Intersection turning method and apparatus, and vehicle

Abstract

An intersection turning method and apparatus, and a vehicle. The method comprises: acquiring navigation guidance information, wherein the navigation guidance information indicates that a vehicle needs to travel from a first road where the vehicle is located to a second road via a first intersection, and an included angle between a boundary of the first road and a boundary of the second road meets a first condition; and on the basis of the navigation guidance information, controlling the vehicle to travel along a first path so as to pass through the first intersection and enter the second road, wherein the first intersection is an at-grade non-roundabout intersection, the first path comprises a first portion and a second portion, the first portion is closer to the first road than the second portion, and the curvature of the second portion is greater than that of the first portion. This technical solution can be applied to the field of intelligent driving of intelligent vehicles such as new energy vehicles and electric vehicles, helps to improve the human-likeness of a vehicle when passing through an intersection in an autonomous driving state, and can improve the traffic efficiency and success rate of the vehicle when making a turn at the intersection.

Description

Methods, devices and vehicles for turning at intersections Technical Field

[0001] This application relates to the field of intelligent driving, and more specifically, to a method, device, and vehicle for turning at intersections. Background Technology

[0002] With the rapid development of the automotive industry, many driver assistance and autonomous driving technologies have emerged, which can reduce driving stress, improve safety, and enhance traffic efficiency. When a vehicle is traveling to its destination using autonomous driving technology, it may need to pass through multiple intersections and make left or right turns at those intersections to enter the target road.

[0003] However, current autonomous driving technology has poorly planned intersection turning trajectories, resulting in low traffic efficiency or the possibility of other vehicles overtaking from behind, thus increasing the risk of collisions between the vehicle and other vehicles. Summary of the Invention

[0004] This application provides a method, apparatus, and vehicle for turning at intersections, which helps to improve the human-likeness of vehicles passing through intersections in autonomous driving mode, and can improve the traffic efficiency and safety of vehicles turning at intersections.

[0005] In one aspect, a method for turning at an intersection is provided, which can be executed by a vehicle; or, it can also be executed by the vehicle's computing platform; or, it can also be executed by a chip or circuit for the vehicle, without limitation in this application.

[0006] The method includes: acquiring navigation guidance information, which instructs the vehicle to travel from a first road through a first intersection to a second road, wherein the angle between the boundary of the first road and the boundary of the second road satisfies a first condition; and controlling the vehicle to travel along the first path through the first intersection and into the second road according to the navigation guidance information; wherein the first intersection is a planar non-roundabout intersection, the first path includes a first part and a second part, the first part being closer to the first road than the second part, and the curvature of the second part being greater than the curvature of the first part.

[0007] In the above technical solution, when a vehicle turns within an intersection to enter the target road, the vehicle is controlled to travel along the first path to avoid the vehicle stopping too early within the intersection and obstructing the vehicle behind it. This helps to reduce the interaction risk between the vehicle and other vehicles and can improve the traffic efficiency of traffic participants within the intersection.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: acquiring obstacle information, the obstacle information indicating the positional change of a first target object, the first target object being an object that poses a collision risk with the vehicle during the vehicle's journey to the second road; controlling the vehicle to travel along the first path through the first intersection into the second road, including: after making a decision about the vehicle based on the obstacle information and when the first target object passes through the first conflict area, controlling the vehicle to travel along the first path; wherein the first conflict area is the area where a collision between the predicted vehicle and the first target object is expected.

[0009] The risk of collision between the target object and the vehicle refers to the risk of interaction between the target object and the vehicle being greater than or equal to the risk threshold.

[0010] In the aforementioned technical solution, when deciding whether the vehicle should yield to a target object, controlling the vehicle to pass through the intersection along a first path helps improve the matching degree between the vehicle's autonomous driving path and the human driving path. It also avoids congestion caused by the vehicle prematurely stopping to yield at the intersection, thus improving the traffic efficiency of all road users within the intersection when the vehicle yields to other vehicles. Furthermore, it avoids increased interaction risks between the vehicle and other vehicles due to overtaking or cutting in, contributing to improved vehicle safety when traveling within the intersection.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the first intersection is at least connected to the third road, and the moving object in the third road affects the path of the vehicle traveling from the first road to the second road. The straight lane of the third road corresponds to the opposite lane of the current lane where the vehicle is located, and the first target object is the object that drives out of the third road.

[0012] For example, the first intersection can be a T-junction, a crossroads, or similar. If the vehicle is turning in the first direction at the first intersection, the straight lane of the third road corresponds to the opposite lane of the vehicle's current lane. This can be understood as: a vehicle traveling in the straight lane of the third road can enter the opposite lane of its current lane via the first intersection. Furthermore, the first target object can be a straight-moving object, or it can be an object turning in the first direction. When traffic rules indicate driving on the right, turning in the first direction can be a left turn; when traffic rules indicate driving on the left, turning in the first direction can be a right turn.

[0013] In the above technical solution, when traffic rules indicate driving on the right, the objects that have a greater impact on the vehicle's driving path when the vehicle turns left within the intersection are the objects that emerge from the third road. Controlling the vehicle's driving based on these objects helps to reduce the interaction risks when the vehicle is driving within the intersection.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the first road further includes a first lane, and the first lane is a lane for traveling towards the third road. The method further includes: when there is a moving object in the first lane, predicting the motion path of the moving object traveling towards the third road based on the angle between the boundary of the third road and the boundary of the first road; determining a first part based on the motion path, wherein the first part does not obstruct the moving object from traveling along the motion path.

[0015] In the above technical solution, the first part of the first path is planned based on the predicted movement path of other vehicles in the straight lane next to the lane where the vehicle is located before entering the intersection. This helps to reduce the obstruction of other vehicles in the straight lane next to the lane where the vehicle is located before entering the intersection during the process of the vehicle traveling along the first path, and can improve the traffic efficiency of traffic participants in the intersection.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: before the vehicle passes through the first conflict zone, a warning device controlling the vehicle provides first information, the first information being used to indicate to the first target object that the vehicle is in a yielding state.

[0017] In the above technical solution, the vehicle is prompted to give way to the first target object, so that the first target object understands the vehicle's intention to give way, reducing the probability of the first target object and the vehicle "stopping at the same time" (such as both showing the intention to give way to each other).

[0018] In conjunction with the first aspect, in some implementations of the first aspect, the navigation guidance information further instructs the vehicle to enter the fifth road from the second road via the second intersection, and the angle between the boundary of the second road and the boundary of the fifth road satisfies the first condition. The method further includes: acquiring obstacle information, which indicates the positional change of a second target object, the second target object being an object that poses a collision risk to the vehicle during its journey to the fifth road; when, based on the obstacle information, it is decided that the vehicle passes through the second conflict area before the second target object, the vehicle is controlled to travel along the second path; wherein, the second conflict area is the predicted area where the vehicle and the second target object will collide, the second path is a path determined based on the first position and the second position that is tangent to the extension lines of the second and third lanes, the first position is the position of entering the second intersection, the second position is the position of exiting the second intersection, the second lane is the lane in which the vehicle travels in the second road, and the third lane is the target lane in which the vehicle enters the fifth road.

[0019] In some implementations, the second path can be the shortest feasible curved path for the vehicle to travel from the starting point to the target point.

[0020] In the above technical solution, when deciding whether to overtake a target object, controlling the vehicle to travel along a path tangent to the extension of the vehicle's current lane and the extension of the target lane helps improve the traffic efficiency of the vehicle passing through the intersection, avoids the increased risk of collision between the vehicle and the target object caused by the vehicle traveling along other paths, and thus improves the safety of the vehicle passing through the intersection.

[0021] In conjunction with the first aspect, in some implementations of the first aspect, the curvature of the first part is zero.

[0022] In the above technical solution, when the curvature of the first part is zero, it helps to reduce the difficulty of planning the driving path and also helps to improve the human-likeness and rationality of the driving path when the vehicle is in autonomous driving mode.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, the included angle satisfying the first condition includes: the included angle is greater than or equal to 60° and less than or equal to 120°.

[0024] Secondly, a road turning device is provided, comprising an acquisition unit and a processing unit. The acquisition unit is used to: acquire navigation guidance information, which indicates that a vehicle needs to travel from a first road through a first intersection to a second road, and the angle between the boundary of the first road and the boundary of the second road satisfies a first condition; the processing unit is used to: control the vehicle to travel along a first path through the first intersection and into the second road according to the navigation guidance information; wherein the first intersection is a planar non-circular intersection, the first path includes a first part and a second part, the first part being closer to the first road than the second part, and the curvature of the second part being greater than the curvature of the first part.

[0025] In conjunction with the second aspect, in some implementations of the second aspect, the acquisition unit is further configured to: acquire obstacle information, the obstacle information indicating the positional change of the first target object, the first target object being an object that poses a collision risk with the vehicle during the vehicle's journey toward the second road; the processing unit is configured to: after making a decision about the vehicle based on the obstacle information, when the first target object passes through the first conflict area, control the vehicle to travel along the first path; wherein, the first conflict area is the area where the vehicle and the first target object are predicted to collide.

[0026] In conjunction with the second aspect, in some implementations of the second aspect, the first intersection is at least connected to the third road, and the moving object in the third road affects the path of the vehicle traveling from the first road to the second road. The straight lane of the third road corresponds to the opposite lane of the current lane where the vehicle is located, and the first target object is the object that drives out of the third road.

[0027] In conjunction with the second aspect, in some implementations of the second aspect, the first road further includes a first lane, and the first lane is a lane for traveling towards the third road. The processing unit is further configured to: when there is a moving object in the first lane, predict the motion path of the moving object traveling towards the third road based on the angle between the boundary of the third road and the boundary of the first road; determine a first part based on the motion path, wherein the first part does not obstruct the moving object from traveling along the motion path.

[0028] In conjunction with the second aspect, in some implementations of the second aspect, the processing unit is further configured to: before the vehicle passes through the first conflict zone, control the vehicle's prompting device to provide first information, the first information being used to indicate to the first target object that the vehicle is in a yielding state.

[0029] In conjunction with the second aspect, in some implementations of the second aspect, the navigation guidance information further instructs the vehicle to enter the fifth road from the second road via the second intersection, and the angle between the boundary of the second road and the boundary of the fifth road satisfies the first condition. The acquisition unit is further configured to: acquire obstacle information, the obstacle information indicating the positional change of the second target object, the second target object being an object that poses a collision risk to the vehicle during the vehicle's journey to the fifth road; when, based on the obstacle information, it is decided that the vehicle passes the second conflict area before the second target object, the vehicle is controlled to travel along the second path; wherein, the second conflict area is the predicted area where the vehicle and the second target object will collide, the second path is a path determined based on the first position and the second position that is tangent to the extension lines of the second lane and the third lane, the first position is the position of entering the second intersection, the second position is the position of exiting the second intersection, the second lane is the lane in which the vehicle travels in the second road, and the third lane is the target lane in which the vehicle enters the fifth road.

[0030] In conjunction with the second aspect, in some implementations of the second aspect, the curvature of the first part is zero.

[0031] In conjunction with the second aspect, in some implementations of the second aspect, the included angle satisfies the first condition, including: the included angle is greater than or equal to 60° and less than or equal to 120°.

[0032] Thirdly, a turning device for intersections is provided, the device comprising: a processor for executing a computer program stored in a memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0033] In conjunction with the third aspect, in some implementations of the third aspect, the device also includes a memory.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] In a seventh aspect, a vehicle is provided that includes means as in any possible implementation of the second to third aspects, or the vehicle includes computer-readable storage 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 computer program code as in any possible implementation of the fourth aspect.

[0039] 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.

[0040] For the beneficial effects not described in detail in aspects two through seven, please refer to the description in aspect one, which will not be repeated here. Attached Figure Description

[0041] Figure 1 is a functional schematic block diagram of the vehicle provided in an embodiment of this application;

[0042] Figure 2 is a schematic block diagram of the autonomous driving system architecture provided in an embodiment of this application;

[0043] Figure 3 is a schematic flowchart of the intersection turning method provided in the embodiment of this application;

[0044] Figure 4 is a schematic diagram of the application scenarios involved in the embodiments of this application;

[0045] Figure 5 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0046] Figure 6 is another schematic diagram of the application scenario provided in the embodiments of this application;

[0047] Figure 7 is another schematic diagram of the application scenario involved in the embodiments of this application;

[0048] Figure 8 is another schematic flowchart of the intersection turning method provided in the embodiments of this application;

[0049] Figure 9 is a schematic block diagram of the intersection turning device provided in an embodiment of this application;

[0050] Figure 10 is another schematic block diagram of the intersection turning device provided in the embodiments of this application. Detailed Implementation

[0051] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0052] 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 perception system 120 and a computing platform 150. In some implementations, the vehicle 100 may also include a prompting device 130. The perception system 120 may include several sensors for sensing information about the surrounding environment of the vehicle 100. For example, the perception system 120 may include a positioning system, which may be a Global Positioning System (GPS), a BeiDou system, or another positioning system. Furthermore, the perception 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.

[0053] 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.

[0054] The computing platform 150 can control the operation of the intelligent driving system, which may include an advanced driving assistance system (ADAS) and / or 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.

[0055] 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.

[0056] The prompting device 130 may include any of the following: a display device, a sound device, and a lighting device. The display device is mainly divided into two categories: the first is an in-vehicle display screen; the second is a projection display screen, such as a head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of the in-vehicle infotainment system. 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. A head-up display, also known as a head-up display system, is mainly used to display driving information such as speed and navigation on a display device (e.g., the windshield) in front of the driver. 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. Sound-generating devices may include in-vehicle speakers, in-vehicle audio systems, or external speakers, external audio systems. Lighting devices are used to display lights and may include external vehicle lights, such as headlights and pixelated headlights. More specifically, headlights include one or more of low beam headlights, high beam headlights, and turn signals. In some implementations, the lighting device may include one or more. Pixel-type vehicle lights may include, but are not limited to, lighting devices based on digital light processing (DLP) technology, lighting devices based on micro light emitting diode (Micro-LED) technology, or lighting devices based on liquid crystal display (LCD). Pixel-type vehicle lights can be used to project specific patterns onto the ground or buildings around the vehicle to alert other road users to relevant information.

[0057] 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 and a control module 220. Optionally, the system may also include a prompting module 230. Wherein:

[0058] 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 perception module 210 is used to collect information about the vehicle's surrounding environment, the vehicle's real-time motion parameters, etc. The perception module 210 can also process the collected surrounding environment information to build a world model of roads, obstacles, etc. for downstream modules (such as the planning and control module 220).

[0059] The planning and control module 220 may include one or more processors in the computing platform 150 shown in Figure 1. Specifically, the planning and control module 220 may include an interactive decision-making module 221, a motion planning module 222, and a control module 223. The interactive decision-making module 221 determines whether the path reference line for the vehicle when passing through the intersection is a first-type reference line or a second-type reference line, and then generates multiple trajectories for the vehicle to pass through the intersection based on the determined path reference line, and selects the optimal trajectory from the multiple trajectories and inputs it into the motion planning module 222. The motion planning module 222 plans the vehicle's driving trajectory through the intersection based on the optimal trajectory from the interactive decision-making module 221; the control module 223 controls the vehicle to pass through the intersection along this driving trajectory.

[0060] In some implementations, the interaction decision module 221 can also filter target objects that have an interactive relationship with the vehicle based on the positional changes of moving objects. For example, taking the traffic rule of driving on the right as an example, when the vehicle needs to turn left at an intersection, the moving object can include moving objects (such as vehicles) located in the opposite lane of the road where the vehicle was before entering the intersection; when the vehicle needs to turn right at an intersection, the moving object can include moving objects (such as pedestrians) located in the zebra crossing area corresponding to the target road. An interactive relationship between the target object and the vehicle can be understood as: the target object may affect the vehicle's driving trajectory, and / or, the vehicle may affect the trajectory of the target object. Furthermore, the interaction decision module 221 determines whether the vehicle should overtake or yield to the target object, and based on the game-theoretic decision result between the vehicle and the target object (such as the vehicle overtaking or yielding to the target object), determines the path reference line as either a first-type reference line or a second-type reference line.

[0061] The first type of reference line can be used as a reference line for a vehicle to drive straight for a certain distance after entering the intersection before turning. The second type of reference line is used as a reference line for a vehicle to turn directly after entering the intersection. In some implementations, the path reference line is the first type when the vehicle needs to yield to a target object; the path reference line is the second type when the vehicle needs to overtake a target object, or when there is no target object.

[0062] The prompting module 230 may include one or more of the prompting devices 130 shown in FIG1. ​​The prompting module 230 may prompt the target object with relevant information that the vehicle is yielding when the vehicle is yielding to the target object; the prompting module 230 may also prompt the target object that the vehicle is in a preemptive state when the vehicle decides to overtake the target object.

[0063] It should be understood that the above module is only an example, and in actual applications, the above module may be added or deleted according to actual needs.

[0064] 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.

[0065] Figure 3 shows a schematic flowchart of an intersection turning method provided in an embodiment of this application. This method 300 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 300 can be executed by the control module 220, and it may include some or all of the steps in S301 to S308 below.

[0066] S301, Obtain road topology information. The road topology information indicates the topological connection relationship between the current road, intersection 1 and the target road, as well as the boundaries of the lanes contained in the target road.

[0067] In some implementations, road topology information can be perceived by the vehicle's perception system; alternatively, it can be extracted from pre-made map data. Pre-made map data can be roadcode (RC) maps, electric horizon (EHP) data, etc.

[0068] For example, the pre-made map data can be generated based on traffic flow data. Here, traffic flow data can be understood as data consisting of the trajectories formed by one or more vehicles traveling on the road. A set of traffic flow data can include multiple traffic flow points, each traffic flow point indicating a coordinate in a vehicle's travel trajectory, the time when the vehicle arrived at this coordinate, and the vehicle's orientation pose at this coordinate.

[0069] Pre-built map data can include at least one of road vectors, intersection vectors, and lane vectors. For example, a processor segments and clusters traffic flow data to obtain road vectors. Further, for multiple roads intersecting at the same intersection, based on traffic flow data and road vectors, the vector points connecting each road to the intersection are determined, and the vector points corresponding to multiple roads constitute the intersection vector. The road width is determined based on traffic flow data, and the intersections of multiple sets of traffic flow data with the perpendicular lines from the roads are clustered. The number of lanes is determined based on the clustering results, and then the lane vectors are determined based on the road width and the number of lanes. It can be understood that lane vectors, road vectors, and intersection vectors constitute a vectorized map. Specifically, road vectors indicate the location and direction of a road segment, intersection vectors indicate the location and boundaries of intersections, and lane vectors indicate the roadway for various vehicles to travel within the same width. Alternatively, lane vectors can also indicate the position of each lane within a road segment.

[0070] It should be noted that intersection 1 is a non-roundabout intersection. "Non-roundabout" can be understood as the topological relationship between intersection 1 and its multiple connecting roads existing on the same plane; that is, a vehicle can enter any other connecting road from a road connected to intersection 1 within the plane of intersection 1. "Non-roundabout" means there is no central island at the intersection, meaning that vehicles going straight do not need to turn or only need a small turn when passing through the intersection. Taking the traffic rule of right-hand drive as an example, when a vehicle turns left to reach its destination road, its driving path is more flexible, unlike a roundabout where a specific path must be followed to enter the destination road. Furthermore, vehicles need to turn when moving from the current road to the destination road, for example, by turning left or right. That is, the angle between the boundary of the current road and the boundary of the destination road must meet certain conditions; for example, the angle between the boundary of the current road and the boundary of the destination road can be greater than or equal to 45° and less than or equal to 135°. More specifically, the angle between the boundary of the current road and the boundary of the target road can be greater than or equal to 60° and less than or equal to 120°. Where the boundary of the current road and / or the boundary of the target road is a curve, the angle between the boundary of the current road and the boundary of the target road can be: the angle between the tangent line of the boundary segment of the current road entering intersection 1 and the tangent line of the boundary segment of intersection 1 entering the target road. The aforementioned boundary segment can be any length from 3 meters to 5 meters, or it can be a boundary of other lengths.

[0071] It should also be noted that after a vehicle enters intersection 1, the current road refers to the road the vehicle was on before entering intersection 1, and the target road is the road the vehicle wants to enter through intersection 1.

[0072] S302, Obtain motion state information, the motion state information indicating the positional change of at least one moving object within the area 1 associated with intersection 1.

[0073] In some implementations, motion state information can be determined based on environmental perception information collected by the vehicle's perception system, which can indicate the positional changes of all moving objects within the range that the vehicle's perception system can perceive.

[0074] It is understandable that the direction and speed of a moving object can be determined based on its positional changes.

[0075] For example, area 1 associated with intersection 1 may include: an area within and / or near intersection 1 where moving objects can move, and where such moving objects may affect the vehicle's travel path. For instance, if the vehicle needs to turn left at intersection 1 to enter the target road, area 1 can be an area within intersection 1 where vehicles on road 1 can travel straight, where road 1 is the road corresponding to the opposite lane of the current lane, meaning vehicles in the straight lane of road 1 can travel straight into the opposite lane of the vehicle's current lane. As another example, if the target vehicle needs to turn right at intersection 1 to enter the target road, area 1 can be a pedestrian crossing area perpendicular to the target road.

[0076] Taking the application scenario shown in Figure 4 as an example, intersection 1 is the part within the short dashed box, that is, the short dashed box is the boundary of intersection 1. Road 1 can be the road where other vehicle 2 is located at time 1. When the target road is to the left of the vehicle and the vehicle needs to turn left to enter the target road, region 1 can be the region within the dashed box a; when the target road is to the right of the vehicle (not shown in the figure), and the vehicle needs to turn right to enter the target road, region 1 can be the region within the dashed box b.

[0077] As shown in Figure 4, vehicles 1 and 2 are traveling straight from road 1, attempting to enter the opposite lane of the user's current lane. Time 1 refers to a time prior to time 2. If the user, vehicles 1, and 2 reach the position shown in the figure at time 2, the user may stop at the position shown to allow vehicles 1 and 2 to pass. During this process, the user will obstruct the continued movement of vehicles behind it for an extended period, and the number of vehicles that can follow behind the user at the stopped position will be limited. If the traffic lights indicate that the left-turn lane is closed during this stop, only vehicles that have crossed the stop line will be able to pass through the intersection after the user begins to move. This will affect the traffic efficiency of vehicles behind the user, especially those that have not crossed the stop line. Therefore, when the user cannot overtake other road users in intersection 1, the path shown in Figure 4, where the user turns immediately upon entering intersection 1, is clearly detrimental to traffic efficiency and safety.

[0078] S303, based on motion state information, select target objects that have an interactive relationship with the vehicle from at least one moving object.

[0079] The interaction between the target object and the vehicle can be understood as: the vehicle influencing the trajectory of the target object, and / or the target object influencing the trajectory of the vehicle. It should be noted that in this embodiment, "path" can be understood as a curve composed of a series of coordinate points containing only location information; "trajectory" is obtained by overlaying time series information onto the path, i.e., "trajectory" is a curve composed of a series of coordinates containing both time and location information.

[0080] In some implementations, based on motion state information, the projected trajectory of each of the multiple moving objects is predicted. Then, based on the predicted projected trajectories of the moving objects and the multiple projected trajectories of the vehicle, at least one target object that affects the vehicle's decision is selected from the multiple moving objects.

[0081] In some implementations, the interaction risk between the vehicle and the moving object is determined by analyzing the projected trajectory of both the moving object and the vehicle itself. For example, multiple projected trajectories T are generated based on different accelerations, according to the vehicle's current position and the target position. i Each trajectory is assigned a different weight. i Among them, T1 to T i Let i represent the predicted trajectories of the vehicle, where i is a positive integer. Based on the current velocity and direction of motion of the moving object j, predict multiple predicted trajectories T of the moving object. jk And assign different weights w to each trajectory. jk , among which, T j1 To T jk These represent the k projected trajectories of the moving object j. For example, the weights w... i The deviation decreases as the deviation between the vehicle's projected trajectory and the straight line where the vehicle is currently facing increases. This deviation can be determined based on the maximum or average lateral offset between the projected trajectory and the straight line where the vehicle is currently facing. The larger the maximum or average lateral offset, the greater the deviation. Furthermore, ∑w i =1; weight w jk The value decreases as the deviation between the predicted trajectory of moving object j and its current position increases, and ∑w jk =1.

[0082] Furthermore, the weighted interaction risk corresponding to the moving object j is calculated. j risk j =∑w i ·w jk ·ri,jk .

[0083] Among them, the interaction risk r i,jk The trajectory T of the vehicle is represented. i The deduced trajectory T of the moving object j jk Interaction risks between them. For example, the interaction risk r i,jk Trajectory T can be deduced i and the deduced trajectory T jk Determining the closest distance between them, or the interaction risk r i,jk Trajectory T can also be deduced i and the deduced trajectory T jk The indicated TTC is determined.

[0084] Understandably, the deduced trajectory T i and the deduced trajectory T jk These can all be a series of shape points with time information, each shape point indicating the position of the vehicle or moving object at a certain moment. The aforementioned "closest distance" can be the extrapolated trajectory T. i The shape point corresponding to time a and the deduced trajectory T jk The distance between the points corresponding to time a, where time a is the nearest neighbor time before the two trajectories intersect. The aforementioned TTC can be calculated based on the deduced trajectory T. i and the deduced trajectory T jk The predicted time of collision between the vehicle and the moving object j is determined, and the time between the collision time and the current time is TTC. This is based on the projected trajectory T. i and the deduced trajectory T jk When it is determined that the vehicle and the moving object j will not collide, TTC is infinite.

[0085] In one example, the extrapolated trajectory T can be used. i and the deduced trajectory T jk The closest distance between them represents the interaction risk r i,jk If the interaction risk r i,jk Following the deduced trajectory T i and the deduced trajectory T jk The nearest distance between them decreases as risk increases. j As the value of increases, the influence of the moving object j on the vehicle increases. In another example, the trajectory T can be extrapolated. i and the deduced trajectory T jk The indicated TTC characterizes the interaction risk r i,jk If the interaction risk r i,jk It decreases as TTC increases, and then decreases with risk. j As the value of increases, the influence of the moving object j on the vehicle increases. In another example, the trajectory T can be extrapolated. iand the deduced trajectory T jk The nearest distance or TTC between them is quantified, for example, quantized into a dimensionless value, and then based on the dimensionless interaction risk r. i,jk Determine the risk j In another example, the interaction risk (r) can also be determined in other ways. i,jk .

[0086] In some implementations, the weighted interaction risks of multiple moving objects can be sorted, and the top n moving objects with higher weighted interaction risks can be selected as target objects. In other implementations, the n moving objects with weighted interaction risks greater than or equal to a risk threshold can be selected as target objects. Here, n is an integer greater than or equal to 1.

[0087] In one example, the lateral path of a moving object can be derived using the following formula:

[0088] Among them, s e This is the longitudinal position (unit: m) of the moving object at the moment of lateral path calculation, and this position changes with the calculation time. l(s) e ) is the longitudinal position s of the moving object. e Corresponding lateral offset (unit: m); s e ST is the starting longitudinal position of the moving object (unit: m). This starting longitudinal position can be understood as the position of the moving object in the direction parallel to the X-axis of the vehicle coordinate system at the moment when the path calculation begins; C1 is the offset corresponding to the current orientation of the moving object (unit: m); s e CT is the longitudinal position at the end of the cubic curve connection (unit: m); C2 is the lateral offset at the end of the cubic curve connection of the moving object (unit: m), and C2 can be the minimum or maximum lateral offset of the moving object during the simulation process (preset); s e ST and s e The CT can be dynamically adjusted based on the vehicle type and the degree of aggression of the moving object. For example, when the moving object is a large vehicle, s e ST and s e When the CT value is large; and / or the degree of aggression of the moving object is high, s e ST and s e The CT value is relatively small. From (s) e ST,C1) to (s e CT,C2) uses cubic curves to connect paths, and the cubic curves are in (s e ST,C1) and (s eThe tangent at CT,C2) is parallel to the direction of the vehicle's travel. Here, a, b, c, and d are the coefficients of a cubic polynomial, and their specific values ​​can be determined based on the type of the moving object and its degree of aggression.

[0089] During the longitudinal path deduction of a moving object, the change in the longitudinal acceleration of the moving object with the deduction time can include at least one of the following four segments: (1) Time delay segment (t∈[0,delayTime)): longitudinal path deduction is performed based on the current acceleration of the moving object; (2) Uniform acceleration rate of change segment (t∈[delayTime,jerkChangeTime), hereinafter referred to as uniform Jerk segment): the acceleration rate of change is determined according to the acceleration at the beginning of the uniform Jerk segment and the deduction acceleration, and longitudinal path deduction is performed according to uniform Jerk; (3) Uniform acceleration segment (t∈[jerkChangeTime,speedLimitTime)): path deduction is performed while maintaining the deduction acceleration; (4) Uniform speed segment (t≥speedLimitTime): when the deduction speed reaches the upper or lower bound speed, the path deduction is performed while maintaining the upper or lower bound speed. It should be noted that the above uniform Jerk segment can be a process of linearly increasing acceleration or a process of linearly decreasing acceleration. Among them, the deduction acceleration can be -4m / s². 2 Up to 3m / s 2 One of the values. For example, for the same lateral path, the extrapolated acceleration can be taken as -4, -3, -2, -1, 0, 1, 2, and 3 m / s². 2 This yields 8 vertical paths, which are then merged with the horizontal paths to obtain 8 projected trajectories.

[0090] In another example, taking the vehicle entering the target road from multiple locations as an example, a lateral path for the vehicle to travel from the current road to that location can be generated for each location; furthermore, multiple longitudinal paths can be determined based on the aforementioned method, and then the multiple lateral paths and multiple longitudinal paths can be merged to obtain multiple projected trajectories of the vehicle.

[0091] S304, Determine if the target object exists.

[0092] Specifically, if the target object exists, execute S305; otherwise, execute S308.

[0093] S305, generate a first type of reference line and a second type of reference line, generate a type A trajectory based on the first type of reference line, and generate a type B trajectory based on the second type of reference line; wherein, the first type of reference line is the reference line for going straight before turning at the entrance, and the second type of reference line is the reference line for turning directly at the entrance.

[0094] For example, a first type of reference line may include two parts, each with a different curvature or rate of change of curvature, wherein the curvature or rate of change of curvature of the part closer to the target road is greater than that of the part farther from the target road. More specifically, the curvature of the part farther from the target road may be zero, that is, the reference line of the part farther from the target road is a straight line.

[0095] In some implementations, the first type of reference line can be generated based on the following steps (a) to (e):

[0096] (a) Determine the starting point and the target point: Take the current position of the vehicle as the starting point and the center point of the target lane when entering the target road from intersection 1 as the target point.

[0097] The target lane can be a lane determined based on navigation guidance information, or it can be a lane determined based on preset rules (such as the left-hand lane on the target road). It should be noted that the navigation guidance information is information indicating the route the vehicle takes to its destination, and this information can be determined based on the vehicle's starting or current location and the destination.

[0098] (b) Determine the corner point: Based on the vehicle's pose at the starting point (the angle between the vehicle's longitudinal axis and the current road boundary), determine line 1. Based on the vehicle's target pose at the target point, determine line 2. The intersection of line 1 and line 2 is the corner point. Taking the application scenario shown in Figure 5 as an example, where the traffic rule is to drive on the right and the vehicle needs to turn left to enter the target road, the specific corner point location is shown in Figure 5.

[0099] For example, the vehicle's pose at the target point can be such that the angle between the vehicle's longitudinal axis and the target road boundary is 0°. The vehicle's pose at the starting point can be determined based on the vehicle's steering direction:

[0100] In one example, when the traffic rule is to drive on the right and the vehicle needs to turn left to enter the target road, the vehicle's pose at the starting point can be determined based on the angle between the boundary of road 1 and the boundary of the current road. For example, the vehicle's pose at the starting point can be a pose where the vehicle's longitudinal axis is parallel to the boundary of road 1; or, the vehicle's pose at the starting point can be a pose where the vehicle's longitudinal axis is deflected counterclockwise by a certain angle relative to the boundary of road 1. This certain angle can be a value less than or equal to 5°, or it can be any other value. For example, the angle between the straight line in the solid line in Figure 6 and the boundary of the current road is determined based on road 1 to avoid the vehicle obstructing another vehicle a traveling along trajectory a while traveling along the straight line. Furthermore, the aforementioned certain angle cannot be too large to avoid the vehicle obstructing another vehicle traveling along trajectory b while traveling along the straight line.

[0101] In another example, when the traffic rule is to drive on the right and the vehicle needs to turn right to enter the target road, the vehicle's pose at the starting point can be a pose where the vehicle's longitudinal axis is deflected clockwise by a certain angle relative to the boundary of road 1. For example, this certain angle can be a value less than or equal to 5°, or it can be other values.

[0102] (c) Determine the inflection point: The coordinates of the inflection point in the world coordinate system are (x...). turnPoint y turnPoint Specifically, the x and y coordinates of the inflection points satisfy the following formulas: x turnPoint =xstartPoint+diststartToTurnPoint*cos(θstartPoint); y turnPoint =ystartPoint+diststartToTurnPoint*sin(θstartPoint);

[0103] Where xstartPoint and ystartPoint are the x and y coordinates of the starting point in the world coordinate system, respectively; diststartToTurnPoint is the distance from the starting point to the inflection point; and θstartPoint is the vehicle's orientation angle at the starting point. diststartToTurnPoint can be determined by the following formula: diststartToTurnPoint = (diststartToCornerPoint - distturnToCornerPoint); α=(0.5*(π-(θ turnPoint -θ goalPoint )); θ turnPoint =θstartPoint;

[0104] Where, θ turnPoint Let θ be the vehicle's heading angle at the inflection point. goalPoint Let be the vehicle's orientation angle at the target point, diststartToCornerPoint be the distance from the starting point to the corner point, distturnToCornerPoint be the distance from the turning point to the corner point, abs(m) be the absolute value of m, and max(r1,r2) be the maximum value between r1 and r2. Specifically, r1 and r2 are the vehicle's current speed v. ego The maximum achievable turning radius is determined by the bicycle model of the vehicle, and the turning radius that can be achieved when the front wheel steering angle of the vehicle is θ at the current moment. Here, the current moment can be the start time of the current inference frame, and r1 and r2 can satisfy the following formulas respectively:

[0105] Where μ is the road surface adhesion coefficient (or road surface friction coefficient), g is the gravitational acceleration, and L is the vehicle wheelbase.

[0106] (d) Using a preset function, connect the starting point, inflection point, and target point sequentially to generate a first-type reference line from the starting point to the target point. In this first-type reference line, the section from the starting point to the inflection point is a straight line, and the section from the inflection point to the target point is a curve.

[0107] For example, the aforementioned preset function can be a planar spiral or other functions. For instance, the aforementioned preset function can be the spiral2 function, whose mathematical expression is: r′=a*cos(2*θ′), where r′ is the polar radius, θ′ is the polar angle, and a is a constant.

[0108] In some implementations, to make the connected curves less prone to deformation (such as bulges), inflection point extension points and target point extension points can be extended along the directions of the inflection point and the target point, respectively. Then, a preset function is used to connect the starting point, inflection point, inflection point extension point, target point, and target point extension point in sequence to obtain the first type of reference line.

[0109] (e) Feasibility verification:

[0110] It should be noted that the "feasibility" or "practicability" involved in this application refers to whether the relevant reference line or path is suitable for vehicle driving and whether it meets the vehicle's kinematic constraints. When the relevant reference line or path meets the vehicle's kinematic constraints, enabling the vehicle to drive along the relevant path or reference line, then the path or reference line is determined to be feasible for the vehicle.

[0111] For example, the drivable area of ​​the vehicle is determined based on the boundary of intersection 1, static obstacles within intersection 1, and the kinematic constraints of the vehicle. The feasibility of the first type of reference line generated in step (d) is then checked. If the vehicle can drive along the first type of reference line within the drivable area, the first type of reference line is determined to meet the feasibility check; otherwise, the reference line is determined not to meet the feasibility check.

[0112] If the reference line does not meet the feasibility check, the starting point and target point remain unchanged, and the distance from the inflection point to the starting point is shifted along the straight line to obtain a new inflection point. Then, steps (d) and (e) are executed until a first-class reference line that meets the feasibility check is obtained.

[0113] Furthermore, multiple Class A trajectories are generated based on the first type of reference line and the different speeds and accelerations of the vehicles. Among these multiple Class A trajectories, at least one trajectory indicating that the vehicle yields to the target object is included.

[0114] In some implementations, a second type of reference line is generated based on the aforementioned starting point and target point. This second type of reference line can be the shortest turning curve among all drivable paths from the starting point to the target point. Furthermore, multiple type B trajectories are generated based on the second type of reference line and the different vehicle speeds and accelerations. These multiple type B trajectories may include at least one trajectory of the vehicle overtaking the target object.

[0115] For example, the first type of reference line and the second type of reference line can be represented by solid curves and dashed curves, respectively, as shown in Figure 5.

[0116] It should be noted that, in this application, "a preempts b" can be understood as: a passes through the conflict zone before b; "a yields to b" can be understood as: a passes through the conflict zone after b. The conflict zone is the area where a and b are predicted to collide.

[0117] S306, Determine whether trajectory 1 is the optimal trajectory.

[0118] Trajectory 1 can be one of the Class A trajectories.

[0119] For example, after obtaining all Class A and Class B trajectories, the trajectory with the best overall evaluation can be determined from the Class A and Class B trajectories based on factors such as safety, comfort, and traffic efficiency corresponding to each trajectory.

[0120] For example, if the overall evaluation of safety, comfort, and traffic efficiency is better when the vehicle tries to overtake the target object based on a Class B trajectory (such as trajectory 2), then the decision is made for the vehicle to overtake the target object along that Class B trajectory, and S308 is executed. If the overall evaluation of safety, comfort, and traffic efficiency is better when the vehicle yields to the target object based on a Class A trajectory (such as trajectory 1), then the decision is made for the vehicle to yield to the target object along that Class A trajectory. Safety can be characterized by the distance (or time interval) between the closest points of the aforementioned trajectories and the target object's derived trajectories; the greater the distance (or time interval), the better the safety. Comfort can be characterized by the maximum acceleration (or maximum deceleration) of the vehicle in the aforementioned trajectories; the greater the maximum acceleration (or the absolute value of the maximum deceleration), the worse the comfort. Traffic efficiency can be characterized by the total time required for the vehicle and / or the target object to pass through the conflict area; the shorter the total time, the higher the traffic efficiency. The method for obtaining the derived path of the target object can be referred to the description in S303, and will not be repeated here.

[0121] In some implementations, multiple Class A trajectories may include at least one trajectory in which the vehicle overtakes the target object, and multiple Class B trajectories may include at least one trajectory in which the vehicle yields to the target object. Understandably, because a vehicle needs to travel a longer distance to overtake a target object based on a Class A trajectory, its traffic efficiency is lower than that of a Class B trajectory; and because a vehicle yields to a target object based on a Class B trajectory, it obstructs following vehicles more significantly, potentially affecting the overall traffic efficiency on the road. Therefore, trajectories in which a vehicle overtakes a target object based on a Class A trajectory or yields to a target object based on a Class B trajectory are generally not optimal trajectories.

[0122] In some implementations, if there are other lanes besides the target lane on the target road, a reference line can be generated based on the aforementioned starting point and each of the other at least one lane, as shown in reference line 3 in Figure 7. Two trajectories are then generated based on these reference lines: one for the vehicle to overtake the target object, and the other for the vehicle to yield to the target object. Further, the optimal trajectory is determined from the aforementioned multiple Class A and Class B trajectories, as well as the Class 2 trajectories generated based on reference line 3 (including the overtaking trajectory and the yielding trajectory). If the optimal trajectory is not a Class A or Class B trajectory, steps S307 and S308 are not executed, and the vehicle's travel trajectory towards the target road is planned based on the optimal trajectory.

[0123] It should be noted that the aforementioned embodiment in S306 uses one target object as an example for illustration. In actual implementation, there may be multiple target objects. More specifically, multiple driving strategies can be determined based on the movement direction of each target object and the position of each target object relative to the vehicle. Each driving strategy instructs the vehicle to make a driving decision for each target object among the multiple target objects. This driving decision instructs the vehicle to either overtake or yield to the target object longitudinally, and to either circumvent or circumvent the target object laterally, or to maintain centering. Specifically, circumventing to the left means the vehicle moves to the left to avoid the target object, i.e., when the vehicle passes the target object, the target object is located to the right of the vehicle; circumventing to the right means the vehicle moves to the right to avoid the target object, i.e., when the vehicle passes the target object, the target object is located to the left of the vehicle. For example, the left and right sides of the vehicle can be defined relative to the vehicle's vehicle coordinate system. For instance, the positive direction of the Y-axis is the left side of the vehicle, and the negative direction of the Y-axis is the right side of the vehicle.

[0124] For example, the lateral and longitudinal directions can be determined relative to the vehicle's driving direction or the vehicle's coordinate system. For instance, the longitudinal direction can be parallel to the vehicle's driving direction, and the lateral direction can be perpendicular to the vehicle's driving direction. Alternatively, the longitudinal direction can be parallel to the X-axis of the vehicle's coordinate system, and the lateral direction can be parallel to the Y-axis of the vehicle's coordinate system. It should be noted that the origin O of the vehicle coordinate system can be located at the projection point of the rear axle center of the vehicle onto the ground, and the positive directions of the X and Z axes can be the direction of the vehicle's front end and the direction perpendicular to the vehicle's plane, respectively.

[0125] Taking at least one target object and n target objects as an example, since the vehicle can make six driving decisions for each target object (such as detouring left and overtaking, detouring right and overtaking, maintaining the center and overtaking, detouring left and yielding, detouring right and yielding, and maintaining the center and yielding), for n target objects, six driving decisions can be determined. n Each driving strategy is further defined. For each driving strategy, the driving decisions for each target object within the strategy, as well as other static and dynamic obstacles on the road, are used as constraints to deduce the predicted paths for n target objects and the planned paths for the vehicle.

[0126] Furthermore, taking n target objects, including 2 objects, as an example, 36 driving strategies can be obtained for these 2 target objects. Based on the aforementioned driving strategies, 36 Class A trajectories and 36 Class B trajectories are generated for the vehicle from the starting point to the target point. The trajectory with the best comprehensive evaluation of safety, comfort, and traffic efficiency is selected from the aforementioned 72 trajectories. If the optimal trajectory is a Class A trajectory, then S307 is executed; if the optimal trajectory is a Class B trajectory, then S308 is executed.

[0127] It should be noted that in actual implementation, several feasible driving decisions can be determined from the six driving strategies based on the target object's position relative to the vehicle and the target object's speed, thus saving the computational power required to determine the optimal trajectory. For example, if the predicted path of the target object intersects with the vehicle's path, and the predicted path of the target object is from the left to the right of the vehicle, then driving decisions such as detouring to the left and overtaking, or detouring to the right and yielding are not reasonable. Therefore, the driving strategy for this target object can be simplified to four: maintain centering and overtake, maintain centering and yield, detouring to the left and yielding, and detouring to the right and overtaking.

[0128] S307, control the vehicle to travel towards the target road according to trajectory 1.

[0129] In one example, the vehicle is controlled to travel along trajectory 1 toward the target road; in another example, the vehicle's planning and control module uses trajectory 1 as a guide to plan the trajectory and controls the vehicle to travel along the planned trajectory so that the vehicle passes through the conflict area behind the target object.

[0130] S308, control the vehicle to travel towards the target road according to trajectory 2.

[0131] In one example, the vehicle is controlled to travel along trajectory 2 toward the target road; in another example, the vehicle's planning and control module uses trajectory 2 as a guide to plan the trajectory and controls the vehicle to travel along the planned trajectory so that the vehicle passes through the conflict area before the target object.

[0132] In some implementations, when a vehicle yields to a target object, it can project a first type of prompt message onto the ground using pixelated headlights, or it can display the first type of prompt message on an external display screen to indicate to the target object that the vehicle is in a yielding state. For example, the first type of prompt message includes the text "Yielding, please proceed" and an icon indicating the direction of passage. When a vehicle tries to overtake a target object, it can project a second type of prompt message onto the ground using pixelated headlights, or it can display the second type of prompt message on an external display screen to indicate to the target object that the vehicle is in a yielding state. For example, the second type of prompt message includes the text "Normal driving, please give way" and a warning icon.

[0133] In some implementations, when the vehicle yields to a target object, a notification device (such as a display device or an audio device) in the vehicle's cabin can also display a notification indicating that the vehicle is in a yielding state; when the vehicle ends its yielding state, the notification device in the vehicle's cabin can also display a notification indicating that the vehicle has ended its yielding state, so that the driver and passengers of the vehicle are aware of the vehicle's status. Furthermore, the vehicle's display device can also display the planned route the vehicle takes when passing through intersection 1.

[0134] The intersection turning method provided in this application can improve the human-likeness of the driving trajectory of a vehicle when it is in autonomous driving mode through an intersection, avoid the vehicle stopping too early in the intersection and blocking the traffic in the intersection, help improve the efficiency of vehicle passage in the intersection and the traffic flow of the intersection, and reduce the risk of collision caused by other vehicles overtaking when the vehicle stops.

[0135] Figure 8 shows another schematic flowchart of the intersection turning method provided in the embodiments of this application. This method can be executed by the vehicle 100 shown in Figure 1, or it can be executed by the control module 220 shown in Figure 2. The method 800 includes:

[0136] S810, obtain navigation guidance information. The navigation guidance information indicates that the vehicle needs to travel from the first road through the first intersection to the second road. The angle between the boundary of the first road and the boundary of the second road satisfies the first condition.

[0137] For example, the first road can be the current road in method 300, and the second road can be the target road in method 300.

[0138] In some implementations, the included angle satisfies the first condition: the included angle is greater than or equal to 60° and less than or equal to 120°.

[0139] In some implementations, the first intersection can be an N-way intersection, where N is an integer greater than or equal to 3. For example, the first intersection can be a T-junction, a crossroads, etc., and vehicles must turn within the first intersection to enter the second road.

[0140] S820, according to navigation guidance information, controls the vehicle to enter the target road through the first intersection along the first path; wherein, the first intersection is a non-roundabout intersection, the first path includes a first part and a second part, the first part is closer to the first road than the second part, and the curvature of the second part is greater than the curvature of the first part.

[0141] In some implementations, the curvature of the first part is zero.

[0142] In some implementations, the first path can be a path planned based on trajectory 1 and / or the first type of reference line in the aforementioned method 300, generating the first type of reference line, and a method for determining trajectory 1 and performing path or trajectory planning based on the first type of reference line, which can be referred to the description in method 300 and will not be repeated here. For example, the first part can be the part corresponding to the straight line part in the aforementioned first type of reference line, and the second part can be the part corresponding to the curved part (i.e., the curvature is not zero) in the aforementioned first type of reference line.

[0143] In some implementations, the method further includes: acquiring obstacle information, which indicates the positional change of a first target object, the first target object being an object that poses a collision risk with the vehicle during its journey to the second road; controlling the vehicle to travel along the first path through the first intersection into the second road, including: after making a decision about the vehicle based on the obstacle information and when the first target object passes through the first conflict area, controlling the vehicle to travel along the first path; wherein the first conflict area is the area where a collision between the vehicle and the first target object is predicted.

[0144] For example, the first target object may include at least one target object in method 300. The existence of a collision risk between the first target object and the vehicle can be understood as: the interaction risk between the first target object and the vehicle is greater than a certain threshold. For a more specific implementation of filtering the first target object, please refer to the description in S303; for the specific implementation of deciding whether the vehicle passes through the first conflict area after the first target object, please refer to the description in S306, which will not be repeated here.

[0145] It should be noted that, during the process of controlling the vehicle to travel along the first path, if it is detected that the target object intends to give way to the vehicle, or if it is deduced that the target object's speed has slowed down so that the target object cannot pass through the conflict area before the vehicle, then the vehicle can also pass through the conflict area before the target object along the first path.

[0146] In some implementations, the first intersection is connected to at least the third road, and moving objects in the third road affect the path of vehicles traveling from the first road to the second road. The straight lanes of the third road correspond to the opposite lanes of the current lane in which the vehicle is located, and the first target object is an object that exits from the third road.

[0147] For example, the topological relationship between the first intersection and the road can be determined based on road topology information, which can be the road topology information in method 300. Taking the first intersection as intersection 1 in method 300, and the first road and the second road as the first road and the second road in method 300, respectively, the third road can be road 1 in method 300. More specifically, the straight lane of the third road corresponds to the opposite lane of the current lane where the vehicle is located. This can be understood as: a vehicle traveling in the straight lane of the third road can enter the opposite lane of the current lane via the first intersection.

[0148] For example, taking a traffic rule indicating driving on the right as an example, a vehicle turns left at the first intersection to enter the second road. The first target object can be a moving object that is going straight or turning left from the third road.

[0149] In some implementations, when traffic rules indicate driving on the right and the vehicle turns right at the first intersection to enter the second road, the first target object can be one or more moving objects near the boundary of the first intersection parallel to the first road, whose direction of movement is parallel to the first road. For example, the first target object may include the moving object within the dashed box b in Figure 4 whose direction of movement is parallel to the direction of the road where the vehicle is at time 1.

[0150] In some implementations, the first road further includes a first lane, and the first lane is a lane for traveling to the third road. The method further includes: when there is a moving object in the first lane, predicting the motion path of the moving object to travel to the third road based on the angle between the boundary of the third road and the boundary of the first road; determining a first part based on the motion path, the first part not hindering the moving object from traveling along the motion path.

[0151] For example, the first lane can be the lane where vehicle a is located as shown in Figure 6, and the movement path of the moving object traveling towards the third road can be the path corresponding to trajectory a.

[0152] In some implementations, the method further includes: before the vehicle passes through the first conflict zone, a warning device controlling the vehicle provides first information to the first target object, the first information being used to indicate that the vehicle is in a yielding state.

[0153] For example, the first information may be the first type of prompt information in method 300. For a more specific implementation of the prompting device controlling the vehicle to prompt the first information, please refer to the description in method 300, which will not be repeated here.

[0154] In some implementations, the navigation guidance information further instructs the vehicle to enter the fifth road from the second road via the second intersection, and the angle between the boundary of the second road and the boundary of the fifth road satisfies a first condition. The method also includes: acquiring obstacle information, which indicates the positional change of a second target object, the second target object being an object that poses a collision risk to the vehicle during its journey to the fifth road; and controlling the vehicle to travel along the second path when, based on the obstacle information, the vehicle passes the second conflict area before the second target object. The second conflict area is the predicted area where the vehicle and the second target object will collide, the second path is a path determined based on the first and second positions and tangent to the extension lines of the second and third lanes, the first position is the position entering the second intersection, the second position is the position exiting the second intersection, the second lane is the lane the vehicle travels in on the second road, and the third lane is the target lane the vehicle will enter on the fifth road.

[0155] For example, the second path can be a driving path planned based on the aforementioned trajectory 2 and / or the second type of reference line.

[0156] It should be noted that, during the process of controlling the vehicle to travel along the second path, if it is detected that the target object intends to overtake the vehicle, or if it is deduced that the target object's speed increases to the point that the vehicle cannot pass the conflict area before the target object, then the vehicle can also pass the conflict area before the target object along the second path 1.

[0157] The intersection turning method provided in this application controls the vehicle to travel along the first path when the vehicle turns in the intersection to enter the second road. This avoids the vehicle stopping too early in the intersection and obstructing the following vehicle in the lane where the vehicle was before entering the intersection, and / or vehicles entering the opposite lane from the lane where the vehicle was before entering the intersection. Therefore, it helps to reduce the probability of collision between the vehicle and other vehicles and can improve the traffic efficiency in the intersection.

[0158] It should be noted that the intersection turning method provided in this application is described in the foregoing embodiments using the traffic rule of driving on the right as an example. In actual implementation, the intersection turning method provided in this application can also be applied to scenarios where the traffic rule is driving on the left. When the method of this application is applied to scenarios where the traffic rule is driving on the left, the method for planning the driving trajectory of the vehicle can refer to the description in the foregoing embodiments, and will not be repeated here.

[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 intersection turning method provided by the embodiments of this application has been described in detail above with reference to Figures 1 to 8. The apparatus provided by the embodiments of this application will now be described in detail below with reference to Figures 9 and 10. It should be understood that the description of the apparatus embodiments corresponds to the description 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 9 shows a schematic block diagram of an intersection turning device 2000 provided in an embodiment of this application. The device 2000 may include units for executing the embodiments described in the foregoing method. Furthermore, each unit in the device 2000 implements a corresponding process of the above-described 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 are capable of implementing the corresponding steps performed by the computing platform 150 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 processing units, 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 control module 220. 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 10 is another schematic block diagram of the intersection turning device provided in the embodiments of this application. The device 2100 shown in Figure 10 may include: a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, transceiver 2120, and memory 2130 are connected via internal connection 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 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 scope of the technology 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.

Images