Vehicle control method and device, electronic equipment and autonomous vehicle

Abstract

The present disclosure provides a vehicle control method and device, electronic equipment and an autonomous vehicle. It relates to the field of artificial intelligence, and in particular to the field of autonomous driving. The specific implementation scheme is: determining a target lane based on environment information in which a vehicle is located; generating a virtual obstacle for the target lane; predicting a driving speed of the virtual obstacle; and controlling a driving speed of the vehicle in combination with the driving speed of the virtual obstacle. According to the scheme of the present disclosure, the driving speed of the vehicle can be reasonably controlled, and the safety of vehicle driving is improved.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, and in particular to the field of autonomous driving. Background Technology

[0002] In the field of autonomous driving, due to the limited perception range of autonomous vehicles, multiple blind spots may appear in complex road conditions, making it impossible for the vehicle to plan a reasonable driving speed based on the information it receives. Furthermore, these blind spots may contain unpredictable obstacles, potentially leading to collisions. Therefore, improving vehicle driving safety has become a pressing technical problem that needs to be solved. Summary of the Invention

[0003] This disclosure provides a vehicle control method, apparatus, electronic device, and autonomous vehicle.

[0004] According to a first aspect of this disclosure, a vehicle control method is provided, comprising:

[0005] Determine the target lane based on the vehicle's surrounding environment information;

[0006] Generate virtual obstacles for the target lane;

[0007] Predict the speed of virtual obstacles;

[0008] The vehicle's speed is controlled by combining the speed of virtual obstacles.

[0009] According to a second aspect of this disclosure, a vehicle control device is provided, comprising:

[0010] The determination module is used to determine the target lane based on the environmental information of the vehicle.

[0011] The generation module is used to generate virtual obstacles for the target lane;

[0012] The prediction module is used to predict the speed of virtual obstacles.

[0013] The control module is used to control the vehicle's speed by combining the speed of the virtual obstacles.

[0014] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] The memory is communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method provided in the first aspect above.

[0018] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method provided in the first aspect above.

[0019] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided in the first aspect described above.

[0020] According to a sixth aspect of this disclosure, a vehicle is provided, including the electronic equipment provided in the third aspect above.

[0021] According to the seventh aspect of this disclosure, an autonomous vehicle is provided, including the electronic equipment provided in the third aspect above.

[0022] According to the technical solution disclosed herein, the vehicle's speed can be reasonably controlled, thereby improving the safety of vehicle driving.

[0023] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of this application will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0024] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0025] Figure 1 This is a blind spot illustration according to an embodiment of the present disclosure. Figure 1 ;

[0026] Figure 2 This is a schematic flowchart of a vehicle control method according to an embodiment of the present disclosure;

[0027] Figure 3 This is a schematic diagram of an intersection scene according to an embodiment of the present disclosure. Figure 1 ;

[0028] Figure 4 This is a schematic diagram of an intersection scene according to an embodiment of the present disclosure. Figure 2 ;

[0029] Figure 5 This is a schematic diagram of the blind zone according to an embodiment of the present disclosure. Figure 2 ;

[0030] Figure 6 This is a schematic diagram of a function representing the characteristics of the handling behavior at an intersection where an accident has occurred, according to an embodiment of this disclosure;

[0031] Figure 7 This is a schematic diagram of the vehicle control architecture according to an embodiment of the present disclosure;

[0032] Figure 8 This is a schematic diagram of the structure of a vehicle control device according to an embodiment of the present disclosure;

[0033] Figure 9 This is a schematic diagram of a vehicle control scenario according to an embodiment of the present disclosure;

[0034] Figure 10 This is a block diagram of an electronic device used to implement the vehicle control method of the embodiments of this disclosure. Detailed Implementation

[0035] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0036] The terms "first," "second," and "third," etc., used in the embodiments, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as including a series of steps or units. A method, system, product, or apparatus is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0037] Before introducing the technical solutions of the embodiments of this disclosure, the technical terms that may be used in this disclosure will be further explained:

[0038] Main vehicle: Autonomous vehicle.

[0039] Obstacle vehicles: Other vehicles encountered by autonomous vehicles.

[0040] Blind spot: Due to the obstruction of obstacles, the main vehicle cannot obtain environmental information at the obstruction point through existing sensing technology. For the main vehicle, the obstructed area is a blind spot.

[0041] High-precision maps are used to describe the topology of roads, including road connections, relative road positions, and lanes controlled by traffic lights.

[0042] V2X: Vehicle to Everything, which refers to the exchange of information between vehicles and the outside world. It enables communication between vehicles, between vehicles and base stations, and between base stations.

[0043] Human drivers encounter blind spots caused by obstacles, making it difficult for them to clearly perceive traffic conditions within these areas. In such situations, human drivers typically employ strategies like slowing down to drive cautiously. Similarly, autonomous vehicles also encounter blind spots created by obstacles obscuring their own perception systems, requiring specialized methods to navigate these blind spots.

[0044] In related technologies, there are generally two ways to solve the blind spot problem: the first is to use V2X technology to eliminate blind spots, and the other is to identify blind spots and take corresponding actions through the host vehicle's strategy.

[0045] Eliminating blind spots using V2X technology: Because V2X communicates between vehicles, between vehicles and base stations, and between base stations, it fundamentally eliminates the problem of blind spots; in other words, blind spots no longer exist. When an obstacle obstructs a vehicle's own perception system, the vehicle cannot perceive traffic information in the obstructed area. However, using V2X technology, if other obstacles exist in the obstructed area, these obstacles will use V2X technology to emit signals that let the vehicle know of their presence. Therefore, the area obstructed by the obstacle is not a blind spot for the vehicle, fundamentally eliminating the blind spot problem.

[0046] The system identifies blind spots and takes corresponding actions based on the master vehicle's strategy: when the master vehicle detects an obstacle, the master vehicle's position and the obstacle's width boundary point can form a triangle. The blind spot is the extended area of ​​the line connecting the master vehicle and the obstacle's width boundary, such as... Figure 1 As shown. Once the main vehicle detects the blind spot, it will take driving actions such as slowing down, changing lanes, and lateral movement within the lane, based on the location of the blind spot and the surrounding road conditions.

[0047] While V2X can completely eliminate blind spots, its application requires the installation of V2X base stations on roads and the installation of relevant equipment in autonomous vehicles. Due to high costs and immature technology, the number of roads and vehicles equipped with V2X is currently very limited, resulting in very limited application scenarios for completely eliminating blind spots using V2X.

[0048] By identifying blind spots and taking corresponding actions based on the driver's strategy, the autonomous vehicle can encounter numerous obstacles in complex road scenarios. Each obstacle obscures a certain area, creating a blind spot. If cautious driving measures are taken for every blind spot, the vehicle's maneuverability will be significantly reduced. Furthermore, the classification of different blind spots is inherently complex, making it difficult to distinguish which blind spots require slowing down or lane changes. This can easily lead to unnecessary lane changes, reducing driving rationality and placing the autonomous vehicle in a more dangerous environment.

[0049] In order to at least partially solve one or more of the above-mentioned problems and other potential problems, this disclosure proposes a vehicle control method that can improve the rationality of the planned vehicle speed, thereby improving the safety of vehicle driving.

[0050] This disclosure provides a vehicle control method. Figure 2 This is a schematic flowchart of a vehicle control method according to an embodiment of the present disclosure. This vehicle control method can be applied to a vehicle control device. The vehicle control device is located in an electronic device, which can be part of the vehicle or independent of the vehicle but capable of communicating with it. The electronic device includes, but is not limited to, fixed devices and / or mobile devices. For example, fixed devices include, but are not limited to, servers, which can be cloud servers or ordinary servers. Mobile devices include, but are not limited to, one or more of the following: mobile phones, tablets, and in-vehicle terminals. In some possible implementations, the vehicle control method can also be implemented by a processor calling computer-readable instructions stored in memory. Figure 2 As shown, the vehicle control method includes:

[0051] S201: Determine the target lane based on the vehicle's surrounding environment information;

[0052] S202: Generate virtual obstacles for the target lane;

[0053] S203: Predict the speed of virtual obstacles;

[0054] S204: Control the vehicle's speed by combining the speed of virtual obstacles.

[0055] In this embodiment of the disclosure, the environmental information includes road environment information. Road environment-related information includes, but is not limited to, information about the vehicle's own lane and information about other lanes intersecting with the vehicle's own lane.

[0056] The relevant information about the lane may include its location, the lane's speed limit, traffic lights, and whether there are any obstacles.

[0057] In this embodiment of the disclosure, the virtual obstacle is a virtually created obstacle. The virtual obstacle can be a motor vehicle, a non-motor vehicle, or a robot. The above is merely illustrative and is not intended to limit the scope to all possible types of virtual obstacles; it is simply not an exhaustive list.

[0058] In this embodiment of the disclosure, controlling the vehicle's speed by combining the speed of virtual obstacles includes: adjusting the vehicle's speed according to the planned route and the speed of virtual obstacles.

[0059] The technical solution of this disclosure embodiment determines the target lane based on the environmental information of the vehicle; generates virtual obstacles for the target lane; predicts the driving speed of the virtual obstacles; and controls the driving speed of the vehicle based on the driving speed of the virtual obstacles. In this way, during the vehicle's driving process, the target road without obstacles is considered, and virtual obstacles are generated for the target road, which improves the rationality of the determined vehicle driving speed and can avoid collisions caused by the sudden appearance of obstacles on the target road, thereby improving the safety of vehicle driving.

[0060] In some embodiments, S201 may include:

[0061] S201a: Determine candidate lanes based on the vehicle's surrounding environment information;

[0062] S201b: In response to the detection that there is no first obstacle on the candidate lane and the upstream connecting lane of the candidate lane, the candidate lane is determined as the target lane.

[0063] In this embodiment of the disclosure, the number of candidate lanes is not limited. There can be one, two, or more candidate lanes. The number of candidate lanes determined in S201a depends on the road environment information of the vehicle. The number of candidate lanes is related to real-time traffic information and basic road infrastructure.

[0064] Here, basic road construction includes the number of lanes, lane road network, lane speed limit settings, traffic light duration settings, etc.

[0065] Here, real-time traffic information includes at least the number of vehicles in the lanes.

[0066] In this embodiment of the disclosure, the first obstacle is an obstacle that the vehicle needs to consider when determining its route.

[0067] Here, the type of the first obstacle can be either a motor vehicle or a non-motor vehicle.

[0068] In some implementations, candidate lanes are determined based on environmental information about the vehicle, including:

[0069] Check if there is an intersection within a certain distance in front of the vehicle;

[0070] If an intersection exists, check if there are other lanes perpendicular to the vehicle lane and in front of the main vehicle at that intersection. These other lanes that are detected will be considered as candidate lanes.

[0071] Here, the distance can be set or adjusted as needed. For example, the distance can be set to 30 meters. Or, the distance can be set to 50 meters.

[0072] Here, the direction is perpendicular to the vehicle lane and in front of the vehicle. The angle between the lane direction and the planned vehicle trajectory is about 90° (e.g., 90°±20°), the lane orientation is close to the planned vehicle trajectory, and the lane is in front of the vehicle.

[0073] Figure 3 A schematic diagram of an intersection scene is shown. Figure 1 ,vehicle( Figure 3 The planned trajectory of the vehicle (referred to as the "main vehicle") is represented by diagonal lines, with smiley faces indicating candidate lanes and crosses indicating non-candidate lanes, such as... Figure 3 As shown, in the current scenario, there are two candidate lanes and four non-candidate lanes.

[0074] Figure 4 A schematic diagram of an intersection scene is shown. Figure 2 ,vehicle( Figure 4 The planned trajectory of the main vehicle (referred to as the "main vehicle") is represented by diagonal lines, and smiley faces represent candidate lanes, such as... Figure 4 As shown, in the current scenario, there is one candidate lane and five non-candidate lanes.

[0075] In this way, candidate lanes related to the vehicle can be identified, providing an accurate calculation basis for selecting the target lane and helping to improve the safety of driving.

[0076] In some embodiments, S202 includes:

[0077] S202a: Determine the target blind spot of the target lane, which is a blind spot caused by a second obstacle that is not located in the target lane;

[0078] S202b: Generate virtual obstacles for the target lane based on the target blind spot.

[0079] In this embodiment of the disclosure, the virtual obstacle is a virtual obstacle, not a real obstacle.

[0080] Here, the target blind spot is caused by the obstruction of a second obstacle. The second obstacle is located in a lane other than the target lane.

[0081] Thus, by generating virtual obstacles for the target lane, the interference of virtual obstacles on the vehicle can be considered when determining the vehicle's speed, which helps to improve the safety of driving.

[0082] In some embodiments, S202a includes:

[0083] S202a1: Identify all blind spots in the target lane caused by obstruction from a second obstacle;

[0084] S202a2: Determine the size and location of each blind spot;

[0085] S202a3: Based on the size and location of each blind zone, determine the target blind zone from all blind zones.

[0086] This can improve the accuracy of target blind spot screening, thereby helping to improve vehicle driving safety.

[0087] In some embodiments, determining the size of each blind zone includes:

[0088] If multiple blind zones corresponding to second obstacles are detected to overlap or border each other, the overlapping or bordering blind zones are first merged, and then the size of the merged blind zone is determined.

[0089] Here, the size of the blind spot can be represented by one-dimensional information such as length, specifically the length of a side of the blind spot. The side length here refers to the longest side of the blind spot that is parallel to the target lane.

[0090] Here, the size of the blind spot can also be represented by two-dimensional information such as area.

[0091] For example, if the blind spots of several obstacles overlap or border each other, the blind spots of these obstacles are first merged into one large blind spot before subsequent calculations are performed.

[0092] For example, if the size of the blind zone is less than a certain threshold (e.g., the length is less than 3m), the blind zone will be considered an invalid blind zone and will no longer be considered.

[0093] like Figure 5 As shown, the blind zone formed by the triangular obstacle is A1B1C1D1, denoted as blind zone 1. Since the blind zones of obstacles a and b overlap, they are merged to form blind zone A2B2C2D2, denoted as blind zone 2. The size of the blind zone can be represented by one-dimensional information... Figure 5 In this context, AB can be represented as (A1B1 or A2B2), or using two-dimensional information. Figure 5The blind zone is represented by ABCD (A1B1C1D1 or A2B2C2D2). Since blind zone 1 is small, it is determined to be an invalid blind zone, which is equivalent to not having this blind zone. So now only blind zone 2 is left. Calculate the size of blind zone 2.

[0094] Therefore, by appropriately merging the target blind spots first, the screening speed of the target blind spots can be improved.

[0095] In some embodiments, the target blind zone is determined from all blind zones based on the size and location of each blind zone, including:

[0096] Blind spots with a vertical distance less than a first preset threshold are defined as target blind spots. The vertical distance is the vertical distance between the first projection point in the target blind spot and the lane where the vehicle is located.

[0097] Here, the first preset threshold can be set or adjusted according to design requirements such as safety or comfort requirements.

[0098] Continue with Figure 5 For example, the blind zone formed by the triangular obstacle is A1B1C1D1, denoted as blind zone 1. Since the blind zones of obstacles a and b overlap, they are merged to form blind zone A2B2C2D2, denoted as blind zone 2. The size of blind zone 2 and the vertical distance b_dist from the first projection point A2 closest to the driver vehicle to the driver vehicle's trajectory are calculated. If b_dist is less than a first preset threshold (e.g., 20m), then this blind zone is a target blind zone, and virtual obstacles need to be generated within it; otherwise, no virtual obstacle generation is required within this blind zone, meaning that the driver does not need to pay special attention to this blind zone and does not need to drive cautiously.

[0099] Therefore, determining the target blind zone based on the vertical distance can improve the speed of target blind zone determination.

[0100] In some embodiments, determining the target blind spot from all blind spots based on the size and location of each blind spot further includes: if there are two or more blind spots in the same target lane that satisfy the condition that the size of the blind spot is greater than a second preset threshold, the blind spot closest to the driver vehicle is determined as the target blind spot.

[0101] Here, the second preset threshold can be set or adjusted according to design requirements such as safety requirements or comfort requirements.

[0102] Continue with Figure 5 For example, since the size of blind zone 2 is large enough, blind zone 2 is an effective target blind zone. Therefore, even if there may be blind zone 3, blind zone 4, etc. behind blind zone 2, they will not be calculated or considered.

[0103] This reduces the number of blind spots to consider, which helps improve the efficiency of speed planning for vehicles.

[0104] In some embodiments, S202b includes:

[0105] S202b1: Determine the type of virtual obstacle based on the height of the second obstacle;

[0106] S202b2: Determine the position of the virtual obstacle by perpendicularly pointing to the center line of the lane where the first projection point in the target blind spot is located;

[0107] S202b3: Determine the direction of the target lane as the velocity direction of the virtual obstacle;

[0108] S202b4: Determine the recommended driving speed for virtual obstacles based on the vehicle's speed, position, and historical trajectory.

[0109] In this embodiment of the disclosure, the types of virtual obstacles include, but are not limited to, motor vehicles and non-motor vehicles.

[0110] In this embodiment of the disclosure, the first projection point is the projection point closest to the lane where the vehicle is located, which constitutes the target blind spot, such as... Figure 5 A2 in the middle.

[0111] In this embodiment of the disclosure, the virtual obstacle can be positioned at the center of the lane where the blind spot projection point is closest to the main vehicle's path, such as... Figure 5 The p position in the text.

[0112] This disclosure does not limit the execution order of S202b1, S202b2, and S202b3. S202b1, S202b2, and S202b3 can be executed simultaneously, or any two steps can be executed first, followed by the other step. Alternatively, they can be executed in the following order: S202b1, S202b2, and S202b3; S202b1, S202b3, and S202b2; S202b2, S202b1, and S202b3; S202b2, S202b3, and S202b1; S202b3, S202b1, and S202b2; or S202b3, S202b2, and S202b1.

[0113] In this way, accurately determining the relevant information of virtual obstacles helps improve the accuracy of the identified virtual obstacle's speed, thereby contributing to improved vehicle driving safety.

[0114] In some embodiments, S202b4 includes:

[0115] S202b4a: Determine the virtual collision point and the distance from the vehicle to the virtual collision point. The virtual collision point is the point of collision between the vehicle and the virtual obstacle in space.

[0116] S202b4b: Based on the distance from the vehicle to the virtual collision point and the vehicle's speed, predict the time it will take for the vehicle to travel to the virtual collision point;

[0117] S202b4c: Determine the collision speed based on the distance from the vehicle to the virtual collision point and the time it takes for the vehicle to travel to the virtual collision point;

[0118] S202b4d: Determine the appropriate speed for the target lane based on the normal speed corresponding to the obstacle type, the recommended speed for the target lane, and the probability of an accident.

[0119] S202b4e: Determine the recommended speed for virtual obstacles based on the collision speed and the reasonable speed of the target lane.

[0120] To determine the speed of a virtual obstacle, the roles of the vehicle (referred to as the master vehicle) and the virtual obstacle (referred to as the obstacle vehicle) can be interchanged. That is, the master vehicle is also an obstacle to the virtual obstacle vehicle. Given the master vehicle's speed, position, and historical trajectory, a planning module can determine the recommended speed for the virtual obstacle. Assuming the virtual obstacle is an intelligent agent, it will consider the master vehicle's behavior during its movement and adjust its speed to avoid collisions. The overall decision-making process is as follows:

[0121] Calculate the time T for the main vehicle to travel to the point of collision according to formula (1). interact The collision point is the point in space where the main vehicle and the virtual obstacle may collide. Figure 5 O in i .

[0122] T interact =c dist / Vego (1)

[0123] Among them, c dist The distance between the main vehicle and the point of collision, V ego The speed of the main vehicle.

[0124] Calculate the collision velocity V according to formula (2) interact ;

[0125] V interact =b dist / T interact (2)

[0126] Among them, b dist This represents the distance between the virtual obstacle and the point of collision.

[0127] Determine the reasonable speed V for the target lane according to formula (3). normal .

[0128] V normal =min(V type V road )*sigmoid(1 / γ) (3)

[0129] Among them, V type V represents the normal speed corresponding to the type of obstacle. road γ represents the recommended speed for the target lane, and γ is the probability of an accident occurring at the intersection.

[0130] Specifically, sigmoid(z) = 1 / (1+e -z It has the characteristic that its value is limited to [0,1] and changes slowly as the value of z increases, such as Figure 6 As shown, this aligns with the behavioral characteristics of human drivers when dealing with intersections where accidents occur.

[0131] In this way, the recommended driving speed for virtual obstacles can be determined, thus providing a reference for subsequent control of the vehicle's driving speed.

[0132] In some embodiments, S202b4e includes:

[0133] If the collision speed is not greater than the reasonable speed of the target lane, the collision speed is determined as the recommended driving speed of the virtual obstacle;

[0134] When the collision speed is greater than the reasonable speed of the target lane, the recommended driving speed of the virtual obstacle is determined based on the collision speed, safe distance, and maximum deceleration of the obstacle type. The safe distance is the safe distance between the vehicle and the virtual obstacle, and the maximum deceleration is the maximum deceleration corresponding to the type of virtual obstacle.

[0135] Based on the reasonable speed V of the target lane normal Determine the collision speed V interact Is it reasonable, specifically:

[0136] If V interact ≤V normal The recommended speed for driving over virtual obstacles is V. obs =V interact ;

[0137] If V interact >V normal The virtual obstacle will slow down to avoid colliding with the main vehicle. The recommended speed for the virtual obstacle is V. obs Calculate according to formula (4).

[0138] V obs =(sdist +1 / 2*α maxdecl *(T interact ) 2 ) / T interact (4)

[0139] Among them, s dist For a safe distance, α maxdecl This represents the maximum deceleration of this type of obstacle vehicle.

[0140] This can improve the rationality of the recommended driving speed for virtual obstacles.

[0141] In some embodiments, S202b1 includes: determining the type of the virtual obstacle as a motor vehicle when the height of the second obstacle is not less than a third preset threshold; and determining the type of the virtual obstacle as a non-motor vehicle when the height of the second obstacle is less than the third preset threshold.

[0142] For example, the type of virtual obstacle is determined based on the maximum height of the second obstacle that causes the blind spot. If the maximum height of the second obstacle is greater than a third preset threshold (e.g., 2m), the type of virtual obstacle is determined to be a car; if the maximum height of the second obstacle is less than the third preset threshold (e.g., 2m), the type of virtual obstacle is determined to be a non-motorized vehicle.

[0143] In this embodiment of the disclosure, the third preset threshold can be set or adjusted according to the actual height of the object.

[0144] Thus, determining the type of virtual obstacle by the height of the second obstacle can make the identified type of virtual obstacle more accurate, thereby helping to improve the rationality of the recommended driving speed for virtual obstacles and further improving the safety of vehicle driving.

[0145] It should be understood that Figure 3 , Figure 4 , Figure 5 and Figure 6 The schematic diagrams shown are merely illustrative and not limiting, and are scalable; those skilled in the art can use them as a basis. Figure 3 , Figure 4 , Figure 5 and Figure 6 Even with various obvious changes and / or substitutions to the examples, the resulting technical solutions still fall within the scope of this disclosure.

[0146] Figure 7 This is a schematic diagram of the vehicle control architecture according to an embodiment of the present disclosure, such as... Figure 7As shown, the architecture includes a blind spot recognition module, a prediction module, and a planning module. The blind spot recognition module filters target blind spots and generates specific virtual obstacles based on their characteristics. The blind spot recognition module then inputs these virtual obstacles into the prediction module, using an existing prediction module to generate prediction lines. The prediction module inputs the virtual obstacles and their prediction lines into the planning module, using an existing planning module to calculate the vehicle's driving behavior. The type, position, and speed of the virtual obstacles can be adjusted according to the degree of impact of the blind spot on the vehicle, and the generated prediction lines will not cause the vehicle to make unreasonable behaviors. This decouples the prediction module from the planning module and the blind spot recognition module, ensuring that the blind spot recognition module does not affect the performance of other modules. Neither the prediction nor the planning module needs modification; their mature and stable performance will not cause the vehicle to make unreasonable behaviors. By using the existing prediction module to predict the prediction lines of the virtual obstacles and the existing planning module to formulate reasonable driving behaviors to avoid these virtual obstacles, collisions between the vehicle and real obstacles within the target blind spot can be avoided, improving the rationality of driving and thus enhancing vehicle driving safety.

[0147] This disclosure provides a vehicle control device, such as... Figure 8 As shown, the vehicle control device may include: a determination module 801, used to determine the target lane based on the environmental information of the vehicle; a generation module 802, used to generate virtual obstacles for the target lane; a prediction module 803, used to predict the driving speed of the virtual obstacles; and a control module 804, used to control the driving speed of the vehicle in combination with the driving speed of the virtual obstacles.

[0148] In some embodiments, the determining module 801 includes: a first determining submodule, configured to determine a candidate lane based on environmental information of the vehicle; and a second determining submodule, configured to determine the candidate lane as a target lane in response to detecting that there is no first obstacle on either the candidate lane or the upstream connecting lane of the candidate lane.

[0149] In some embodiments, the generation module 802 includes: a third determining submodule, configured to determine a target blind spot of the target lane, wherein the target blind spot is a blind spot caused by a second obstacle, and the second obstacle is not an obstacle located on the target lane; and a generation submodule, configured to generate virtual obstacles for the target lane based on the target blind spot.

[0150] In some embodiments, the third determining submodule is configured to: determine all blind spots in the target lane caused by the second obstacle; determine the size and location of each blind spot; and determine the target blind spot from all blind spots based on the size and location of each blind spot.

[0151] In some embodiments, the third determining submodule is configured to: first merge the overlapping or adjacent blind areas when multiple blind areas corresponding to second obstacles are detected to be overlapping or adjacent, and then determine the size of the merged blind area.

[0152] In some embodiments, the third determining submodule is configured to: determine blind spots with a vertical distance less than a first preset threshold as target blind spots, wherein the vertical distance is the vertical distance between the first projection point in the target blind spot and the lane where the vehicle is located.

[0153] In some embodiments, the third determining submodule is used to: determine the blind spot closest to the driver vehicle as the upper target blind spot when there are two or more blind spots in the same target lane that satisfy the condition that the blind spot size is greater than a second preset threshold.

[0154] In some embodiments, the generation submodule is configured to: determine the obstacle type of the virtual obstacle based on the height of the second obstacle; determine the position of the virtual obstacle as the perpendicular point of the first projection point in the target blind spot to the center line of the lane where the target blind spot is located; determine the direction of the target lane as the speed direction of the virtual obstacle; and determine the recommended driving speed of the virtual obstacle based on the vehicle's speed, position, and historical trajectory.

[0155] In some embodiments, the generation submodule is configured to: determine a virtual collision point and the distance from the vehicle to the virtual collision point, wherein the virtual collision point is the point of collision between the vehicle and the virtual obstacle in space; predict the time it takes for the vehicle to travel to the virtual collision point based on the distance from the vehicle to the virtual collision point and the vehicle's speed; determine the collision speed based on the distance from the vehicle to the virtual collision point and the time it takes for the vehicle to travel to the virtual collision point; determine a reasonable speed for the target lane based on the normal speed corresponding to the obstacle type, the recommended speed for the target lane, and the probability of an accident; and determine a recommended speed for the virtual obstacle based on the collision speed and the reasonable speed for the target lane.

[0156] In some embodiments, the generation submodule is configured to: determine the collision speed as the recommended driving speed of the virtual obstacle when the collision speed is not greater than the reasonable speed of the target lane; and determine the recommended driving speed of the virtual obstacle based on the collision speed, the safe distance, and the maximum deceleration of the obstacle type when the collision speed is greater than the reasonable speed of the target lane, wherein the safe distance is the safe distance between the vehicle and the virtual obstacle, and the maximum deceleration is the maximum deceleration corresponding to the type of virtual obstacle.

[0157] In some embodiments, the generation submodule is configured to: determine the type of the virtual obstacle as a motor vehicle when the height of the second obstacle is not less than a third preset threshold; and determine the type of the virtual obstacle as a non-motor vehicle when the height of the second obstacle is less than the third preset threshold.

[0158] Those skilled in the art should understand that the functions of each processing module in the vehicle control device of the present disclosure embodiments can be understood with reference to the relevant description of the foregoing vehicle control method. Each processing module in the vehicle control device of the present disclosure embodiments can be implemented by an analog circuit that implements the functions described in the present disclosure embodiments, or by running software that performs the functions described in the present disclosure embodiments on an electronic device.

[0159] The vehicle control device of this disclosure can improve the safety of vehicle driving.

[0160] This disclosure also provides schematic diagrams of vehicle control scenarios, such as... Figure 9 As shown, the vehicle sends its own information to electronic devices, such as a cloud server. This information includes the vehicle's status, such as speed and location. Based on the vehicle's environment, the electronic devices determine a target lane for each vehicle and generate virtual obstacles for that lane. They predict the speed of these virtual obstacles and, combined with the obstacle speeds, determine a recommended speed for the vehicle. The electronic devices then return this recommended speed to the vehicle, allowing it to follow the planned route and control its movement accordingly. This improves driving safety.

[0161] This disclosure does not limit the number of vehicles and electronic devices; in practical applications, it may include multiple vehicles and multiple electronic devices.

[0162] It should be understood that Figure 9 The scene diagrams shown are merely illustrative and not restrictive; those skilled in the art can interpret them based on... Figure 9 Even with various obvious changes and / or substitutions to the examples, the resulting technical solutions still fall within the scope of this disclosure.

[0163] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0164] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, a computer program product, a vehicle, and an autonomous vehicle.

[0165] Figure 10A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0166] like Figure 10 As shown, device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 1002 or a computer program loaded from storage unit 1008 into random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. An input / output (I / O) interface 1005 is also connected to bus 1004.

[0167] Multiple components in device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1007, such as various types of monitors, speakers, etc.; storage unit 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0168] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as vehicle control methods. For example, in some embodiments, the vehicle control method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the vehicle control method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform vehicle control methods by any other suitable means (e.g., by means of firmware).

[0169] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0173] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0174] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0175] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0176] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A vehicle control method, comprising: Determine the target lane based on the vehicle's surrounding environment information; Virtual obstacles are generated for the target lane; Predict the speed of the virtual obstacle; The vehicle's speed is controlled based on the speed of the virtual obstacles. Determining the target lane based on the vehicle's environmental information includes: Candidate lanes are determined based on the environmental information of the vehicle. In response to the detection that there is no first obstacle on either the candidate lane or the upstream connecting lane of the candidate lane, the candidate lane is determined as the target lane; The process of determining candidate lanes based on the environmental information of the vehicle includes: Check if there is an intersection within a preset distance ahead of the vehicle; If an intersection exists, check if there are other lanes perpendicular to the vehicle lane and in front of the vehicle's main vehicle at the intersection, and use those other lanes as the candidate lanes; The process of generating virtual obstacles for the target lane includes: Determine the target blind spot of the target lane, wherein the target blind spot is a blind spot caused by a second obstacle that is not located in the target lane; The virtual obstacle is generated for the target lane based on the target blind spot; The step of generating the virtual obstacle for the target lane based on the target blind spot includes: The obstacle type of the virtual obstacle is determined based on the height of the second obstacle; The position of the virtual obstacle is determined by the perpendicular point of the first projection point in the target blind spot to the center line of the lane where the target blind spot is located. The direction of the target lane is determined as the velocity direction of the virtual obstacle; Based on the vehicle's speed, position, and historical trajectory, determine the recommended driving speed for the virtual obstacle; The step of determining the recommended driving speed for the virtual obstacle based on the vehicle's speed, position, and historical trajectory includes: Determine the virtual collision point and the distance from the vehicle to the virtual collision point, wherein the virtual collision point is the point of collision between the vehicle and the virtual obstacle in space; Based on the distance of the vehicle to the virtual collision point and the speed of the vehicle, predict the time it will take for the vehicle to travel to the virtual collision point; The collision speed is determined based on the distance from the vehicle to the virtual collision point and the time it takes for the vehicle to travel to the virtual collision point. Based on the normal speed corresponding to the obstacle type, the recommended speed of the target lane, and the probability of an accident, the reasonable speed of the target lane is determined; the reasonable speed is determined based on the sigmoid function, wherein the sigmoid function takes values ​​in the range of [0,1], and its changing trend conforms to the behavioral characteristics of human drivers when dealing with accident intersections; The recommended speed for the virtual obstacle is determined based on the collision speed and the reasonable speed of the target lane.

2. The method according to claim 1, wherein, Determining the target blind spot of the target lane includes: Identify all blind spots in the target lane caused by the second obstacle; Determine the size and location of each blind spot; Based on the size and location of each blind zone, the target blind zone is determined from all blind zones.

3. The method according to claim 2, wherein, Determine the size of each blind spot, including: If multiple blind zones corresponding to the second obstacle are detected to overlap or border each other, the overlapping or bordering blind zones are first merged, and then the size of the merged blind zone is determined.

4. The method according to claim 2, wherein, The process of determining the target blind zone from all blind zones based on the size and location of each blind zone includes: The blind zone with a vertical distance less than a first preset threshold is defined as the target blind zone, where the vertical distance is the vertical distance between the first projection point in the target blind zone and the lane where the vehicle is located.

5. The method according to claim 4, wherein, The method of determining the target blind zone from all blind zones based on the size and location of each blind zone also includes: If there are two or more blind spots in the same target lane that meet the condition that the size of the blind spot is greater than the second preset threshold, the blind spot closest to the driver vehicle is determined as the target blind spot.

6. The method according to claim 1, wherein, Based on the collision speed and the reasonable speed of the target lane, determine the recommended driving speed of the virtual obstacle, including: If the collision speed is not greater than the reasonable speed of the target lane, the collision speed is determined as the recommended driving speed of the virtual obstacle; If the collision speed is greater than the reasonable speed of the target lane, the recommended driving speed of the virtual obstacle is determined based on the collision speed, the safe distance, and the maximum deceleration of the obstacle type. The safe distance is the safe distance between the vehicle and the virtual obstacle, and the maximum deceleration is the maximum deceleration corresponding to the type of virtual obstacle.

7. The method according to claim 1, wherein, Determining the type of the virtual obstacle based on the height of the second obstacle includes: If the height of the second obstacle is not less than a third preset threshold, the type of the virtual obstacle is determined to be a motor vehicle; If the height of the second obstacle is less than the third preset threshold, the type of the virtual obstacle is determined to be a non-motorized vehicle.

8. A vehicle control device, comprising: The determination module is used to determine the target lane based on the environmental information of the vehicle. The generation module is used to generate virtual obstacles for the target lane; The prediction module is used to predict the speed of the virtual obstacle. The control module is used to control the vehicle's speed based on the speed of the virtual obstacles. The determining module includes: The first determining submodule is used to determine candidate lanes based on the environmental information of the vehicle. The second determining submodule is used to determine the candidate lane as the target lane in response to detecting that there is no first obstacle on the candidate lane and the upstream connecting lane of the candidate lane; The first determining submodule is used for: Check if there is an intersection within a preset distance ahead of the vehicle; If an intersection exists, check if there are other lanes perpendicular to the vehicle lane and in front of the vehicle's main vehicle at the intersection, and use those other lanes as the candidate lanes; The generation module includes: The third determining submodule is used to determine the target blind spot of the target lane, wherein the target blind spot is a blind spot caused by the obstruction of a second obstacle, and the second obstacle is not an obstacle located on the target lane; A generation submodule is used to generate the virtual obstacle for the target lane based on the target blind spot; The generation submodule is used for: The obstacle type of the virtual obstacle is determined based on the height of the second obstacle; The position of the virtual obstacle is determined by the perpendicular point of the first projection point in the target blind spot to the center line of the lane where the target blind spot is located. The direction of the target lane is determined as the velocity direction of the virtual obstacle; Based on the vehicle's speed, position, and historical trajectory, determine the recommended driving speed for the virtual obstacle; The generation submodule is used for: Determine the virtual collision point and the distance from the vehicle to the virtual collision point, wherein the virtual collision point is the point of collision between the vehicle and the virtual obstacle in space; Based on the distance of the vehicle to the virtual collision point and the speed of the vehicle, predict the time it will take for the vehicle to travel to the virtual collision point; The collision speed is determined based on the distance from the vehicle to the virtual collision point and the time it takes for the vehicle to travel to the virtual collision point. Based on the normal speed corresponding to the obstacle type, the recommended speed of the target lane, and the probability of an accident, the reasonable speed of the target lane is determined; the reasonable speed is determined based on the sigmoid function, wherein the sigmoid function takes values ​​in the range of [0,1], and its changing trend conforms to the behavioral characteristics of human drivers when dealing with accident intersections; The recommended speed for the virtual obstacle is determined based on the collision speed and the reasonable speed of the target lane.

9. The apparatus according to claim 8, wherein, The third determining submodule is used for: Identify all blind spots in the target lane caused by the second obstacle; Determine the size and location of each blind spot; Based on the size and location of each blind zone, the target blind zone is determined from all blind zones.

10. The apparatus according to claim 9, wherein, The third determining submodule is used for: If multiple blind zones corresponding to the second obstacle are detected to overlap or border each other, the overlapping or bordering blind zones are first merged, and then the size of the merged blind zone is determined.

11. The apparatus according to claim 9, wherein, The third determining submodule is used for: The blind zone with a vertical distance less than a first preset threshold is defined as the target blind zone, where the vertical distance is the vertical distance between the first projection point in the target blind zone and the lane where the vehicle is located.

12. The apparatus according to claim 11, wherein, The third determining submodule is used for: If there are two or more blind spots in the same target lane that meet the condition that the size of the blind spot is greater than the second preset threshold, the blind spot closest to the driver vehicle is determined as the target blind spot mentioned above.

13. The apparatus according to claim 8, wherein, The generation submodule is used for: If the collision speed is not greater than the reasonable speed of the target lane, the collision speed is determined as the recommended driving speed of the virtual obstacle; If the collision speed is greater than the reasonable speed of the target lane, the recommended driving speed of the virtual obstacle is determined based on the collision speed, the safe distance, and the maximum deceleration of the obstacle type. The safe distance is the safe distance between the vehicle and the virtual obstacle, and the maximum deceleration is the maximum deceleration corresponding to the type of virtual obstacle.

14. The apparatus according to claim 8, wherein, The generation submodule is used for: If the height of the second obstacle is not less than a third preset threshold, the type of the virtual obstacle is determined to be a motor vehicle; If the height of the second obstacle is less than the third preset threshold, the type of the virtual obstacle is determined to be a non-motorized vehicle.

15. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

17. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

18. A vehicle comprising: Including the electronic device as described in claim 15.

19. An autonomous vehicle, comprising: Including the electronic device as described in claim 15.

Images