Vehicle lane changing command control method based on virtual traffic signal, medium and equipment

Abstract

The invention discloses a virtual traffic signal-based vehicle lane changing command control method, medium and equipment, and the method comprises the steps: enabling a vehicle to cooperatively sense the first traffic road condition information in front of a vehicle to be subjected to lane changing, and inputting the first traffic road condition information and the path planning information of the vehicle to be subjected to lane changing into a first neural network model, inputting the vehicle lane changing reason, the driving track information of the vehicle waiting for lane changing, the second traffic road condition information behind the vehicle, the third traffic road condition information on the side of the vehicle and the fourth traffic road condition information of the target lane into a second neural network model so as to enable the second neural network model to output a management and control strategy; a virtual traffic signal sequence is generated based on the management and control strategy; and respectively issuing the virtual traffic signal sequence to the vehicle waiting for lane changing or other vehicles associated with the lane changing event. According to the scheme, the virtual traffic signal sequence can be generated when the vehicle changes the lane and is published to the related network connection vehicle, and the refined traffic management requirement is met.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and in particular to a vehicle lane change command and control method, medium and device based on virtual traffic signals. Background Art

[0002] Despite the continuous advancement of autonomous driving technology, traffic conflicts caused by lane changes are still a major traffic hazard. Existing vehicle lane changes usually rely on human or vehicle-mounted systems for identification and judgment, lacking a global control mechanism, making it difficult to achieve refined vehicle lane change traffic management needs. Summary of the invention

[0003] In view of the above problems, the present invention provides a vehicle lane change command and control method, medium and device based on virtual traffic signals, so as to solve the problem that the existing vehicle lane change is difficult to meet the refined management requirements.

[0004] To achieve the above objectives, in a first aspect, the present application provides a vehicle lane change command and control method based on a virtual traffic signal, the method comprising the following steps: Receive a lane change request and path planning information sent by a vehicle to be lane changed; The vehicle-road collaboration senses the first traffic condition information ahead of the vehicle to change lanes; Inputting road condition information ahead of the vehicle to be changed lanes and path planning information of the vehicle to be changed lanes into a first neural network model, and identifying a vehicle lane change reason corresponding to the vehicle to be changed lanes based on the first neural network model, wherein the vehicle lane change reason includes at least one of the following three types: overtaking, avoiding obstacles, or turning at a road intersection; The vehicle-road collaboration senses the second traffic condition information behind the vehicle to be changed, the third traffic condition information on the side, and the fourth traffic condition information on the target lane to be changed, and obtains the driving trajectory information of the vehicle to be changed; Inputting the second traffic condition information, the third traffic condition information, the fourth traffic condition information, the driving trajectory information and the path planning information into a second neural network model, so that the second neural network model outputs a control strategy in response to the lane change request; Generate a virtual traffic signal sequence based on the control strategy, wherein the virtual traffic signal sequence is a collection of virtual traffic signals, and the virtual traffic signals include virtual lane change lights or virtual traffic signs; The virtual traffic signal sequence is respectively issued to the vehicle to be changed lanes or other vehicles associated with the lane change event.

[0005] Optionally, the virtual lane change signal light includes any one of the following: A virtual left lane change green light is used to indicate that the vehicle to be changed lanes is allowed to change left lanes; A virtual left lane change red light is used to indicate that the vehicle to be changed lanes is prohibited from changing lanes left; A virtual yellow left lane-changing light is used to serve as a warning during the lane-changing process of the vehicle to be changed. When the virtual yellow left lane-changing light flashes continuously, it is used to indicate that the vehicle to be changed needs to change lanes cautiously after observing and confirming safety; when the virtual green left lane-changing light turns into the virtual yellow left lane-changing light, it is used to indicate that the left lane-changing permission is about to end; A virtual right lane change green light is used to indicate that the vehicle to be changed lanes is allowed to change right lanes; A virtual right lane change red light is used to indicate that the vehicle to be changed lanes is prohibited from changing lanes right; A virtual yellow right lane change light is used to serve as a warning during the lane change process of the vehicle to be changed. When the virtual yellow right lane change light continues to flash, it is used to indicate that the vehicle to be changed needs to change right lanes cautiously after observing and confirming safety; when the virtual green right lane change light turns into the virtual yellow right lane change light, it is used to indicate that the right lane change access is about to end; The virtual traffic sign includes: The virtual slow down and yield sign is used to instruct the vehicle to change lanes or other vehicles associated with the lane change event to slow down and yield.

[0006] Optionally, the reason for the vehicle lane change identified by the first neural network model is overtaking, and the control strategy includes allowing the vehicle to change lanes, prohibiting the vehicle to change lanes, or changing lanes cautiously; When the control strategy is to prohibit the vehicle to be changed from changing lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to be changed or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change red light or a virtual right lane change red light, and sending the virtual left lane change red light or the virtual right lane change red light to the vehicle to be changed; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to the vehicle traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

[0007] Optionally, the reason for the vehicle lane change identified by the first neural network model is to avoid an obstacle, and the control strategy includes allowing the vehicle to change lanes, merge in an orderly manner, or change lanes cautiously; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to other vehicles traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is orderly merging, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be changed or other vehicles associated with the lane change event, including: generating merging insertion point position information, and a virtual left lane change green light or a virtual right lane change green light, sending the merging insertion point position information and the virtual left lane change green light or the virtual right lane change green light to the vehicle to be changed, and sending the virtual slow down and yield sign to other vehicles on the target lane that are located behind the merging insertion point position information; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

[0008] Optionally, the first neural network model identifies that the reason for the vehicle changing lanes is turning at a road intersection, and the control strategy includes allowing the vehicle to change lanes, illegally cut in line, merge in an orderly manner, or change lanes cautiously; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to other vehicles traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is illegal queue jumping, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to be changed lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change red light or a virtual right lane change red light, and sending the virtual left lane change red light or the virtual right lane change red light to the vehicle to be changed lanes; When the control strategy is orderly lane merging, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be changed lanes or other vehicles associated with the lane change event, including: generating the merging insertion point position information, and a virtual left lane change green light or a virtual right lane change green light, sending the merging insertion point position information, and the virtual left lane change green light or the virtual right lane change green light to the vehicle to be changed lanes, and sending the virtual slow down and yield sign to other vehicles on the target lane that are located behind the merging insertion point position information; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

[0009] Optionally, the first neural network model is trained according to the following method: Acquire a first sample data set, where the first sample data set includes first sample path planning information corresponding to the sample vehicle and first sample traffic condition information ahead of the sample vehicle; Performing data expansion on the first sample data set, and randomly arranging and combining the first sample data in the expanded first sample data set to obtain multiple groups of first test cases; Inputting multiple groups of the first test cases into the first neural network model to be trained for iterative training to obtain a trained first neural network model.

[0010] Optionally, the second neural network model is trained according to the following method: Acquire a second sample data set, wherein the second sample data set includes second sample traffic condition information, third sample traffic condition information, fourth sample traffic condition information, and sample driving trajectory information; Performing data expansion on the second sample data set, and randomly arranging and combining the second sample data in the expanded second sample data set and the first sample data in the expanded first sample data set to obtain multiple groups of second test cases; Input multiple groups of the second test cases into the second neural network model to be trained for iterative training to obtain a trained second neural network model.

[0011] 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 lane change command and control method based on virtual traffic signals as described in the first aspect of the present application.

[0012] 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 lane change command and control method based on virtual traffic signals as described in the first aspect of the present application is implemented.

[0013] Different from the prior art, the above technical solution provides a vehicle lane change command and control method, medium and equipment based on virtual traffic signals, the method includes: vehicle-road cooperatively perceives the first traffic condition information in front of the vehicle to be changed, inputs the first traffic condition information and the path planning information of the vehicle to be changed into the first neural network model, obtains the reason for the vehicle lane change, and then inputs the reason for the vehicle lane change, the driving trajectory information of the vehicle to be changed, the second traffic condition information behind the vehicle, the third traffic condition information on the side and the fourth traffic condition information on the target lane to be changed into the second neural network model, so that the second neural network model outputs a control strategy; and generates a virtual traffic signal sequence based on the control strategy; and publishes the virtual traffic signal sequence to the vehicle to be changed or other vehicles associated with this lane change event. The above scheme can generate a virtual traffic signal sequence when the vehicle changes lanes and publish it to related networked vehicles, and can realize dynamic, real-time and differentiated traffic control and guidance when the vehicle changes lanes, meeting the refined traffic management needs of vehicle lane changes.

[0014] The above-mentioned records related to the content of the invention are only an overview of the technical solution of the present invention. In order to enable ordinary technicians in the 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 in order to make the above-mentioned purpose and other purposes, features and advantages of the present invention easier to understand, the following is a description in combination with the specific implementation mode of the present invention and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The 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 shall not be considered as limiting the present invention.

[0016] In the drawings of the specification: Figure 1 A first flow chart of a vehicle lane change command and control method based on a virtual traffic signal according to a specific implementation method; Figure 2 A second flow chart of a vehicle lane change command and control method based on a virtual traffic signal according to a specific implementation method; Figure 3 A third flow chart of a vehicle lane change command and control method based on a virtual traffic signal according to a specific implementation method; Figure 4 It is a module schematic diagram of the electronic device described in the specific implementation mode; Figure 5 A module architecture diagram of a traffic management system based on virtual traffic signals according to a specific implementation method; Figure 6 A schematic diagram of a vehicle lane change command and control process based on a virtual traffic signal according to a specific implementation method; The reference numerals in the above drawings are described as follows: 10. Electronic equipment; 101. Processor; 102. Storage medium. DETAILED DESCRIPTION

[0017] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects of the present invention, the following is a detailed description in combination with the specific embodiments listed and 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 used as examples, and cannot be used to limit the scope of protection of the present invention.

[0018] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The word "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present invention, as long as there is no technical contradiction or conflict, the various technical features mentioned in each embodiment can be combined in any way to form a corresponding implementable technical solution.

[0019] 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.

[0020] In the description of the present invention, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in a logical relationship of "or".

[0021] 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.

[0022] Without further restrictions, in the present invention, the words "include", "comprises", "has" 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.

[0023] In the present invention, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of the present invention, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0024] 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 referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present invention.

[0025] Unless otherwise expressly specified or limited, in the description of the embodiments of the present invention, the terms such as "install", "connect", "connect", "fix", "set" and the like 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 of two elements or the interaction relationship between two elements. For those skilled in the art of the technical field 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 the specific circumstances.

[0026] like Figure 1 As shown, in a first aspect, the present application provides a vehicle lane change command and control method based on a virtual traffic signal, the method comprising the following steps: Step S101: receiving a lane change request and path planning information sent by a vehicle to change lanes.

[0027] In step S101, the lane change request of the vehicle can be triggered by the driver of the vehicle to be changed lanes or the vehicle-mounted system usually operating or controlling the relevant components on the vehicle, such as turning on the lane change turn signal or issuing a voice control command. The path planning information includes global path planning or local path planning. Preferably, in this embodiment, the path planning information is local path planning. Compared with global path planning, local path planning refers to an algorithm used to generate a local motion path of a vehicle in the field of vehicle navigation or moving vehicles. These algorithms are designed to enable the vehicle to reach the target point as efficiently as possible while avoiding obstacles and maintaining a safe distance.

[0028] Step S102: Vehicle-road collaboration senses first traffic condition information ahead of the vehicle to change lanes.

[0029] In step S102, the first traffic condition information includes weather information, road surface condition information of the road on which the vehicle to be changed lanes is currently traveling, physical traffic signal information, position speed and direction information of vehicles and pedestrians in front of the vehicle to be changed lanes, driving parameters of the vehicle to be changed lanes, etc.

[0030] Step S103: inputting the road condition information ahead of the vehicle to be changed lanes and the path planning information of the vehicle to be changed lanes into a first neural network model, and identifying the vehicle lane change reason corresponding to the vehicle to be changed lanes based on the first neural network model.

[0031] In step S103, the reason for the vehicle changing lanes includes at least one of the following three: overtaking, avoiding obstacles or turning at a road intersection.

[0032] Step S104: The vehicle-road collaboration senses the second traffic condition information behind the vehicle to change lanes, the third traffic condition information on the side, and the fourth traffic condition information on the target lane to be changed, and obtains the driving trajectory information of the vehicle to change lanes.

[0033] In step S104, the second traffic condition information includes the position speed and direction information of vehicles and pedestrians behind the vehicle to be changed, and the driving parameters of the vehicle behind the vehicle to be changed. The third traffic condition information includes the position speed and direction information of vehicles and pedestrians on the side of the vehicle to be changed, and the driving parameters of the vehicle on the side of the vehicle to be changed. The target lane to be changed refers to the road after the vehicle to be changed is ready to change lanes. For example, if the vehicle to be changed is ready to change lanes from road A to road B, then road A is the road on which the vehicle to be changed is currently traveling, and road B is the target lane to be changed corresponding to the vehicle to be changed. At this time, the fourth traffic condition information refers to the speed and direction information of vehicles or pedestrians on road B, and the driving parameters of vehicles on road B behind the vehicle to be changed. Driving trajectory information refers to the driving trajectory calculated based on the speed, driving direction, and surrounding vehicle conditions of the vehicle to be changed.

[0034] Step S105: input the second traffic condition information, the third traffic condition information, the fourth traffic condition information, the driving trajectory information and the path planning information into a second neural network model, so that the second neural network model outputs a control strategy in response to the lane change request.

[0035] In step S104 and step S105, the first neural network model and / or the second neural network model may be a convolutional neural network (CNN) or a recurrent neural network (RNN) and variants thereof (such as LSTM, GRU).

[0036] Step S106: Generate a virtual traffic signal sequence based on the control strategy, where the virtual traffic signal sequence is a collection of virtual traffic signals.

[0037] In step S106, the virtual traffic signal sequence is a collection of control strategy implementation measures for all relevant vehicles (including the vehicle to be changed, the rear vehicle of the lane where the vehicle to be changed is located, the rear vehicle of the target lane, etc.) in this lane change event. The virtual traffic signals in the collection are matched one-to-one with the relevant vehicles, that is, the virtual traffic signal received by each vehicle is determined according to the control strategy of the vehicle to be changed lanes output by the second neural network model, and the control strategy responding to the lane change request of the vehicle to be changed lanes is obtained by comprehensive calculation based on the vehicle lane change reason of the vehicle to be changed lanes and the road condition information around it, thereby realizing the customization of the vehicle lane change control strategy.

[0038] Step S107: issuing the virtual traffic signal sequence to the vehicle to be changed lanes or other vehicles associated with the lane change event.

[0039] In step S107, the lane change event refers to the entire process from the vehicle to be changed lanes initiating a lane change request to the prohibition of lane change or the completion of allowing lane change. Other vehicles associated with the lane change event include but are not limited to: vehicles located behind or to the side of the current vehicle to be changed lanes and traveling on the same road as the vehicle to be changed lanes, and vehicles located on the target road to be changed and in front of or behind the vehicle to be changed lanes.

[0040] In some embodiments, the virtual traffic signal includes a virtual lane change signal light or a virtual traffic sign. The virtual traffic signal is a virtualized electronic traffic signal dynamically generated by a cloud server according to road traffic conditions, and is issued to related networked vehicles via a communication network, so as to achieve dynamic, real-time and differentiated control and guidance of traffic activities, so that traffic activities can be managed in a refined manner.

[0041] Virtual traffic signals are a complement, enhancement and emergency adjustment to physical traffic signals. When physical traffic signals are missing, damaged or obscured, this application comprehensively analyzes traffic conditions information, combines the operating parameter information of relevant vehicles, generates a control strategy for corresponding vehicles when changing lanes, and generates a virtual traffic signal sequence based on the control strategy. By deploying virtual traffic signs and issuing virtual traffic lights to connected vehicles, physical traffic signals are enhanced to meet the traffic management needs under complex road conditions.

[0042] Generally, a vehicle lane change is divided into a left lane change or a right lane change. Therefore, in this embodiment, the virtual lane change signal light is a superset of a physical traffic signal light, and the virtual lane change signal light includes any one of the following: A virtual left lane change green light is used to indicate that the vehicle to be changed lanes is allowed to change left lanes; A virtual left lane change red light is used to indicate that the vehicle to be changed lanes is prohibited from changing lanes left; A virtual yellow left lane-changing light is used to serve as a warning during the lane-changing process of the vehicle to be changed. When the virtual yellow left lane-changing light flashes continuously, it is used to indicate that the vehicle to be changed needs to change lanes cautiously after observing and confirming safety; when the virtual green left lane-changing light turns into the virtual yellow left lane-changing light, it is used to indicate that the left lane-changing permission is about to end; A virtual right lane change green light is used to indicate that the vehicle to be changed lanes is allowed to change right lanes; A virtual right lane change red light is used to indicate that the vehicle to be changed lanes is prohibited from changing lanes right; The virtual right lane change yellow light is used to serve as a warning during the lane change process of the vehicle to be changed. When the virtual right lane change yellow light continues to flash, it is used to indicate that the vehicle to be changed lanes needs to change right lanes cautiously after observing and confirming safety; when the virtual right lane change green light turns into the virtual right lane change yellow light, it is used to indicate that the right lane change access is about to end.

[0043] In this embodiment, the virtual traffic sign is a superset of the physical traffic sign. The virtual traffic sign includes: a virtual slow down and yield sign, which is used to instruct the vehicle to change lanes or other vehicles associated with the lane change event to slow down and yield.

[0044] In other embodiments, the virtual traffic signal may also include virtual traffic markings and virtual traffic personnel's commands, wherein the virtual traffic markings are a superset of physical traffic markings. The virtual traffic personnel's commands are a superset of physical traffic personnel's commands. The virtual traffic personnel's commands not only have richer command gestures, but can also be presented through the image of a virtual character, which can send traffic command signals to specific connected vehicles through verbal dialogue or text.

[0045] In some embodiments, the reason for the vehicle lane change identified by the first neural network model is overtaking, and the control strategy includes allowing the vehicle to change lanes, prohibiting the vehicle to change lanes, or changing lanes cautiously; When the control strategy is to prohibit the vehicle to be changed from changing lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to be changed or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change red light or a virtual right lane change red light, and sending the virtual left lane change red light or the virtual right lane change red light to the vehicle to be changed; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to the vehicle traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

[0046] In some embodiments, the reason for the vehicle lane change identified by the first neural network model is to avoid an obstacle, and the control strategy includes allowing the vehicle to change lanes, merge in an orderly manner, or change lanes cautiously; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to other vehicles traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is orderly merging, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be changed or other vehicles associated with the lane change event, including: generating merging insertion point position information, and a virtual left lane change green light or a virtual right lane change green light, sending the merging insertion point position information and the virtual left lane change green light or the virtual right lane change green light to the vehicle to be changed, and sending the virtual slow down and yield sign to other vehicles on the target lane that are located behind the merging insertion point position information; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

[0047] In this embodiment, whether the control strategy needs to be determined as an orderly lane merging can be determined by a comprehensive judgment based on whether there is a continuous flow of traffic on the target lane by the second neural network model in combination with the second traffic condition information, the third traffic condition information, the fourth traffic condition information, the driving trajectory information and the path planning information.

[0048] like Figure 6 As shown, car A is the vehicle to change lanes, and an obstacle appears in front of the road where car A is traveling. After comprehensive judgment by the first neural network model, the reason why car A initiates the lane change is to avoid the obstacle. Since cars B and C are driving in the left lane, the control strategy output by the second neural network model is to change lanes with caution. At this time, a virtual left lane change green light will be sent to car A, and the virtual slow down and yield sign and insertion point position information will be sent to car C. The insertion point position information can be presented on the on-board display screen of car C in the form of a virtual frame. When presenting, the simulated trajectory of car A's insertion process can also be simulated, and car C can be reminded in real time of the possible overlapping parts between the body of car C and the simulated trajectory, so as to remind car C to slow down and avoid collision.

[0049] In some embodiments, the first neural network model identifies that the reason for the vehicle changing lanes is turning at a road intersection, and the control strategy includes allowing the vehicle to change lanes, illegally cut in line, merge in an orderly manner, or change lanes cautiously; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to other vehicles traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is illegal queue jumping, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to be changed lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change red light or a virtual right lane change red light, and sending the virtual left lane change red light or the virtual right lane change red light to the vehicle to be changed lanes; When the control strategy is orderly lane merging, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be changed lanes or other vehicles associated with the lane change event, including: generating the merging insertion point position information, and a virtual left lane change green light or a virtual right lane change green light, sending the merging insertion point position information, and the virtual left lane change green light or the virtual right lane change green light to the vehicle to be changed lanes, and sending the virtual slow down and yield sign to other vehicles on the target lane that are located behind the merging insertion point position information; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

[0050] In some embodiments, Figure 2 As shown, the first neural network model is trained according to the following method: Step S201: Acquire a first sample data set, where the first sample data set includes first sample path planning information corresponding to a sample vehicle and first sample traffic condition information ahead of the sample vehicle; Step S202: expanding the first sample data set, and randomly arranging and combining the first sample data in the expanded first sample data set to obtain multiple groups of first test cases; Step S203: inputting the plurality of groups of the first test cases into the first neural network model to be trained for iterative training to obtain a trained first neural network model.

[0051] In some embodiments, Figure 3 As shown, the second neural network model is trained according to the following method: Step S301: obtaining a second sample data set, wherein the second sample data set includes second sample traffic condition information, third sample traffic condition information, fourth sample traffic condition information, and sample driving trajectory information; Step S302: expanding the second sample data set, and randomly arranging and combining the second sample data in the expanded second sample data set and the first sample data in the expanded first sample data set to obtain multiple groups of second test cases; Step S303: inputting multiple groups of the second test cases into the second neural network model to be trained for iterative training to obtain a trained second neural network model.

[0052] 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 lane change command and control method based on virtual traffic signals as described in the first aspect of the present invention.

[0053] The computer-readable storage medium may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories.

[0054] The non-volatile memory can 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 memory, an optical disc, or a compact disc read-only memory (CD ROM); the magnetic surface memory can be a disk memory or a tape memory.

[0055] The volatile memory may be a random access memory (RAM), which 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), synchronous link dynamic random access memory (SLDRAM), direct memory bus 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.

[0056] like Figure 4 As shown, in a third aspect, the present invention provides an electronic device 10, comprising a processor 101 and a storage medium 102, wherein a computer program is stored on the storage medium, and when the computer program is executed by the processor, the vehicle lane change command and control method based on virtual traffic signals as described in the first aspect of the present invention is implemented.

[0057] In some embodiments, the processor can be implemented by software, hardware, firmware or a combination thereof, and can use circuits, single or multiple application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (Digital Signal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), central processing units (Central Processing Unit, CPU), controllers, microcontrollers, microprocessors and at least one thereof, so that the processor can execute some or all of the steps or any combination of the steps in the vehicle lane change command and control method based on virtual traffic signals described in the various embodiments of the present application.

[0058] In a fourth aspect, the present application provides a traffic management system based on virtual traffic signals, the system comprising: An electronic device, which is the electronic device as described in the third aspect of the present application; The vehicle-mounted device is communicatively connected with the electronic device and is used for receiving the virtual traffic signal.

[0059] like Figure 5 As shown, the electronic device involved in the present application may be built with a cloud computing unit, which has a virtual traffic signal system built on a physical traffic signal system. The function of the virtual traffic signal system is to generate corresponding virtual traffic signals according to the surrounding traffic situation of each vehicle road condition and publish them to the corresponding vehicles for traffic control. The virtual traffic signal is a virtualized electronic traffic signal dynamically generated by the computing unit according to the road traffic conditions and the driving intention of the networked vehicle, and is published to the relevant networked vehicles through the communication network.

[0060] 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 concept 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 lane change command and control method based on virtual traffic signals, characterized in that: The method comprises the following steps: Receive a lane change request and path planning information sent by a vehicle to be lane changed; The vehicle-road collaboration senses the first traffic condition information ahead of the vehicle to change lanes; Inputting road condition information ahead of the vehicle to be changed lanes and path planning information of the vehicle to be changed lanes into a first neural network model, and identifying a vehicle lane change reason corresponding to the vehicle to be changed lanes based on the first neural network model, wherein the vehicle lane change reason includes at least one of the following three types: overtaking, avoiding obstacles, or turning at a road intersection; The vehicle-road collaboration senses the second traffic condition information behind the vehicle to be changed, the third traffic condition information on the side, and the fourth traffic condition information on the target lane to be changed, and obtains the driving trajectory information of the vehicle to be changed; Inputting the second traffic condition information, the third traffic condition information, the fourth traffic condition information, the driving trajectory information and the path planning information into a second neural network model, so that the second neural network model outputs a control strategy in response to the lane change request; Generate a virtual traffic signal sequence based on the control strategy, wherein the virtual traffic signal sequence is a collection of virtual traffic signals, and the virtual traffic signals include virtual lane change lights or virtual traffic signs; The virtual traffic signal sequence is respectively issued to the vehicle to be changed lanes or other vehicles associated with the lane change event.

2. The vehicle lane change command and control method based on virtual traffic signals as claimed in claim 1, characterized in that: The virtual lane change signal light includes any one of the following: A virtual left lane change green light is used to indicate that the vehicle to be changed lanes is allowed to change left lanes; A virtual left lane change red light is used to indicate that the vehicle to be changed lanes is prohibited from changing lanes left; A virtual yellow left lane-changing light is used to serve as a warning during the lane-changing process of the vehicle to be changed. When the virtual yellow left lane-changing light flashes continuously, it is used to indicate that the vehicle to be changed needs to change lanes cautiously after observing and confirming safety; when the virtual green left lane-changing light turns into the virtual yellow left lane-changing light, it is used to indicate that the left lane-changing permission is about to end; A virtual right lane change green light is used to indicate that the vehicle to be changed lanes is allowed to change right lanes; A virtual right lane change red light is used to indicate that the vehicle to be changed lanes is prohibited from changing lanes right; A virtual yellow right lane change light is used to warn the vehicle to be changed lanes during the lane change process. When the virtual yellow right lane change light flashes continuously, it indicates that the vehicle to be changed lanes needs to change right carefully after observing and confirming safety. When the virtual right lane change green light turns into the virtual right lane change yellow light, it is used to indicate that the right lane change access is about to end; The virtual traffic sign includes: The virtual slow down and yield sign is used to instruct the vehicle to change lanes or other vehicles associated with the lane change event to slow down and yield.

3. The vehicle lane change command and control method based on virtual traffic signals as claimed in claim 2, characterized in that: The first neural network model identifies that the reason for the vehicle to change lanes is overtaking, and the control strategy includes allowing the vehicle to change lanes, prohibiting the vehicle to change lanes, or changing lanes cautiously; When the control strategy is to prohibit the vehicle to be changed from changing lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to be changed or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change red light or a virtual right lane change red light, and sending the virtual left lane change red light or the virtual right lane change red light to the vehicle to be changed; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to the vehicle traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

4. The vehicle lane change command and control method based on virtual traffic signals as claimed in claim 2, characterized in that: The first neural network model identifies that the reason for the vehicle to change lanes is to avoid an obstacle, and the control strategy includes allowing the vehicle to change lanes, merge in an orderly manner, or change lanes cautiously; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to other vehicles traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is orderly merging, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be changed or other vehicles associated with the lane change event, including: generating merging insertion point position information, and a virtual left lane change green light or a virtual right lane change green light, sending the merging insertion point position information and the virtual left lane change green light or the virtual right lane change green light to the vehicle to be changed, and sending the virtual slow down and yield sign to other vehicles on the target lane that are located behind the merging insertion point position information; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

5. The vehicle lane change command and control method based on virtual traffic signals as claimed in claim 2, characterized in that: The first neural network model identifies that the reason for the vehicle changing lanes is turning at a road intersection, and the control strategy includes allowing the vehicle to change lanes, illegally cut in line, merge in an orderly manner, or change lanes cautiously; When the control strategy is to allow the vehicle to change lanes, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to change lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change green light or a virtual right lane change green light, sending the virtual left lane change green light or the virtual right lane change green light to the vehicle to change lanes, and sending the virtual slow down and yield sign to other vehicles traveling on the target lane and located behind the vehicle to change lanes; When the control strategy is illegal queue jumping, generating a virtual traffic signal sequence based on the control strategy, and issuing the virtual traffic signal sequence to the vehicle to be changed lanes or other vehicles associated with the lane change event respectively includes: generating a virtual left lane change red light or a virtual right lane change red light, and sending the virtual left lane change red light or the virtual right lane change red light to the vehicle to be changed lanes; When the control strategy is orderly merging, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be changed or other vehicles associated with the lane change event, including: generating merging insertion point position information, and a virtual left lane change green light or a virtual right lane change green light, sending the merging insertion point position information and the virtual left lane change green light or the virtual right lane change green light to the vehicle to be changed, and sending the virtual slow down and yield sign to other vehicles on the target lane that are located behind the merging insertion point position information; When the control strategy is cautious lane change, a virtual traffic signal sequence is generated based on the control strategy, and the virtual traffic signal sequence is respectively issued to the vehicle to be lane changed or other vehicles associated with the lane change event, including: generating a virtual left lane change yellow light or a virtual right lane change yellow light, and sending the virtual left lane change yellow light or the virtual right lane change yellow light to the vehicle to be lane changed.

6. The vehicle lane change command and control method based on virtual traffic signals as claimed in claim 1, characterized in that: The first neural network model is trained according to the following method: Acquire a first sample data set, where the first sample data set includes first sample path planning information corresponding to the sample vehicle and first sample traffic condition information ahead of the sample vehicle; Performing data expansion on the first sample data set, and randomly arranging and combining the first sample data in the expanded first sample data set to obtain multiple groups of first test cases; Inputting multiple groups of the first test cases into the first neural network model to be trained for iterative training to obtain a trained first neural network model.

7. The vehicle lane change command and control method based on virtual traffic signals as claimed in claim 6, characterized in that: The second neural network model is trained according to the following method: Acquire a second sample data set, wherein the second sample data set includes second sample traffic condition information, third sample traffic condition information, fourth sample traffic condition information, and sample driving trajectory information; Performing data expansion on the second sample data set, and randomly arranging and combining the second sample data in the expanded second sample data set and the first sample data in the expanded first sample data set to obtain multiple groups of second test cases; Input multiple groups of the second test cases into the second neural network model to be trained for iterative training to obtain a trained second neural network model.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the vehicle lane change command and control method based on virtual traffic signals as described in any one of claims 1 to 7 is implemented.

9. An electronic device having a computer program stored thereon, characterized in that: It includes a processor and a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed by the processor, the vehicle lane change command and control method based on virtual traffic signals as described in any one of claims 1 to 7 is implemented.

Images