it is passable.

[0155] For example, a more specific method for predicting the state of the first traffic light during the second time period can be found in the description of S409, which will not be repeated here. In one example, when the state of the first traffic light is green during the second time period, it is determined that the state of the first traffic light indicates that passage is permitted; in another example, when the state of the first traffic light is flashing yellow during the second time period, it is determined that the state of the first traffic light indicates that passage is permitted.

[0156] In some implementations, the method further includes: determining a first boundary of the nearest intersection, the first boundary indicating the position where the first lane meets the nearest intersection; controlling the vehicle to temporarily stop, including: controlling the vehicle to temporarily stop outside the first boundary of the nearest intersection.

[0157] For example, the first boundary can be the location where the virtual wall is set in method 400.

[0158] When a vehicle cannot perceive the status of a traffic light due to obstruction by a vehicle in front, the autonomous driving method of this application allows the vehicle to determine whether to follow the vehicle in front into the intersection based on the intersection guidance supported by the lane in which the vehicle is located and the target driving direction. This helps to balance the efficiency of vehicle passage and driving safety at intersections, avoids the vehicle from indiscriminately slowing down when the traffic light is obstructed, and helps to improve the human-like nature of the vehicle in the autonomous driving process.

[0159] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0160] The methods provided by the embodiments of this application have been described in detail above with reference to Figures 1 to 12. The apparatus provided by the embodiments of this application will now be described in detail with reference to Figures 13 and 14. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any content not described in detail can be referred to the method embodiments above, and for the sake of brevity, will not be repeated here.

[0161] Figure 13 shows a schematic block diagram of an autonomous driving device 2000 provided in an embodiment of this application. The device 2000 may include units for executing the methods described in the foregoing embodiments. Furthermore, each unit in the device 2000 implements a corresponding process of the above method embodiments. The device 2000 includes an acquisition unit 2010, which can be used to implement corresponding data acquisition or transmission / reception functions. The device 2000 also includes a processing unit 2020, which can be used to implement corresponding processing functions.

[0162] Optionally, the device 2000 further includes a storage unit, which can be used to store instructions and / or data. The processing unit 2020 can read the instructions and / or data in the storage unit so that the device can perform the relevant actions in the aforementioned method embodiments.

[0163] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0164] It should also be understood that the device 2000 described herein is embodied in the form of a functional unit. The terms “module” or “unit” may refer to application-specific ASICs, electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components that support the described functions.

[0165] The apparatuses described above have the function of implementing the corresponding steps in the methods described above. These functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above; for example, the acquisition unit 2010 can be replaced by a transceiver, and other units, such as the processing unit, can be replaced by a processor, used to execute the relevant processing operations in each method embodiment.

[0166] Exemplarily, the acquisition unit 2010 and processing unit 2020 can be disposed in the vehicle 100 shown in FIG. 1, or they can also be disposed in the system shown in FIG. 2. More specifically, the acquisition unit 2010 and processing unit 2020 can be disposed in the occlusion following module 230 and the regulation control module 240. Exemplarily, the operations performed by the acquisition unit 2010 and processing unit 2020 can be performed by a single processor, or they can be performed by different processors. In specific implementation, the one or more processors can be processors disposed in the vehicle 100 shown in FIG. 1; or, the device 2000 can be a chip disposed in the vehicle 100.

[0167] In the specific implementation process, the units in the above device can be fully or partially integrated together, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0168] Figure 14 is another schematic block diagram of the autonomous driving device provided in an embodiment of this application. The device 2100 shown in Figure 14 may include a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, transceiver 2120, and memory 2130 are connected via internal interconnection paths. The memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 may be coupled to the processor 2110 via an interface or integrated with the processor 2110.

[0169] It should be noted that the transceiver 2120 mentioned above may include, but is not limited to, transceiver devices such as input / output interfaces, to realize communication between device 2100 and other devices or communication networks.

[0170] Memory 2130 can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes various forms such as: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0171] Transceiver 2120 uses transceiver devices, such as but not limited to transceivers, to enable communication between device 2100 and other devices or communication networks to receive / send data / information for implementing the methods in the above embodiments.

[0172] This application also provides an intelligent driving device, which includes the device 2000 or device 2100 in the above embodiments.

[0173] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to implement the methods described in the above embodiments of this application.

[0174] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to implement the methods described in the above embodiments of this application.

[0175] This application also provides a chip, including circuitry, for performing the methods described in the above embodiments of this application.

[0176] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0177] In the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. In this application, "at least one" means one or more, and "more" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0178] The use of prefixes such as "first" and "second" in this application embodiment is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions.

[0179] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0180] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0181] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0182] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0183] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An autonomous driving method, characterized in that, include: Acquire traffic light sensing information and road sensing information; The traffic light sensing information indicates at least the state of the first traffic light during a first time period. The first traffic light is the traffic light that a vehicle must follow when passing through the nearest intersection. The end time of the first time period is earlier than the current time, and the time interval between the end time and the current time is less than a duration threshold. The road sensing information indicates at least the intersection guidance supported by the first lane in which the vehicle is located, and the position of at least one vehicle ahead of the vehicle in its direction of travel. Obtain navigation information, which indicates the target driving direction of the vehicle at the nearest intersection; When the traffic light sensing information indicates that the state of the first traffic light in the current time period is unknown, the vehicle is controlled to follow the first vehicle into the nearest intersection, or the vehicle is controlled to temporarily stop, based on the road sensing information and the navigation information. Wherein, the first vehicle is located in the first lane, and the at least one vehicle includes the first vehicle.

2. The method according to claim 1, characterized in that, The step of controlling the vehicle to follow the first vehicle into the nearest intersection based on the road perception information and the navigation information, or controlling the vehicle to temporarily stop, includes: Based on the matching of the intersection guidance supported by the first lane and the target driving direction, and / or the matching of the predicted driving direction of the first vehicle at the nearest intersection with the target driving direction, the vehicle is controlled to follow the first vehicle into the nearest intersection, or the vehicle is controlled to temporarily stop.

3. The method according to claim 2, characterized in that, The road perception information also includes turn signal information for each of the at least one vehicle, the turn signal information indicating the direction of each vehicle at the nearest intersection; The method further includes: The predicted driving direction is predicted based on the turn signal information of the first vehicle and / or the heading angle information of the first vehicle.

4. The method according to any one of claims 1 to 3, characterized in that, The control of the vehicle to follow the first vehicle into the nearest intersection includes: When the intersection guidance supported by the first lane is consistent with the target driving direction, the vehicle is controlled to follow the first vehicle into the nearest intersection.

5. The method according to claim 4, characterized in that, The first lane is included in the first road, and the first road is a one-way road.

6. The method according to any one of claims 1 to 3, characterized in that, The first lane is included in the second road, and the second road is a single-lane road; The control of the vehicle to follow the first vehicle into the nearest intersection includes: When the predicted driving direction and the target driving direction of the first vehicle at the nearest intersection follow the same traffic light signal, the vehicle is controlled to follow the first vehicle into the nearest intersection.

7. The method according to any one of claims 1 to 3, characterized in that, The road perception information also indicates the intersection guidance supported by the second lane, which is a lane in the same direction adjacent to the first lane. Controlling the vehicle to follow the first vehicle into the nearest intersection includes: When the intersection guidance supported by the first lane includes the target driving direction, and the intersection guidance supported by the second lane is consistent with the target driving direction, the vehicle is controlled to follow the first vehicle into the nearest intersection.

8. The method according to claim 7, characterized in that, The at least one vehicle includes a second vehicle in the second lane, and controlling the vehicle to follow the first vehicle into the nearest intersection includes: When the first vehicle is in motion and the second vehicle is also in motion, control the second vehicle to follow the first vehicle into the nearest intersection.

9. The method according to any one of claims 1 to 8, characterized in that, The control of the vehicle to follow the first vehicle into the nearest intersection includes: When the encroachment of the first vehicle is greater than or equal to the encroachment threshold, and the distance between the vehicle and the first vehicle is less than or equal to the distance threshold, the vehicle is controlled to follow the first vehicle into the nearest intersection. The vehicle body encroachment refers to the ratio of the portion of the first vehicle's body that is located in the first lane to the entire body of the first vehicle.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: Based on the state of the first traffic light during the first time period, predict the state of the first traffic light during the second time period, where the second time period includes the time period during which the vehicle enters the nearest intersection. The control of the vehicle to follow the first vehicle into the nearest intersection includes: When the first traffic light indicates that passage is permitted during the second time period, the vehicle is controlled to follow the first vehicle into the nearest intersection.

11. The method according to any one of claims 1 to 9, characterized in that, The method further includes: Determine the first boundary of the nearest intersection, the first boundary indicating the position where the first lane and the nearest intersection meet; The control of temporarily stopping the vehicle includes: Control the vehicle to temporarily stop outside the first boundary of the nearest adjacent intersection.

12. An automatic driving device, characterized in that, include: The acquisition unit is used to acquire traffic light sensing information and road sensing information; The traffic light sensing information indicates at least the state of the first traffic light during a first time period. The first traffic light is the traffic light that a vehicle must follow when passing through the nearest intersection. The end time of the first time period is earlier than the current time, and the time interval between the end time and the current time is less than a duration threshold. The road sensing information indicates at least the intersection guidance supported by the first lane in which the vehicle is located, and the position of at least one vehicle ahead of the vehicle in its direction of travel. The acquisition unit is further configured to: acquire navigation information, wherein the navigation information indicates the target driving direction of the vehicle at the nearest intersection; The processing unit is configured to, when the traffic light sensing information indicates that the state of the first traffic light in the current time period is unknown, control the vehicle to follow the first vehicle into the nearest intersection, or control the vehicle to temporarily stop, based on the road sensing information and the navigation information. Wherein, the first vehicle is located in the first lane, and the at least one vehicle includes the first vehicle.

13. The apparatus according to claim 12, characterized in that, The processing unit is used for: Based on the matching of the intersection guidance supported by the first lane and the target driving direction, and / or the matching of the predicted driving direction of the first vehicle at the nearest intersection with the target driving direction, the vehicle is controlled to follow the first vehicle into the nearest intersection, or the vehicle is controlled to temporarily stop.

14. The apparatus according to claim 13, characterized in that, The road perception information also includes turn signal information for each of the at least one vehicle, the turn signal information indicating the direction of each vehicle at the nearest intersection; The processing unit is also used for: The predicted driving direction is predicted based on the turn signal information of the first vehicle and / or the heading angle information of the first vehicle.

15. The apparatus according to any one of claims 12 to 14, characterized in that, The processing unit is used for: When the intersection guidance supported by the first lane is consistent with the target driving direction, the vehicle is controlled to follow the first vehicle into the nearest intersection.

16. The apparatus according to claim 15, characterized in that, The first lane is included in the first road, and the first road is a one-way road.

17. The apparatus according to any one of claims 12 to 14, characterized in that, The first lane is included in the second road, and the second road is a single-lane road; The processing unit is used for: When the predicted driving direction and the target driving direction of the first vehicle at the nearest intersection follow the same traffic light signal, the vehicle is controlled to follow the first vehicle into the nearest intersection.

18. The apparatus according to any one of claims 12 to 14, characterized in that, The road perception information also indicates the intersection guidance supported by the second lane, which is a lane in the same direction adjacent to the first lane. The processing unit is used to: When the intersection guidance supported by the first lane includes the target driving direction, and the intersection guidance supported by the second lane is consistent with the target driving direction, the vehicle is controlled to follow the first vehicle into the nearest intersection.

19. The apparatus according to claim 18, characterized in that, The at least one vehicle includes a second vehicle in the second lane, and the processing unit is configured to: When the first vehicle is in motion and the second vehicle is also in motion, control the second vehicle to follow the first vehicle into the nearest intersection.

20. The apparatus according to any one of claims 12 to 19, characterized in that, The processing unit is used for: When the encroachment of the first vehicle is greater than or equal to the encroachment threshold, and the distance between the vehicle and the first vehicle is less than or equal to the distance threshold, the vehicle is controlled to follow the first vehicle into the nearest intersection. The vehicle body encroachment refers to the ratio of the portion of the first vehicle's body that is located in the first lane to the entire body of the first vehicle.

21. The apparatus according to any one of claims 12 to 20, characterized in that, The processing unit is also used for: Based on the state of the first traffic light during the first time period, predict the state of the first traffic light during the second time period, where the second time period includes the time period during which the vehicle enters the nearest intersection. When the first traffic light indicates that passage is permitted during the second time period, the vehicle is controlled to follow the first vehicle into the nearest intersection.

22. The apparatus according to any one of claims 12 to 21, characterized in that, The processing unit is also used for: Determine the first boundary of the nearest intersection, the first boundary indicating the position where the first lane and the nearest intersection meet; Control the vehicle to temporarily stop outside the first boundary of the nearest adjacent intersection.

23. An automatic driving device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 11.

24. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 11.

25. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 11.

26. A computer program product, characterized in that, The computer program product includes: computer program code, which, when executed by a processor, implements the method as described in any one of claims 1 to 11.

27. A vehicle, characterized in that, Includes the apparatus as described in any one of claims 12 to 23, or the computer-readable storage medium as described in claim 24, or the chip as described in claim 25, or the vehicle is equipped with the computer program product as described in claim 26.

Images