Vehicle collaborative control method based on simulated traffic signal, medium and equipment

Abstract

The invention discloses a vehicle collaborative control method based on simulated traffic signals, a medium and equipment. The method comprises the following steps: acquiring real-time road condition information of a road through a vehicle collaborative sensing module; when it is judged that the entity signal lamp is not set or the signal lamp fails, a driving intention request of a first vehicle is received, the road condition information and the driving intention are input into a first neural network model, a control strategy responding to the driving intention is output after the road condition information and the driving intention are analyzed by the first neural network model, and a simulated traffic signal sequence containing simulated signal lamps or signs is generated; and respectively sending the simulated traffic signal sequences to corresponding vehicle-mounted terminals for display, and monitoring whether the vehicle driving behavior violates rules or not in real time based on the sequences. Through the scheme, a responsibility determination mechanism can be determined, the problem that the vehicle driving behavior is difficult to trace when the entity traffic signal lamp is missing or invalid is solved, and meanwhile, the sequence is only presented in an instruction form, so that the computing power of a server can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and in particular to a vehicle cooperative control method, medium and equipment based on simulated traffic signals. Background Art

[0002] Traffic signals scientifically allocate access to road resources and are the primary means of regulating and guiding traffic. However, traffic is complex and dynamic, and existing physical traffic signals are typically deployed in fixed locations. These signals suffer from limitations such as fixed operational areas, insufficient deployment numbers, and difficulty in dynamic adjustment. These limitations make them unable to meet the growing demand for real-time, refined traffic management in the information age.

[0003] Chinese invention application publication number CN113327421A discloses a V2X-based road network control method and system. This system improves traffic efficiency to a certain extent by sensing traffic status data in real time and combining it with a predictive model to generate a collaborative control solution. However, this system has the following drawbacks:

[0004] First, the system is inadequate in responding to signal failure scenarios. When physical traffic lights fail or there are no signals at intersections, the existing system lacks effective alternative control methods, which can easily cause traffic chaos.

[0005] Second, there's a lack of a mechanism for determining responsibility. The control instructions output by the system (such as route suggestions and speed limits) are essentially constructive suggestions for all vehicles on the relevant road section. Compliance depends on the driver's own self-control. When a vehicle violates a traffic rule or an accident occurs, the lack of traffic lights or malfunctioning traffic lights make it impossible to determine responsibility, making it difficult to determine who is responsible.

[0006] Third, it is necessary to coordinate and plan the routes of all vehicles on the road section. As the number of vehicles increases, the computing power requirements on the server will increase sharply. Summary of the Invention

[0007] In view of the above problems, the present invention provides a vehicle collaborative control method, medium and equipment based on simulated traffic signals to solve the problems of the existing system such as the lack of responsibility identification mechanism, complex computing power, and easy traffic congestion in scenarios where there are no physical traffic lights on the road or the physical traffic lights are out of service.

[0008] To achieve the above objectives, in a first aspect, the present application provides a vehicle cooperative control method based on simulated traffic signals, the method comprising the following steps:

[0009] The vehicles cooperatively sense road condition information of a road on which the first vehicle is located, the road condition information including the setting of a physical traffic light, vehicle information, and location information of pedestrians or obstacles, and the vehicle information including vehicle location information and vehicle driving parameter information;

[0010] When it is determined that no physical traffic light is provided on the road or the physical traffic light is out of service, receiving a driving intention request from a first vehicle, and inputting the road condition information and the driving intention request of the first vehicle into a first neural network model;

[0011] The first neural network model outputs a first control strategy responsive to the driving intention based on the road condition information and the driving intention of the first vehicle, and generates a simulated traffic signal sequence based on the first control strategy, wherein the simulated traffic signal sequence is a set of simulated traffic signals, the simulated traffic signals including simulated traffic lights or simulated traffic signs, and the simulated traffic signal sequence includes a first simulated traffic signal sequence and a second simulated traffic signal sequence;

[0012] sending the first simulated traffic signal sequence to a first vehicle and displaying it on an onboard terminal of the first vehicle, and sending the second simulated traffic signal sequence to other vehicles associated with the driving intention request of the first vehicle and displaying it on the onboard terminals of the other vehicles;

[0013] Whether the driving behavior of the first vehicle is in violation of traffic rules is determined based on the first simulated traffic signal sequence and / or whether the driving behavior of other vehicles is in violation of traffic rules is determined based on the second simulated traffic signal sequence.

[0014] Furthermore, the driving intention request of the first vehicle includes a U-turn request;

[0015] The first neural network model outputs a first control strategy in response to the driving intention based on the road condition information and the driving intention of the first vehicle, including: the first neural network model determines the type of the vehicle U-turn area based on the road condition information, and outputs a first control strategy according to the U-turn area type.

[0016] Furthermore, the simulated traffic light includes a simulated U-turn light, and the simulated U-turn light includes any one of the following:

[0017] a simulated U-turn green light, used to indicate that the first vehicle is permitted to make a U-turn;

[0018] a simulated U-turn red light, used to indicate that the first vehicle is prohibited from making a U-turn;

[0019] A simulated U-turn yellow light is used to serve as a warning when the first vehicle is making a U-turn. When the simulated U-turn yellow light continues to flash, it indicates that the first vehicle needs to make a U-turn with caution after observing and confirming that it is safe. When the simulated U-turn green light turns into the simulated U-turn yellow light, it indicates that the U-turn permission is about to end.

[0020] The simulated traffic sign includes:

[0021] A simulated countdown sign is used to indicate the remaining operating time of a simulated traffic signal;

[0022] A simulated no-U-turn sign is used to indicate that a first vehicle is prohibited from making a U-turn on the current road;

[0023] a simulated slow down and yield sign, used to instruct the first vehicle or other vehicles associated with the driving intention request of the first vehicle to slow down and yield;

[0024] a simulated stop line, used to indicate the parking position of the first vehicle before turning around;

[0025] Simulated U-turn lane guide lines, used to indicate the driving route of the first vehicle when making a U-turn;

[0026] The simulated attention signal light sign is used to indicate that a physical signal light is installed in the first vehicle U-turn zone and vehicles should drive according to the physical signal light.

[0027] Furthermore, the types of vehicle U-turn zones include prohibited U-turn zones, traffic light-controlled U-turn points, and non-traffic light-controlled U-turn points, and the other vehicles include oncoming vehicles corresponding to the first vehicle;

[0028] When the first neural network model identifies that the vehicle U-turn zone type is a no-U-turn zone, determining that the first control strategy is a no-U-turn strategy; generating a simulated traffic signal sequence based on the first control strategy includes: generating a simulated no-U-turn sign based on the no-U-turn strategy, and issuing the simulated no-U-turn sign to the first vehicle;

[0029] When the first neural network model identifies that the vehicle U-turn zone type is a light-controlled U-turn point, determining that the first control strategy is an indicated U-turn strategy; generating a simulated traffic signal sequence based on the first control strategy includes: generating a simulated attention signal light sign based on the indicated U-turn strategy, and issuing the simulated attention signal light sign to the first vehicle;

[0030] When the first neural network model identifies that the vehicle U-turn area type is a non-light-controlled U-turn point, it determines whether the current road condition allows U-turn based on the road condition information. If not allowed, a stop-and-wait U-turn strategy is generated. The simulated traffic signal sequence generated based on the first control strategy includes: issuing a simulated U-turn red light and a simulated stop line to the first vehicle, instructing the first vehicle to stop and wait for U-turn after the simulated stop line; if allowed, a time-limited U-turn strategy is generated. The simulated traffic signal sequence generated based on the first control strategy includes: issuing a simulated slowdown and yield sign and a warning message that an oncoming vehicle is turning around to the oncoming vehicle, and after receiving the first response information from the oncoming vehicle, issuing a simulated U-turn green light, a simulated countdown sign and a countdown time to the first vehicle, instructing the first vehicle to complete the U-turn action according to the simulated traffic signal.

[0031] Furthermore, the vehicle U-turn zone type includes an optional U-turn point, and the other vehicles include an oncoming vehicle corresponding to the first vehicle;

[0032] The first neural network model outputs a first control strategy according to the U-turn zone type, including: when the first neural network model identifies that the vehicle U-turn zone type is an optional U-turn point, determining that the first control strategy is an opportune U-turn strategy, specifically including: determining whether the current road condition allows U-turn according to the road condition information, and if not, generating a stop-and-wait U-turn strategy; if allowed, generating a time-limited U-turn strategy;

[0033] Generating a simulated traffic signal sequence based on the first control strategy includes:

[0034] Based on the stop-and-wait U-turn strategy, a simulated U-turn red light and a simulated stop line are issued to the first vehicle, instructing the first vehicle to stop and wait for a U-turn after the simulated stop line;

[0035] Alternatively, based on the time-limited U-turn strategy, a simulated slow down and yield sign and a warning message that an oncoming vehicle is turning around are issued to the oncoming vehicle. After receiving the second response message from the oncoming vehicle, a simulated U-turn green light, a simulated countdown sign and a countdown time are issued to the first vehicle, instructing the first vehicle to complete the U-turn action according to the simulated traffic signal.

[0036] Furthermore, the method further comprises:

[0037] The first neural network model determines whether a traffic event with a safety risk occurs on the current road based on the road condition information, and if so, outputs a second control strategy corresponding to the traffic event based on the road condition information, and generates multiple sets of third simulated traffic signal sequences based on the second control strategy;

[0038] Each group of the third simulated traffic signal sequences is sent to the connected vehicles related to the traffic event.

[0039] Furthermore, the traffic event is that the first vehicle is changing lanes, and the third simulated traffic signal sequence includes a simulated lane change signal light, a simulated traffic sign marking, and a simulated traffic signal countdown;

[0040] The method comprises:

[0041] After the first neural network model determines that a lane change is permitted based on the road condition information, it generates a lane change permission control strategy, and generates multiple sets of third simulated traffic signal sequences based on the lane change permission control strategy, wherein one set of the third simulated traffic signal sequences includes a left lane change green light signal and a corresponding signal expiration time point, recorded as a first sequence, and another set of the third simulated traffic signal sequences includes a slow down and yield sign and a corresponding signal expiration condition, recorded as a second sequence, wherein the slow down and yield sign expiration time point is when the first vehicle completes the lane change and the first vehicle maintains a safe distance from the second vehicle, the second vehicle being the vehicle associated with the current lane change event during the lane change process of the first vehicle;

[0042] The first sequence is sent to a first vehicle and displayed on an onboard terminal of the first vehicle, and the second sequence is sent to a second vehicle and displayed on an onboard terminal of the second vehicle.

[0043] Furthermore, determining whether the driving behavior of the first vehicle is in violation of traffic rules based on the first simulated traffic signal sequence and / or determining whether the driving behavior of other vehicles is in violation of traffic rules based on the second simulated traffic signal sequence includes:

[0044] Adding a digital signature to the first simulated traffic signal sequence or the second simulated traffic signal sequence and storing the signature on a blockchain;

[0045] Real-time monitoring is performed to determine whether the driving behavior of the first vehicle complies with the behavioral specifications corresponding to the first simulated traffic signal sequence, or real-time monitoring is performed to determine whether the driving behavior of other vehicles complies with the behavioral specifications corresponding to the second simulated traffic signal sequence. If not, the regulations, timestamps, and road condition snapshots violated by the violating vehicle are automatically recorded, a traffic behavior responsibility map is generated, and the map is uploaded to the traffic management platform.

[0046] In a second aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle cooperative control method based on simulated traffic signals as described in the first aspect of the present application.

[0047] In a third aspect, the present application provides an electronic device having a computer program stored thereon, comprising a processor and a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by the processor, the vehicle cooperative control method based on simulated traffic signals as described in the first aspect of the present application is implemented.

[0048] Different from the existing technology, the above technical solution provides a vehicle collaborative control method, medium and equipment based on simulated traffic signals. The method obtains real-time road condition information (including the status of physical traffic lights, vehicle position / driving parameters, pedestrian and obstacle information) through the vehicle collaborative perception module; when it is determined that the physical traffic light is not set or the traffic light fails, the driving intention request of the first vehicle is received, and the road condition information and driving intention are input into the first neural network model. After analysis by the first neural network model, a control strategy in response to the driving intention is output, and a simulated traffic signal sequence including simulated traffic lights or signs is generated; the simulated traffic signal sequence is sent to the corresponding vehicle on-board terminal for display, and the vehicle driving behavior is monitored in real time based on the sequence to see if it is in violation of traffic rules. Through the above solution, the responsibility identification mechanism can be clarified, and the problem of difficulty in tracing the vehicle driving behavior when the physical traffic light is missing or fails can be solved. At the same time, the sequence is only presented in the form of instructions, which can effectively reduce the computing power of the server.

[0049] The above-mentioned description of the invention content is only an overview of the technical solution of the present invention. In order to enable ordinary technicians in this field to more clearly understand the technical solution of the present invention, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned objects and other objects, features and advantages of the present invention easier to understand, the following is an explanation in combination with the specific implementation methods and drawings of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are only used to illustrate the principles, implementations, applications, features, and effects of the specific embodiments of the present invention and other related contents, and are not to be considered as limiting the present invention.

[0051] In the drawings of the specification:

[0052] Figure 1 A first flow chart of a vehicle cooperative control method based on simulated traffic signals according to a specific embodiment;

[0053] Figure 2 This is a first schematic diagram of a vehicle U-turn scenario involved in a specific embodiment;

[0054] Figure 3 A second schematic diagram of a vehicle U-turn scenario involved in a specific embodiment;

[0055] Figure 4 is a third schematic diagram of a vehicle U-turn scenario involved in a specific embodiment;

[0056] Figure 5 A fourth schematic diagram of a vehicle U-turn scenario according to a specific embodiment;

[0057] Figure 6 A schematic diagram of a module of an electronic device according to a specific embodiment;

[0058] Figure 7 This is a module architecture diagram of a vehicle cooperative control system based on simulated traffic signals according to a specific embodiment;

[0059] The reference numerals in the above drawings are described as follows:

[0060] 10. Electronic equipment;

[0061] 101. Processor;

[0062] 102. Storage medium. DETAILED DESCRIPTION

[0063] In order to explain in detail the possible application scenarios, technical principles, specific solutions that can be implemented, and the purpose and effects of the present invention, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present invention and are therefore only examples and are not intended to limit the scope of protection of the present invention.

[0064] References to "embodiments" herein mean that the specific features, structures, or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the term "embodiment" in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in the present invention, as long as there are no technical contradictions or conflicts, the various technical features mentioned in the embodiments can be combined in any manner to form a corresponding implementable technical solution.

[0065] Unless otherwise defined, the technical terms used herein have the same meanings as those generally understood by those skilled in the art to which the present invention belongs. The use of relevant terms herein is only for describing specific embodiments and is not intended to limit the present invention.

[0066] In the description of the present invention, the term "and / or" is used to describe a logical relationship between objects, indicating that three possible relationships exist. For example, A and / or B means: A exists, B exists, and both A and B exist. Furthermore, the character " / " generally indicates that the objects are in a logical "or" relationship.

[0067] In the present invention, terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0068] Without further restrictions, in the present invention, the words "include", "comprise", "have" or other similar expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0069] In the present invention, expressions such as "greater than," "less than," and "exceed" are understood to exclude the number itself; expressions such as "above," "below," and "within" are understood to include the number itself. Furthermore, in the description of the embodiments of the present invention, "multiple" means two or more (including two), and similar expressions related to "multiple," such as "multiple groups" and "multiple times," are also understood in this manner, unless otherwise specifically defined.

[0070] In the description of the embodiments of the present invention, the space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present invention or facilitating the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as limiting the embodiments of the present invention.

[0071] Unless otherwise expressly specified or limited, in the description of the embodiments of the present invention, the terms "installed", "connected", "connected", "fixed", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection between two elements or the interaction relationship between two elements. For those skilled in the art of the technology to which the present invention belongs, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0072] In the first aspect, Figure 1 As shown, the present application provides a vehicle cooperative control method based on simulated traffic signals, the method comprising the following steps:

[0073] Step S101: Vehicles collaboratively sense road condition information of a road where a first vehicle is located;

[0074] Step S102: When it is determined that no physical traffic light is installed on the road or the physical traffic light is out of service, receiving a driving intention request from a first vehicle, and inputting the road condition information and the driving intention request of the first vehicle into a first neural network model;

[0075] Step S103: The first neural network model outputs a first control strategy responsive to the driving intention based on the road condition information and the driving intention of the first vehicle, and generates a simulated traffic signal sequence based on the first control strategy, wherein the simulated traffic signal sequence includes a first simulated traffic signal sequence and a second simulated traffic signal sequence;

[0076] Step S104: sending the first simulated traffic signal sequence to the first vehicle and displaying it on the vehicle-mounted terminal of the first vehicle; sending the second simulated traffic signal sequence to other vehicles associated with the driving intention request of the first vehicle and displaying it on the vehicle-mounted terminals of the other vehicles;

[0077] Step S105: determining whether the driving behavior of the first vehicle is in violation of traffic rules based on the first simulated traffic signal sequence and / or determining whether the driving behavior of other vehicles is in violation of traffic rules based on the second simulated traffic signal sequence.

[0078] In step S101, the road condition information includes the setting of physical traffic lights, vehicle information, and pedestrian or obstacle position information, and the vehicle information includes vehicle position information and vehicle driving parameter information.

[0079] In step S102, the vehicle's driving intention includes left lane change, right lane change, emergency obstacle avoidance, acceleration, deceleration, cruising, going straight, turning (left / right), overtaking, parking, U-turn, etc. The first neural network model can be a convolutional neural network (CNN) or a recurrent neural network (RNN) and its variants (such as LSTM, GRU).

[0080] The failure of a physical traffic light can be determined in the following ways. A physical traffic light is considered to be failed when any of the following conditions are met: (a) the on-board camera recognizes that the physical traffic light has not been on for 10 seconds; (b) the V2X system receives the fault code issued by the traffic management platform; (c) within a 50-meter radius of the physical traffic light, at least three connected vehicles report that the physical traffic light is abnormal.

[0081] In step S103, the simulated traffic signal sequence is a collection of simulated traffic signals, and the simulated traffic signals include simulated traffic lights or simulated traffic signs. The collection of simulated traffic signals is a collection of control strategy implementation measures for all relevant vehicles involved in the driving intention of the first vehicle. The simulated traffic signals in the collection are matched one-to-one with the relevant vehicles, that is, the simulated traffic signals received by each vehicle are obtained by comprehensive calculation based on the road condition information around the current vehicle. Different vehicles under the same road condition can also be controlled by setting different simulated traffic signal sequences to realize customization of the control strategy.

[0082] The above scheme can output a control strategy based on the road condition information of the road and the driving intention of the first vehicle when there is no physical traffic light or the physical traffic light fails, and publish the simulated traffic signal sequence generated based on the control strategy to the relevant connected vehicles, wherein the first simulated traffic signal sequence is sent to the first vehicle, and the second simulated traffic signal sequence is sent to other vehicles. The other vehicles here refer to other vehicles that are related to the current driving intention of the first vehicle. For example, if the driving intention of the first vehicle is a lane change request, the other vehicles may be the vehicles on the left and right sides of the first vehicle, as well as the vehicles in front and behind. For another example, if the driving intention of the first vehicle is a U-turn request, the other vehicles may be the oncoming vehicles corresponding to the first vehicle.

[0083] Then, it can be judged whether the driving behavior of the first vehicle is in violation of traffic rules based on the first simulated traffic signal sequence and / or whether the driving behavior of other vehicles is in violation of traffic rules based on the second simulated traffic signal sequence. In this way, the simulated traffic signal sequence can take over the traffic control of the current road when the physical traffic signal is on, and the simulated traffic signal sequence refers to the instruction form issued to each connected vehicle (including the first vehicle and other vehicles). Compared with the method of directly planning a recommended driving path for each connected vehicle, it can greatly save transmission bandwidth and server computing power, and can make the division of rights and responsibilities of traffic accidents on the current road section in the event of failure of the physical traffic light clearer. It is only necessary to retrieve the simulated traffic signal sequence sent to each vehicle when a traffic accident occurs, and then refer to the judgment rules of the physical traffic light to make a judgment. The division of responsibilities is clear and can effectively improve the efficiency and safety of traffic control.

[0084] In some embodiments, the driving intention request of the first vehicle includes a U-turn request;

[0085] The first neural network model outputs a first control strategy in response to the driving intention based on the road condition information and the driving intention of the first vehicle, including: the first neural network model determines the type of the vehicle U-turn area based on the road condition information, and outputs a first control strategy according to the U-turn area type.

[0086] Preferably, the simulated traffic light includes a simulated U-turn light, and the simulated U-turn light includes any one of the following:

[0087] a simulated U-turn green light, used to indicate that the first vehicle is permitted to make a U-turn;

[0088] a simulated U-turn red light, used to indicate that the first vehicle is prohibited from making a U-turn;

[0089] A simulated U-turn yellow light is used to serve as a warning when the first vehicle is making a U-turn. When the simulated U-turn yellow light continues to flash, it indicates that the first vehicle needs to make a U-turn with caution after observing and confirming that it is safe. When the simulated U-turn green light turns into the simulated U-turn yellow light, it indicates that the U-turn permission is about to end.

[0090] The simulated traffic sign includes:

[0091] A simulated countdown sign is used to indicate the remaining operating time of a simulated traffic signal;

[0092] A simulated no-U-turn sign is used to indicate that a first vehicle is prohibited from making a U-turn on the current road;

[0093] a simulated slow down and yield sign, used to instruct the first vehicle or other vehicles associated with the driving intention request of the first vehicle to slow down and yield;

[0094] a simulated stop line, used to indicate the parking position of the first vehicle before turning around;

[0095] Simulated U-turn lane guide lines, used to indicate the driving route of the first vehicle when making a U-turn;

[0096] The simulated attention signal light sign is used to indicate that a physical signal light is installed in the first vehicle U-turn zone and vehicles should drive according to the physical signal light.

[0097] Preferably, the simulated traffic signal may also include simulated traffic personnel's commands. These simulated traffic personnel's commands are a superset of those of real traffic personnel. Simulated traffic personnel's commands not only include richer command gestures but can also be presented through the image of a simulated character. This simulated character can issue traffic control signals to specific connected vehicles through verbal dialogue or text.

[0098] In some embodiments, the vehicle U-turn zone types include a prohibited U-turn zone, a light-controlled U-turn point, and a non-light-controlled U-turn point, and the other vehicles include an oncoming vehicle corresponding to the first vehicle;

[0099] When the first neural network model identifies that the vehicle U-turn zone type is a no-U-turn zone, determining that the first control strategy is a no-U-turn strategy; generating a simulated traffic signal sequence based on the first control strategy includes: generating a simulated no-U-turn sign based on the no-U-turn strategy, and issuing the simulated no-U-turn sign to the first vehicle;

[0100] When the first neural network model identifies that the vehicle U-turn zone type is a light-controlled U-turn point, determining that the first control strategy is an indicated U-turn strategy; generating a simulated traffic signal sequence based on the first control strategy includes: generating a simulated attention signal light sign based on the indicated U-turn strategy, and issuing the simulated attention signal light sign to the first vehicle;

[0101] When the first neural network model identifies that the vehicle U-turn area type is a non-light-controlled U-turn point, it determines whether the current road condition allows U-turn based on the road condition information. If not allowed, a stop-and-wait U-turn strategy is generated. The simulated traffic signal sequence generated based on the first control strategy includes: issuing a simulated U-turn red light and a simulated stop line to the first vehicle, instructing the first vehicle to stop and wait for U-turn after the simulated stop line; if allowed, a time-limited U-turn strategy is generated. The simulated traffic signal sequence generated based on the first control strategy includes: issuing a simulated slowdown and yield sign and a warning message that an oncoming vehicle is turning around to the oncoming vehicle, and after receiving the first response information from the oncoming vehicle, issuing a simulated U-turn green light, a simulated countdown sign and a countdown time to the first vehicle, instructing the first vehicle to complete the U-turn action according to the simulated traffic signal.

[0102] In some other embodiments, the vehicle U-turn zone type includes an optional U-turn point, and the other vehicle includes an oncoming vehicle corresponding to the first vehicle;

[0103] The first neural network model outputs a first control strategy according to the U-turn zone type, including: when the first neural network model identifies that the vehicle U-turn zone type is an optional U-turn point, determining that the first control strategy is an opportune U-turn strategy, specifically including: determining whether the current road condition allows U-turn according to the road condition information, and if not, generating a stop-and-wait U-turn strategy; if allowed, generating a time-limited U-turn strategy;

[0104] Generating a simulated traffic signal sequence based on the first control strategy includes:

[0105] Based on the stop-and-wait U-turn strategy, a simulated U-turn red light and a simulated stop line are issued to the first vehicle, instructing the first vehicle to stop and wait for a U-turn after the simulated stop line;

[0106] Alternatively, based on the time-limited U-turn strategy, a simulated slow down and yield sign and a warning message that an oncoming vehicle is turning around are issued to the oncoming vehicle. After receiving the second response message from the oncoming vehicle, a simulated U-turn green light, a simulated countdown sign and a countdown time are issued to the first vehicle, instructing the first vehicle to complete the U-turn action according to the simulated traffic signal.

[0107] like Figure 2 As shown, vehicle A sends a U-turn request, and the first neural network model determines that the U-turn zone type is an optional U-turn point on the road section, and the control strategy is to make a U-turn at an appropriate time.

[0108] like Figure 3 As shown, the first simulated traffic signal sequence includes a planned simulated U-turn area, and a simulated U-turn lane guide line is issued to vehicle A (i.e., the first vehicle), such as Figure 3 Indicated by the green line in the middle.

[0109] like Figure 4 As shown, the vehicle-road collaboration senses that vehicle B (one of the other vehicles associated with the driving intention of the first vehicle A) is approaching in the opposite lane. At this time, vehicle A is likely to collide if it turns around. The first neural network model determines that vehicle A is not allowed to turn around at this time; the stop and wait U-turn strategy is executed, specifically, a simulated U-turn red light and a simulated stop line are issued to vehicle A, instructing vehicle A to stop and wait for U-turn after the simulated stop line; and a "front vehicle U-turn" warning message is issued to vehicle C, and vehicle C changes lanes to overtake.

[0110] like Figure 5 As shown, the vehicle-road collaboration senses vehicle B leaving the road section. The first neural network model determines that the road conditions allow for a U-turn and implements a time-limited U-turn control strategy. Specifically, a simulated slow down and yield sign and a warning message "oncoming vehicle U-turn ahead" are issued to vehicle D. Vehicle D responds to the U-turn control message by issuing a simulated U-turn green light, a simulated countdown sign, and a countdown timer to vehicle A, instructing vehicle A to complete the U-turn under the guidance of the simulated traffic signal.

[0111] In this way, when the physical traffic signal is missing, damaged, or obscured, the present application conducts a comprehensive analysis of the road condition information of the road where the first vehicle is located, combines the operating parameter information of the connected vehicle, generates a control strategy for the first vehicle when turning around, and generates a simulated traffic signal sequence based on the control strategy. By deploying simulated traffic signs, issuing simulated traffic lights to connected vehicles, etc., the effectiveness of the physical traffic signal is enhanced to meet the traffic management operation needs under complex road conditions.

[0112] For example, the simulated traffic signs include simulated traffic sign lines. The simulated traffic sign lines can be obtained in the following way: burying grating sensors every 3-5 meters along the road, monitoring the road boundary displacement in real time, generating road contour reference coordinates, converting the road width into Frenet coordinate system parameters (lateral offset δx, longitudinal curvature κ), generating a marking space matrix that is independent of vehicle dynamics, obtaining simulated traffic sign lines based on the marking space matrix, and publishing the simulated traffic sign lines to all connected vehicles.

[0113] In some embodiments, the method also includes: the first neural network model determines whether a traffic incident with safety risks has occurred on the current road based on road condition information; if so, outputs a second control strategy corresponding to the traffic incident based on the road condition information, and generates multiple groups of third simulated traffic signal sequences based on the second control strategy; and sends each group of the third simulated traffic signal sequences to the connected vehicles related to this traffic incident.

[0114] Preferably, the traffic events with safety risks include: any one or more of sudden severe weather, damage to roads and traffic facilities, traffic flow conflicts, traffic violations, and failure of physical traffic signals.

[0115] Furthermore, the traffic event is that the first vehicle is changing lanes, and the third simulated traffic signal sequence includes a simulated lane change signal light, a simulated traffic sign marking, and a simulated traffic signal countdown;

[0116] The method comprises:

[0117] After the first neural network model determines that a lane change is permitted based on the road condition information, it generates a lane change permission control strategy, and generates multiple sets of third simulated traffic signal sequences based on the lane change permission control strategy, wherein one set of the third simulated traffic signal sequences includes a left lane change green light signal and a corresponding signal expiration time point, recorded as a first sequence, and another set of the third simulated traffic signal sequences includes a slow down and yield sign and a corresponding signal expiration condition, recorded as a second sequence, wherein the slow down and yield sign expiration time point is when the first vehicle completes the lane change and the first vehicle maintains a safe distance from the second vehicle, the second vehicle being the vehicle associated with the current lane change event during the lane change process of the first vehicle;

[0118] The first sequence is sent to a first vehicle and displayed on an onboard terminal of the first vehicle, and the second sequence is sent to a second vehicle and displayed on an onboard terminal of the second vehicle.

[0119] For example, vehicle A traveling in the slow lane attempts to change lanes left to the fast lane, while vehicle B in the fast lane is traveling behind vehicle A. The trained first neural network model recognizes this left lane change traffic event.

[0120] Based on the traffic event information and the road conditions surrounding vehicle A, the first neural network model generates a second control strategy, authorizing vehicle A to complete a left lane change within a specified timeframe and requiring vehicle B to slow down and yield. This strategy then generates a simulated traffic signal sequence. This simulated traffic signal sequence consists of two sets of simulated traffic signals: one set, issued to vehicle A, contains a green light for a left lane change and a set expiration time; the other set, issued to vehicle B, instructs vehicle B to slow down and yield, with a set expiration condition requiring that vehicles A and B maintain a safe distance after vehicle A completes the lane change. The simulated traffic signal sequences are then issued to vehicles A and B, respectively. Vehicle A receives the simulated lane change signal and completes the left lane change within the specified timeframe. Once vehicles A and B have established a safe distance in the fast lane, the traffic event is controlled.

[0121] In some embodiments, determining whether the driving behavior of the first vehicle is in violation of traffic rules based on the first simulated traffic signal sequence and / or determining whether the driving behavior of other vehicles is in violation of traffic rules based on the second simulated traffic signal sequence includes:

[0122] S1: Adding a digital signature to the first simulated traffic signal sequence or the second simulated traffic signal sequence and storing the signature on the blockchain;

[0123] S2: Real-time monitoring of whether the driving behavior of the first vehicle complies with the behavioral specifications corresponding to the first simulated traffic signal sequence, or real-time monitoring of whether the driving behavior of other vehicles complies with the behavioral specifications corresponding to the second simulated traffic signal sequence. If not, the regulations, timestamps, and road condition snapshots violated by the illegal vehicles are automatically recorded, and a traffic behavior responsibility map is generated and uploaded to the traffic management platform.

[0124] In step S1, a hash calculation is performed on the first simulated traffic signal sequence (corresponding to the first vehicle) and the second simulated traffic signal sequence (corresponding to other vehicles) to generate a unique digest. The digest is encrypted using the private key of the traffic management department to generate a digital signature to ensure data integrity and source credibility. The blockchain evidence storage process is as follows: the first simulated traffic signal sequence or the second simulated traffic signal sequence and the digital signature are packaged into a data block, and the data block is broadcast to the consensus node through the consortium chain or private chain network. After the node verifies the validity of the signature, the data block is written to the blockchain to generate an unalterable timestamp record.

[0125] In step S2, the vehicle position, speed, acceleration and other dynamic data are collected in real time through the vehicle-road collaborative perception module. The vehicle-road collaborative perception module can apply for roadside units (RSU), on-board terminals (OBU) and traffic cameras, and obtain the interaction data between vehicles and traffic signals through V2X technology (such as DSRC or C-V2X). Then build a rule engine to compare the real-time collected vehicle behavior data with the behavior specifications corresponding to the simulated traffic signal sequence (such as red light stop, speed limit, etc.). When a vehicle violation is detected, it will be automatically recorded. The record content includes the violated regulations, the precise time (such as based on GPS timing or blockchain timestamp), and a snapshot of the road conditions (fused camera images, radar point cloud data), and the evidence data is encrypted to ensure privacy and security.

[0126] A traffic behavior responsibility map is then constructed based on a graph database, with nodes including vehicles, simulated traffic signal sequences, and road elements. This map quantifies the responsibilities of each participant through a graph computing model, reducing subjective judgment errors and enabling automatic identification of vehicle traffic behavior when physical traffic lights are not set or are malfunctioning.

[0127] In a second aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle cooperative control method based on simulated traffic signals as described in the first aspect of the present invention.

[0128] The computer-readable storage medium may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories.

[0129] The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface storage, an optical disc, or a compact disc read-only memory (CD ROM); the magnetic surface storage may be a magnetic disk storage or a magnetic tape storage.

[0130] The volatile memory may be a random access memory (RAM) that is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronized dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM). The computer-readable storage medium described in the embodiments of the present invention is intended to include these and any other suitable types of memory.

[0131] like Figure 6 As shown, in the third aspect, the present invention provides an electronic device 10, including a processor 101 and a storage medium 102, on which a computer program is stored. When the computer program is executed by the processor, the vehicle cooperative control method based on simulated traffic signals as described in the first aspect of the present invention is implemented.

[0132] In some embodiments, the processor can be implemented through software, hardware, firmware or a combination thereof, and can use circuits, single or multiple application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), central processing units (CPU), controllers, microcontrollers, and at least one of microprocessors, so that the processor can execute some or all of the steps or any combination of the steps in the vehicle cooperative control method based on simulated traffic signals described in the various embodiments of the present application.

[0133] In a fourth aspect, the present application provides a traffic management system based on simulated traffic signals, the system comprising:

[0134] An electronic device, which is the electronic device as described in the third aspect of this application;

[0135] The vehicle-mounted device is communicatively connected with the electronic device and is used to receive the simulated traffic signal.

[0136] like Figure 7 As shown, the electronic device involved in this application can have a built-in cloud computing unit, which has a simulated traffic signal system built on top of the physical traffic signal system. The function of the simulated traffic signal system is to generate corresponding simulated traffic signals based on the surrounding traffic situation of each vehicle's road conditions and issue them to the corresponding vehicles for traffic control. The simulated traffic signal is a simulated electronic traffic signal dynamically generated by the computing unit based on road traffic conditions and the driving intentions of the connected vehicles, and is issued to the relevant connected vehicles via the communication network.

[0137] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concepts of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A vehicle cooperative control method based on simulated traffic signals, characterized in that: The method comprises the following steps: The vehicles cooperatively sense road condition information of a road on which the first vehicle is located, the road condition information including the setting of a physical traffic light, vehicle information, and location information of pedestrians or obstacles, and the vehicle information including vehicle location information and vehicle driving parameter information; When it is determined that no physical traffic light is provided on the road or the physical traffic light is out of service, receiving a driving intention request from a first vehicle, and inputting the road condition information and the driving intention request of the first vehicle into a first neural network model; The first neural network model outputs a first control strategy responsive to the driving intention based on the road condition information and the driving intention of the first vehicle, and generates a simulated traffic signal sequence based on the first control strategy, wherein the simulated traffic signal sequence is a set of simulated traffic signals, the simulated traffic signals including simulated traffic lights or simulated traffic signs, and the simulated traffic signal sequence includes a first simulated traffic signal sequence and a second simulated traffic signal sequence; sending the first simulated traffic signal sequence to a first vehicle and displaying it on an onboard terminal of the first vehicle, and sending the second simulated traffic signal sequence to other vehicles associated with the driving intention request of the first vehicle and displaying it on the onboard terminals of the other vehicles; Whether the driving behavior of the first vehicle is in violation of traffic rules is determined based on the first simulated traffic signal sequence and / or whether the driving behavior of other vehicles is in violation of traffic rules is determined based on the second simulated traffic signal sequence.

2. The vehicle cooperative control method based on simulated traffic signals according to claim 1, characterized in that: The driving intention request of the first vehicle includes a U-turn request; The first neural network model outputs a first control strategy in response to the driving intention based on the road condition information and the driving intention of the first vehicle, including: the first neural network model determines the type of the vehicle U-turn area based on the road condition information, and outputs a first control strategy according to the U-turn area type.

3. The vehicle cooperative control method based on simulated traffic signals according to claim 2, characterized in that: The simulated traffic light includes a simulated U-turn light, and the simulated U-turn light includes any one of the following: a simulated U-turn green light, used to indicate that the first vehicle is permitted to make a U-turn; a simulated U-turn red light, used to indicate that the first vehicle is prohibited from making a U-turn; A simulated U-turn yellow light is used to serve as a warning when the first vehicle is making a U-turn. When the simulated U-turn yellow light continues to flash, it indicates that the first vehicle needs to make a U-turn with caution after observing and confirming that it is safe. When the simulated U-turn green light turns into the simulated U-turn yellow light, it is used to indicate that the U-turn permission is about to end; The simulated traffic sign includes: A simulated countdown sign is used to indicate the remaining operating time of a simulated traffic signal; A simulated no-U-turn sign is used to indicate that a first vehicle is prohibited from making a U-turn on the current road; a simulated slow down and yield sign, used to instruct the first vehicle or other vehicles associated with the driving intention request of the first vehicle to slow down and yield; a simulated stop line, used to indicate the parking position of the first vehicle before turning around; Simulated U-turn lane guide lines, used to indicate the driving route of the first vehicle when making a U-turn; The simulated attention signal light sign is used to indicate that a physical signal light is installed in the first vehicle U-turn zone and vehicles should drive according to the physical signal light.

4. The vehicle cooperative control method based on simulated traffic signals according to claim 3, characterized in that: The vehicle U-turn zone types include a prohibited U-turn zone, a light-controlled U-turn point, and a non-light-controlled U-turn point, and the other vehicles include the oncoming vehicle corresponding to the first vehicle; When the first neural network model identifies that the vehicle U-turn zone type is a no-U-turn zone, determining that the first control strategy is a no-U-turn strategy; Generating a simulated traffic signal sequence based on the first control strategy includes: generating a simulated no-U-turn sign based on the no-U-turn strategy, and issuing the simulated no-U-turn sign to the first vehicle; When the first neural network model identifies that the vehicle U-turn zone type is a light-controlled U-turn point, determining that the first control strategy is an indicated U-turn strategy; generating a simulated traffic signal sequence based on the first control strategy includes: generating a simulated attention signal light sign based on the indicated U-turn strategy, and issuing the simulated attention signal light sign to the first vehicle; When the first neural network model identifies that the vehicle U-turn area type is a non-light-controlled U-turn point, it determines whether the current road condition allows U-turn based on the road condition information. If not allowed, a stop-and-wait U-turn strategy is generated. The simulated traffic signal sequence generated based on the first control strategy includes: issuing a simulated U-turn red light and a simulated stop line to the first vehicle, instructing the first vehicle to stop and wait for U-turn after the simulated stop line; if allowed, a time-limited U-turn strategy is generated. The simulated traffic signal sequence generated based on the first control strategy includes: issuing a simulated slowdown and yield sign and a warning message that an oncoming vehicle is turning around to the oncoming vehicle, and after receiving the first response information from the oncoming vehicle, issuing a simulated U-turn green light, a simulated countdown sign and a countdown time to the first vehicle, instructing the first vehicle to complete the U-turn action according to the simulated traffic signal.

5. The vehicle cooperative control method based on simulated traffic signals according to claim 3, characterized in that: The vehicle U-turn zone type includes an optional U-turn point, and the other vehicles include an oncoming vehicle corresponding to the first vehicle; The first neural network model outputs a first control strategy according to the U-turn zone type, including: when the first neural network model identifies that the vehicle U-turn zone type is an optional U-turn point, determining that the first control strategy is an opportune U-turn strategy, specifically including: determining whether the current road condition allows U-turn according to the road condition information, and if not, generating a stop-and-wait U-turn strategy; if allowed, generating a time-limited U-turn strategy; Generating a simulated traffic signal sequence based on the first control strategy includes: Based on the stop-and-wait U-turn strategy, a simulated U-turn red light and a simulated stop line are issued to the first vehicle, instructing the first vehicle to stop and wait for a U-turn after the simulated stop line; Alternatively, based on the time-limited U-turn strategy, a simulated slow down and yield sign and a warning message that an oncoming vehicle is turning around are issued to the oncoming vehicle. After receiving the second response message from the oncoming vehicle, a simulated U-turn green light, a simulated countdown sign and a countdown time are issued to the first vehicle, instructing the first vehicle to complete the U-turn action according to the simulated traffic signal.

6. The vehicle cooperative control method based on simulated traffic signals according to claim 1, characterized in that: The method further comprises: The first neural network model determines whether a traffic event with a safety risk occurs on the current road based on the road condition information, and if so, outputs a second control strategy corresponding to the traffic event based on the road condition information, and generates multiple sets of third simulated traffic signal sequences based on the second control strategy; Each group of the third simulated traffic signal sequences is sent to the connected vehicles related to the traffic event.

7. The vehicle cooperative control method based on simulated traffic signals according to claim 6, characterized in that: The traffic event is that the first vehicle is changing lanes, and the third simulated traffic signal sequence includes a simulated lane change signal light, simulated traffic sign markings, and a simulated traffic signal countdown; The method comprises: After the first neural network model determines that a lane change is permitted based on the road condition information, it generates a lane change permission control strategy, and generates multiple sets of third simulated traffic signal sequences based on the lane change permission control strategy, wherein one set of the third simulated traffic signal sequences includes a left lane change green light signal and a corresponding signal expiration time point, recorded as a first sequence, and another set of the third simulated traffic signal sequences includes a slow down and yield sign and a corresponding signal expiration condition, recorded as a second sequence, wherein the slow down and yield sign expiration time point is when the first vehicle completes the lane change and the first vehicle maintains a safe distance from the second vehicle, the second vehicle being the vehicle associated with the current lane change event during the lane change process of the first vehicle; The first sequence is sent to a first vehicle and displayed on an onboard terminal of the first vehicle, and the second sequence is sent to a second vehicle and displayed on an onboard terminal of the second vehicle.

8. The vehicle cooperative control method based on simulated traffic signals according to claim 1, characterized in that: Determining whether the driving behavior of the first vehicle is in violation of traffic rules based on the first simulated traffic signal sequence and / or determining whether the driving behavior of other vehicles is in violation of traffic rules based on the second simulated traffic signal sequence includes: Adding a digital signature to the first simulated traffic signal sequence or the second simulated traffic signal sequence and storing the signature on a blockchain; Real-time monitoring is performed to determine whether the driving behavior of the first vehicle complies with the behavioral specifications corresponding to the first simulated traffic signal sequence, or real-time monitoring is performed to determine whether the driving behavior of other vehicles complies with the behavioral specifications corresponding to the second simulated traffic signal sequence. If not, the regulations, timestamps, and road condition snapshots violated by the violating vehicle are automatically recorded, a traffic behavior responsibility map is generated, and the map is uploaded to the traffic management platform.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the vehicle cooperative control method based on simulated traffic signals as described in any one of claims 1 to 8 is implemented.

10. An electronic device having a computer program stored thereon, characterized in that: It includes a processor and a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by the processor, it implements the vehicle cooperative control method based on simulated traffic signals as described in any one of claims 1 to 8.

Images