Vehicle-road cloud integrated complex traffic road condition-based automatic driving vehicle passing method and system

Abstract

The invention discloses an automatic driving vehicle passing method and system based on vehicle and road cloud integration complex traffic conditions. The method comprises the steps of planning an optimal driving path based on an initial position and a target position of a target vehicle; when the optimal driving path has the congestion area, re-planning the driving path, and calculating the driving time required to be increased by the newly planned path; comparing the accident removal expected time with the increased driving time; when the accident removal expected time is not greater than the increased driving time, selecting a new planned path for passing; when the accident removal expected time is greater than the increased driving time, selecting an optimal driving path for passing; and when the distance between the target vehicle and the front vehicle is greater than a first safety distance threshold and the distance between the target vehicle and the opposite driving vehicle is greater than a second safety distance threshold, controlling the target vehicle to pass through the blocking area by borrowing the opposite road. The method can solve the problem that the automatic driving vehicle stops or takes over when encountering the congestion area.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving navigation technology, and in particular to a method and system for autonomous driving vehicle traffic under complex traffic conditions based on vehicle-road-cloud integration. Background Art

[0002] With the significant improvement in the level of automobile intelligence, innovative breakthroughs have been achieved in key technology areas such as smart cockpits and autonomous driving. L2-level driving assistance technology has entered the market popularization period, and L4-level autonomous driving technology has made continuous breakthroughs and regional demonstrations. Single-vehicle intelligent functions mainly rely on the vehicle's own cameras, radars and other sensors and computing platforms for environmental perception, calculation decisions and control execution, resulting in limitations such as no non-line-of-sight perception capabilities, no global perception capabilities, and lack of group collaboration. Relying on the vehicle-road-cloud collaborative development model enabled by technologies such as Cellular-V2X (C-V2X), the bottleneck problem of single-vehicle intelligent technology has been solved through collaborative information interaction, collaborative perception and collaborative decision-making control. It has gradually formed an industry consensus on the development path of the intelligent connected vehicle industry.

[0003] V2X, which refers to the connection between vehicles and everything, mainly includes V2V vehicles and vehicles, V2I vehicles and infrastructure, V2P vehicles and people, and V2N vehicles and clouds. C-V2X organically links the traffic elements of "people-vehicle-road-cloud" together, and realizes the full-scale coordination and cooperation (such as collaborative perception, collaborative decision-making and planning, collaborative control, etc.) between vehicles and vehicles (V2V), vehicles and roads (V2I, including roadside communication units, roadside sensing equipment, roadside computing units, status monitoring equipment, traffic induction and control facilities, etc.), vehicles and clouds (V2N, including cloud control platforms, map platforms, traffic management platforms, travel service platforms, etc.), and vehicles and people (V2P), so as to meet the application needs of autonomous driving vehicles of different levels and achieve the development goals of optimizing autonomous driving vehicles and optimizing the overall traffic situation.

[0004] Due to the limitations of single-vehicle intelligence, autonomous vehicles are unable to pass through accident congestion areas on the planned routes when passing through road construction, traffic accidents, traffic control, and especially in some complex road construction scenarios (such as construction at intersections and construction occupying all lanes in the direction of travel), which can easily lead to vehicle stagnation or takeover problems. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and system for autonomous driving vehicles to pass through complex traffic conditions based on vehicle-road-cloud integration in response to the shortcomings of the existing technology. The method can solve the problem of vehicle stagnation or takeover when autonomous driving vehicles are unable to pass through accident congestion areas of planned routes when passing through complex traffic conditions such as road construction, traffic accidents, and traffic control.

[0006] To achieve the above object, according to one aspect of the present invention, a method for driving an automatic driving vehicle under complex traffic conditions based on vehicle-road-cloud integration is provided, comprising:

[0007] Plan the optimal driving path based on the initial position and target position of the target vehicle;

[0008] When a blocked area appears in front of the target vehicle during the target vehicle's driving according to the optimal driving path, replanning the driving path and calculating the additional driving time required for the new planned path;

[0009] comparing the expected time to resolve the accident with the increased travel time;

[0010] When the expected time to resolve the accident is not greater than the increased travel time, the newly planned path is selected for travel;

[0011] When the expected time to resolve the accident is greater than the increased driving time, the optimal driving path is selected for passage; when the target vehicle is about to reach the blocked area, the position information and basic data of the target vehicle and surrounding vehicles are collected, and the distance between the target vehicle and the preceding vehicle and the distance between the target vehicle and the oncoming vehicle are obtained. When the distance between the target vehicle and the preceding vehicle is greater than a first safety distance threshold and the distance between the target vehicle and the oncoming vehicle is greater than a second safety distance threshold, the target vehicle is controlled to use the oncoming road to pass through the blocked area.

[0012] In the above scheme, the first safety distance threshold is the minimum distance that the target vehicle can avoid colliding with the leading vehicle when the leading vehicle traveling in the same lane and direction as the target vehicle continues to travel in the current motion state while overtaking the leading vehicle.

[0013] In the above scheme, the second safety distance threshold is the minimum distance at which the target vehicle can avoid colliding with the oncoming vehicle when the target vehicle continues to travel in the current motion state while overtaking the leading vehicle.

[0014] In the above scheme, the target vehicle changes lanes with constant lateral and longitudinal accelerations that satisfy comfort.

[0015] In the above scheme, the optimal driving route is planned by the cloud platform based on real-time road traffic flow and historical traffic record data.

[0016] In the above scheme, the oncoming road used by the target vehicle is the leftmost lane on the oncoming road; the target vehicle travels in the leftmost lane on the road on this side before using the oncoming road.

[0017] In the above scheme, the blocking area is located on the road on the side where the target vehicle is located, which hinders the vehicles on this side of the road from traveling normally.

[0018] In the above scheme, the increased driving time is obtained based on a cloud platform according to real-time road traffic flow and historical traffic record data; the cloud platform includes a cloud control platform, a map platform, a traffic management platform and a travel service platform.

[0019] In the above scheme, the expected time for resolving the accident is calculated by the roadside perception system based on the type of accident, road congestion area, cause of congestion, and accessibility of congestion; the roadside perception system includes a roadside communication unit, a roadside perception device, a roadside computing unit, a status monitoring device, and traffic induction and control facilities.

[0020] In the above solution, the basic data at least includes vehicle size, vehicle speed and acceleration.

[0021] According to another aspect of the present invention, there is provided an automatic driving vehicle passage system for complex traffic conditions based on vehicle-road-cloud integration, comprising:

[0022] A planning module, used to plan an optimal driving path based on an initial position and a target position of a target vehicle, and to re-plan the driving path when a blocked area appears in front of the target vehicle during the driving of the target vehicle according to the optimal driving path;

[0023] A calculation module is used to calculate the additional travel time required for the new planned path;

[0024] A comparison module, used for comparing the expected time to resolve the accident with the increased travel time;

[0025] A first selection module, configured to select the new planned path for passage when the expected time to resolve the accident is not greater than the increased travel time;

[0026] The second selection module is used to select the optimal driving path when the expected time to resolve the accident is greater than the increased driving time; when the target vehicle is about to reach the blocked area, collect the position information and basic data of the target vehicle and surrounding vehicles, obtain the distance between the target vehicle and the preceding vehicle, and the distance between the target vehicle and the oncoming vehicle, and when the distance between the target vehicle and the preceding vehicle is greater than a first safety distance threshold and the distance between the target vehicle and the oncoming vehicle is greater than a second safety distance threshold, control the target vehicle to use the oncoming road to pass through the blocked area.

[0027] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0028] (1) The present invention provides a method for autonomous driving vehicles to pass complex traffic conditions based on vehicle-road-cloud integration. The method can solve the problem of vehicle stagnation or takeover when autonomous driving vehicles are unable to pass through accident congestion areas on planned routes when passing through complex traffic conditions such as road construction, traffic accidents, and traffic control.

[0029] (2) The present invention provides an autonomous driving vehicle passage system for complex traffic conditions based on the integration of vehicle, road and cloud. The system, through the vehicle-road-cloud collaborative development model, utilizes collaborative information interaction, collaborative perception and collaborative decision-making control to meet the application needs of autonomous driving vehicles of different levels and optimizes the global traffic solution for autonomous driving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Also, throughout the accompanying drawings, the same reference figures are used to represent the same components. In the drawings:

[0031] Figure 1 Schematic diagram of the process of an automatic driving vehicle passage method under complex traffic conditions based on vehicle-road-cloud integration in Example 1 of the present invention.

[0032] Figure 2 This is a schematic diagram of the structure of the vehicle-road-cloud integrated system in Example 1 of the present invention.

[0033] Figure 3 This is a schematic diagram of an autonomous driving vehicle encountering a blocked area in Example 1 of the present invention.

[0034] Figure 4 This is a schematic diagram of replanning the driving route based on VICIS in Example 1 of the present invention.

[0035] Figure 5 This is a schematic diagram of controlling the target vehicle to use the opposite road to pass through the blocked area in Example 1 of the present invention.

[0036] Figure 6 This is a schematic diagram of a scenario in which a target vehicle overtakes another vehicle by using another lane in Example 1 of the present invention.

[0037] Figure 7 Schematic diagram of a critical collision between a target vehicle and a preceding vehicle in Embodiment 1 of the present invention.

[0038] Figure 8 This is a schematic diagram of a target vehicle overtaking a preceding vehicle by using a different lane in Embodiment 1 of the present invention.

[0039] Fig. 9 Schematic diagram of a critical collision between a target vehicle and an oncoming vehicle in Example 1 of the present invention.

[0040] Fig.10 Schematic diagram of the process of an automatic driving vehicle passage method under complex traffic conditions based on vehicle-road-cloud integration in Example 2 of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0042] It should be understood that the size of the serial numbers of the steps in the embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0043] Example 1

[0044] The present application provides a method for driving an autonomous vehicle in complex traffic conditions based on vehicle-road-cloud integration. Figure 1 ,include:

[0045] S1, planning the optimal driving path based on the initial position and target position of the target vehicle.

[0046] In the embodiments of the present application, it can be understood that the target vehicle is an autonomous driving vehicle and has related services provided by the Vehicle-Infrastructure-Cloud Integrated System (VICIS). VICIS is an information-physical system that integrates people, vehicles, roads, and clouds through a new generation of information and communication technologies, and realizes safe, energy-saving, comfortable, and efficient operation of intelligent networked vehicle transportation systems based on system collaborative perception, decision-making, and control. The vehicle-road-cloud integrated system is a complex large system composed of vehicles and other traffic participants, roadside infrastructure, cloud control platforms, related support platforms, communication networks, and other parts. Its structural diagram is shown in the figure below. Figure 2 shown.

[0047] Traffic participants, transportation tools, transportation infrastructure and traffic environment in VICIS are not just regarded as simple objects. Traffic elements corresponding to people, vehicles, roads and environment are collected and fused by sensors to become digital twins with autonomous identities and information interaction functions. The physical entity and the digital twin can complete the information transmission and decision control closed loop through effective information flow and decision control flow, such as remote control of vehicles, optimized control of road traffic lights, and control of variable road signs. Different physical entities present a more efficient and orderly traffic operation situation under the global scheduling of the complex information-physical system of the vehicle-road-cloud integrated system.

[0048] Specifically, it can be understood that, in this embodiment, after obtaining the initial position and target position of the target vehicle, the cloud platform plans the optimal driving path based on the real-time road traffic flow and historical traffic record data.

[0049] S2, when a blocked area appears in front of the target vehicle during the target vehicle driving according to the optimal driving path, the driving path is replanned, and the additional driving time required for the new planned path is calculated.

[0050] It is understandable that traffic events such as road construction, traffic accidents, and traffic control are scenarios that autonomous vehicles often encounter and are difficult to deal with. Especially in some complex road construction scenarios (such as construction at intersections and construction that occupies all lanes in the direction of travel), relying solely on single-vehicle intelligence cannot successfully overcome them, which can easily cause the vehicle to stagnate or take over. Figure 3 As shown, there are safety risks for autonomous vehicles encountering these blocked areas.

[0051] Specifically, in this embodiment, when the target vehicle is traveling along the optimal driving path, a blocked area appears ahead, and the cloud platform needs to re-plan the driving path, such as Figure 4 As shown; and the cloud platform can also calculate the additional driving time ΔT required for the new planned path compared to the original optimal driving path.

[0052] S3, comparing the expected time to resolve the accident with the increased travel time.

[0053] Specifically, in this embodiment, the roadside perception system calculates the expected time Δδ for resolving the accident based on the accident type, road congestion area, congestion cause, and congestion accessibility; and compares the expected time Δδ for resolving the accident with the increased driving time ΔT.

[0054] S4, when the expected time to resolve the accident is greater than the increased driving time, select the optimal driving path for passage; when the target vehicle is about to reach the blocked area, collect the location information and basic data of the target vehicle and surrounding vehicles, obtain the distance between the target vehicle and the preceding vehicle, and the distance between the target vehicle and the oncoming vehicle, and when the distance between the target vehicle and the preceding vehicle is greater than the first safety distance threshold and the distance between the target vehicle and the oncoming vehicle is greater than the second safety distance threshold, control the target vehicle to use the oncoming road to pass through the blocked area.

[0055] In this embodiment, the increased driving time ΔT is obtained by comparison>the expected time Δδ for resolving the accident, therefore, the optimal driving path is selected to pass through, and the target vehicle is controlled to use the opposite road to pass through the blocked area.

[0056] At the same time, if the target vehicle needs to pass through a blocked area (accident scenario), it is necessary to further solve the collaborative traffic problem from the perspective of decision-making planning based on collaborative path planning. The specific process is as follows:

[0057] (1) Through the roadside perception system, the two-way traffic flow is continuously observed in real time to obtain the traffic trajectory around the blocked area. Combined with the road traffic situation, it is identified that the road on this side is no longer passable. In this case, the leftmost lane of the oncoming road is used as the lane for the target vehicle to travel when using the oncoming road.

[0058] (2) When the road end finds that the lane's drivable direction and connection relationship have changed, the road topology data of the local area is updated.

[0059] (3) Before the target vehicle reaches the blocked area, the new local road network topology is obtained, and the local path planning of the target vehicle is re-performed. The oncoming road is used to reach the blocked area. The collaborative decision-making planning is as follows: Figure 5 shown.

[0060] Specifically, in this embodiment, Figure 6 As shown, the target vehicle 1 is in lane A and is following or about to follow the low-speed vehicle 2 (the front vehicle) in front. Due to the accident in front (blocked area) and vehicle 2, the target vehicle 1 cannot reach the predetermined expected speed. Therefore, the target vehicle 1 can only improve the traffic efficiency by overtaking in the current road. At the same time, there are oncoming vehicles 3 and 4 in the opposite lane B, so there is a potential collision risk in the overtaking behavior of the target vehicle 1. At this time, there are the following working conditions:

[0061] ① Condition 1: The distance between target vehicle 1 and the oncoming vehicle is sufficient, which means that the vehicle in lane B will not actually constitute a potential collision risk source for target vehicle 1, that is, there is no need to consider the impact of obstacles on lane B. Target vehicle 1 only needs to consider the motion information of the dynamic obstacle vehicle 2 in front, and reasonably plan a lane-overtaking trajectory to pass the scene. For the overtaking behavior in this condition, it is necessary to determine whether the longitudinal distance (the distance between the target vehicle and the front vehicle) is greater than the first safety distance threshold. The first safety distance threshold refers to the minimum distance that the target vehicle can avoid colliding with the front vehicle during the overtaking process when the front vehicle traveling in the same lane and direction as the target vehicle continues to travel in the current motion state. Since the speed of the target vehicle will form an angle with the current lane during the overtaking process, it is necessary to calculate a reasonable overtaking longitudinal distance based on the characteristics of the overtaking behavior. When the longitudinal distance meets the requirements, the dangerous situation of rear-end collision or corner collision can be avoided. The critical position of the corner collision between the target vehicle and the front vehicle during overtaking is as follows: Figure 7 As shown, a first safety distance threshold model is established.

[0062] Specifically, the target vehicle 1 and the vehicle 2 are at t end From the geometric relationship of the position where the corner collision occurs at time t, it can be seen that the target vehicle 1 starts from the overtaking motion to t end After the time period, the total accumulated lateral displacement is y 1end , this lateral displacement needs to compensate for the width of vehicle 2 and the direction angle θ of target vehicle 1 end The slope of , so the critical condition of lateral displacement is approximately:

[0063]

[0064]

[0065] In the formula, y 2end For vehicle 2 at t end Y coordinate of vehicle 2, W2 is the width of vehicle 2, W1 is the width of vehicle 1, and L1 is the length of vehicle 1; θ end is a function of time t. If the target vehicle 1 satisfies the constant lateral and longitudinal acceleration a required for comfort x 、a y To plan lane change, the time point t at which the collision occurs is obtained by equations (1) and (2): end In order to prevent the target vehicle 1 from colliding with the vehicle 2 during the lane change process, the target vehicle 1 and the vehicle 2 are end The longitudinal safety distance conditions that need to be met at all times are:

[0066]

[0067] In the formula, x 1end is the target vehicle 1 at the time tend The X displacement represents the longitudinal displacement of the target vehicle 1 during this period, x 2end For vehicle 2 at t end X coordinate, S 1，2sta is the initial longitudinal distance between the two vehicles at the beginning of the lane change.

[0068] Therefore, to avoid collision during lane change, S 11，2sta Formula (2) should be satisfied, and the first safety distance threshold model is obtained by shifting the terms to ΔS:

[0069]

[0070]

[0071] Where ε is the shape condition factor, It is represented as the initial longitudinal acceleration of vehicles 1 and 2, It is represented by the longitudinal speed of the starting point of target vehicle 1 and vehicle 2. It can be seen from formula (5) that the factors affecting the safety distance threshold model mainly include the initial speed and initial acceleration of the two vehicles, the comfortable lateral and longitudinal acceleration of the target vehicle 1 during the lane change process, and the size data of the target vehicle 1 and vehicle 2. As long as the initial distance between the two vehicles is greater than the first safety distance threshold, the target vehicle 1 will not suffer from the risk of collision when planning lane change with comfortable acceleration. In particular, it should be noted that when there is no vehicle between the target vehicle and the blocked area, it can be regarded as having a sufficient safety distance between the target vehicle and the preceding vehicle, and the target vehicle can change lanes at any time.

[0072] ② Working condition 2: If Figure 8 As shown in FIG. 1 , first, the target vehicle 1 overtakes the vehicle 2 in the same lane by using a lane as a pretext; then, the target vehicle 1 returns to the original lane before colliding with the oncoming vehicle 3, as shown in FIG. Fig. 9 shown.

[0073] For the target vehicle 1 to overtake the front vehicle 2 in the same lane, the automatic driving at this stage mainly has two parts of displacement, longitudinal displacement and lateral displacement. The longitudinal displacement is the longitudinal acceleration a of the automatic driving target vehicle 1. x The displacement required to overtake:

[0074]

[0075] Among them, t st1 represents the time required to complete the current overtaking phase, and the comfortable longitudinal acceleration a of the target vehicle 1 x It is known that the vehicle size information and the initial motion state information can be measured by relevant sensors, so t can be solved by formula (6): st1 , and then enter Fig. 9 The merging phase is shown.

[0076] For the target vehicle 1 merging process, according to the time between vehicle 1 and vehicle 3 at t st2 From the geometric relationship of the position where the corner collision occurs at time t, it can be seen that vehicle 1 st1 Movement to t st2 The total accumulated lateral displacement is y 1st2 , this lateral displacement needs to compensate for the width of the oncoming vehicle 3 and the direction angle θ of the target vehicle 1 st2 The critical condition for lateral displacement is:

[0077]

[0078]

[0079] In formula (8), if the target vehicle 1 satisfies the constant lateral and longitudinal acceleration a of the comfort factor, x 、a y To plan lane change, the time point t at which the collision occurs is obtained by equation (7): st2 , then in order to prevent the target vehicle 1 from colliding with the oncoming vehicle 3 during the lane change process, the target vehicle 1 and the oncoming vehicle 3 are st2 The longitudinal safety distance conditions that need to be met at all times are:

[0080]

[0081] Among them, x 1st2 is the target vehicle 1 at t st2 The longitudinal displacement of time represents the longitudinal displacement of the target vehicle 1 during this period, x 3st2 is the oncoming vehicle 3 at t st2 The longitudinal displacement, S 1，3st1 It is the initial longitudinal distance between the target vehicle 1 and the oncoming vehicle 3 at the beginning of the merging process.

[0082] Therefore, to avoid collision during the lane change process, S 1，3st1 Formula (9) should be satisfied, and the second safety distance threshold model of the lane merging process is obtained as:

[0083]

[0084]

[0085] By combining the safety distances of the overtaking phase and the merging phase, we can obtain the second safety distance threshold type from the oncoming vehicle in the case of overtaking by using the lane:

[0086]

[0087] In formula (12), first calculate t according to formula (6): st1 , and then combine equations (7) and (8) to deduce t st2 , that is, the second safety distance threshold in the case of overtaking by using a lane can be obtained. As long as the initial distance between the target vehicle 1 and the oncoming vehicle 3 is greater than the second safety distance threshold, the target vehicle 1 will not suffer from the risk of collision when planning to overtake by using a lane at a comfort acceleration.

[0088] Specifically, in this embodiment, when the distance between the target vehicle and the preceding vehicle is greater than a first safety distance threshold and the distance between the target vehicle and the oncoming vehicle is greater than a second safety distance threshold, the target vehicle can be controlled to use the oncoming road to pass through the blocked area.

[0089] To sum up, the embodiments of the present application provide a method for autonomous driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration. The method can solve the problem of vehicle stagnation or takeover when the autonomous driving vehicle is unable to pass through the accident congestion area of ​​the planned route when passing through complex traffic conditions such as road construction, traffic accidents, and traffic control.

[0090] Example 2

[0091] The present application provides a method for driving an autonomous vehicle in complex traffic conditions based on vehicle-road-cloud integration. Figure 1 ,include:

[0092] S1, planning the optimal driving path based on the initial position and target position of the target vehicle.

[0093] S2, when a blocked area appears in front of the target vehicle during the target vehicle driving according to the optimal driving path, the driving path is replanned, and the additional driving time required for the new planned path is calculated.

[0094] S3, comparing the expected time to resolve the accident with the increased travel time.

[0095] S4: When the expected time to resolve the accident is not greater than the increased travel time, the newly planned route is selected.

[0096] Another aspect of the present application embodiment provides an automatic driving vehicle passage system for complex traffic conditions based on vehicle-road-cloud integration, including:

[0097] A planning module, used to plan an optimal driving path based on the initial position and the target position of the target vehicle, and to re-plan the driving path when a blocking area appears in front of the target vehicle during the driving of the target vehicle according to the optimal driving path;

[0098] A calculation module is used to calculate the additional travel time required for the new planned path;

[0099] A comparison module, used for comparing the expected time to resolve the accident with the increased travel time;

[0100] The first selection module is used to select a new planned path for passage when the expected time to resolve the accident is not greater than the increased travel time;

[0101] The second selection module is used to select the optimal driving path when the expected time to resolve the accident is greater than the increased driving time; when the target vehicle is about to reach the blocked area, the position information and basic data of the target vehicle and surrounding vehicles are collected, and the distance between the target vehicle and the preceding vehicle and the distance between the target vehicle and the oncoming vehicle are obtained. When the distance between the target vehicle and the preceding vehicle is greater than a first safety distance threshold and the distance between the target vehicle and the oncoming vehicle is greater than a second safety distance threshold, the target vehicle is controlled to use the oncoming road to pass through the blocked area.

[0102] To summarize, the embodiments of the present application also provide an autonomous driving vehicle traffic system for complex traffic conditions based on vehicle-road-cloud integration. The system, through the vehicle-road-cloud collaborative development model, utilizes collaborative information interaction, collaborative perception, and collaborative decision-making control to meet the application needs of autonomous driving vehicles of different levels and optimizes the global traffic solution for autonomous driving vehicles.

[0103] It should be pointed out that, according to the needs of implementation, the various steps described in this application can be divided into more steps, or two or more steps or partial operations of the steps can be combined into a new step to achieve the purpose of the present invention.

[0104] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatic driving vehicle traffic in complex traffic conditions based on vehicle-road-cloud integration, characterized in that: include: Plan the optimal driving path based on the initial position and target position of the target vehicle; When a blocked area appears in front of the target vehicle during the target vehicle's driving according to the optimal driving path, replanning the driving path and calculating the additional driving time required for the new planned path; comparing the expected time to resolve the accident with the increased travel time; When the expected time to resolve the accident is not greater than the increased travel time, the newly planned path is selected for travel; When the expected time to resolve the accident is greater than the increased driving time, the optimal driving path is selected for passage; when the target vehicle is about to reach the blocked area, the position information and basic data of the target vehicle and surrounding vehicles are collected, and the distance between the target vehicle and the preceding vehicle and the distance between the target vehicle and the oncoming vehicle are obtained. When the distance between the target vehicle and the preceding vehicle is greater than a first safety distance threshold and the distance between the target vehicle and the oncoming vehicle is greater than a second safety distance threshold, the target vehicle is controlled to use the oncoming road to pass through the blocked area.

2. The method for automatic driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The first safety distance threshold is a minimum distance at which the target vehicle can avoid colliding with the preceding vehicle when the preceding vehicle traveling in the same lane and in the same direction as the target vehicle continues to travel in the current motion state while overtaking the preceding vehicle.

3. The method for automatic driving vehicle passage under complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The second safety distance threshold is a minimum distance at which the target vehicle can avoid colliding with the oncoming vehicle when the target vehicle passes the leading vehicle when the oncoming vehicle continues to travel in the current motion state.

4. The method for automatic driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The optimal driving route is planned by the cloud platform based on real-time road traffic flow and historical traffic record data.

5. The method for automatic driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The oncoming road used by the target vehicle is the leftmost lane on the oncoming road; the target vehicle is traveling in the leftmost lane on the road on this side before using the oncoming road.

6. The method for automatic driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The blocking area is located on the road on the side where the target vehicle is located, and hinders the vehicles on the road on this side from traveling normally.

7. The method for automatic driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The increased driving time is obtained based on a cloud platform according to real-time road traffic flow and historical traffic record data; the cloud platform includes a cloud control platform, a map platform, a traffic management platform and a travel service platform.

8. The method for automatic driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The expected time for resolving the accident is calculated by a roadside perception system based on the type of accident, road congestion area, cause of congestion, and accessibility of congestion; the roadside perception system includes a roadside communication unit, a roadside perception device, a roadside computing unit, a status monitoring device, and traffic induction and control facilities.

9. The method for automatic driving vehicle passage in complex traffic conditions based on vehicle-road-cloud integration according to claim 1 is characterized in that: The basic data includes at least vehicle size, vehicle speed and acceleration.

10. An automatic driving vehicle traffic system based on vehicle-road-cloud integration for complex traffic conditions, characterized in that: include: A planning module, used to plan an optimal driving path based on an initial position and a target position of a target vehicle, and to re-plan the driving path when a blocked area appears in front of the target vehicle during the driving of the target vehicle according to the optimal driving path; A calculation module is used to calculate the additional travel time required for the new planned path; A comparison module, used for comparing the expected time to resolve the accident with the increased travel time; A first selection module, configured to select the new planned path for passage when the expected time to resolve the accident is not greater than the increased travel time; The second selection module is used to select the optimal driving path when the expected time to resolve the accident is greater than the increased driving time; when the target vehicle is about to reach the blocked area, collect the position information and basic data of the target vehicle and surrounding vehicles, obtain the distance between the target vehicle and the preceding vehicle, and the distance between the target vehicle and the oncoming vehicle, and when the distance between the target vehicle and the preceding vehicle is greater than a first safety distance threshold and the distance between the target vehicle and the oncoming vehicle is greater than a second safety distance threshold, control the target vehicle to use the oncoming road to pass through the blocked area.

Images