Automatic driving method based on broadcast communication and storage medium

Abstract

The invention relates to an automatic driving method based on broadcast communication and a storage medium, and the method comprises the steps: obtaining the vehicle situation information of a vehicle, and the information comprises the driving environment information; external vehicle situation information broadcasted by an external vehicle is received and analyzed, and external vehicle driving environment information and an external vehicle driving intention are obtained; generating a driving environment model based on the situation information data of all the external vehicles and the vehicle situation information of the vehicle so as to control the vehicle to automatically drive; according to the application, the technical problems that the sensing range is limited, the influence of shielding is large and the intention of other vehicles needs to be inferred by consuming a large amount of computing power due to the physical limitation of a single vehicle sensor in the prior art are solved, the environmental sensing beyond the sight distance is realized, and the driving intention of surrounding vehicles is directly and reliably acquired; and long-distance early warning of major danger information can be realized.

Description

[0001] This application claims priority to the Chinese patent application with the application number 2025114292840, the title of "Automatic driving system and method based on broadcast communication", which was filed on October 8, 2025, and the entire content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the field of automatic driving, and in particular, to an automatic driving method based on broadcast communication and a storage medium. BACKGROUND

[0003] With the deep integration of intelligent and networked technologies, automatic driving is becoming the core development direction of future transportation. Currently, the mainstream technical route to achieve automatic driving mainly relies on single-vehicle intelligent systems, that is, through multiple sensors (including cameras, radars, lidar, etc.) mounted on the vehicle itself to independently perceive and make decisions on the surrounding environment. However, this single-vehicle intelligent mode has two significant technical bottlenecks:

[0004] On the one hand, the environmental perception range is severely limited. The detection capability of single-vehicle sensors is limited by the range of sight, and cannot penetrate physical obstacles (such as large vehicles in front, buildings, curves, etc.), resulting in the vehicle being unable to timely perceive the traffic conditions in the blind area (such as accidents in front, road construction, etc.), posing a safety hazard.

[0005] On the other hand, the driving intention of other vehicles is unclear. Existing systems mainly analyze and predict the historical trajectory and behavior pattern of surrounding vehicles through algorithms to infer their future direction. This process requires a large amount of computing resources, and the prediction result has uncertainty, leading to a lag in the decision-making of the vehicle, making it difficult to achieve truly forward-looking planning.

[0006] In summary, the existing technical solutions cannot simultaneously solve the two interrelated problems of limited environmental perception range and unclear intention of other vehicles, resulting in serious deficiencies in the safety of decision-making and the cost of computing power for the automatic driving system.

[0007] Therefore, at present, there is no effective solution to the technical problems of low safety of automatic driving decision-making and high cost of computing power caused by the limited environmental perception range and unclear intention of other vehicles in the related technology. SUMMARY

[0008] The embodiments of the present application provide an automatic driving method and system based on broadcast communication to at least solve the problems of low safety of automatic driving decision-making and high cost of computing power caused by the limited environmental perception range and unclear intention of other vehicles in the related technology.

[0009] In a first aspect, the embodiments of the present application provide an automatic driving method based on broadcast communication.

[0010] In some embodiments, the vehicle situation information of the ego vehicle includes driving environment information of the ego vehicle;

[0011] receiving a vehicle situation information data packet broadcasted by at least one external vehicle; the vehicle situation information data packet is obtained by the external vehicle from vehicle situation information of the external vehicle; the vehicle situation information of the external vehicle includes driving environment information and driving intention of the external vehicle; the driving intention of the external vehicle is used to represent a future driving plan of the external vehicle; parsing the vehicle situation information data packet to obtain the driving environment information and the driving intention of the external vehicle;

[0012] generating a driving environment model based on the driving environment information and the driving intention of the external vehicle, and the vehicle situation information of the ego vehicle; and controlling the ego vehicle to perform an automatic driving operation based on the driving environment model.

[0013] In some embodiments, the vehicle situation information of the ego vehicle further includes position information of the ego vehicle; and the vehicle situation information of the external vehicle further includes position information of the external vehicle.

[0014] The generating of the driving environment model based on the driving environment information and the driving intention of the external vehicle, and the vehicle situation information of the ego vehicle includes:

[0015] performing coordinate transformation on the position information of the external vehicle based on the position information of the ego vehicle to generate a comprehensive map containing the position information of the external vehicle; and generating the driving environment model based on the driving environment information of the external vehicle and the driving environment information of the ego vehicle, and in combination with the comprehensive map.

[0016] In some embodiments, the generating of the driving environment model based on the driving environment information and the driving intention of the external vehicle, and the driving environment information of the ego vehicle, and in combination with the comprehensive map includes:

[0017] traversing each piece of driving environment information in a driving environment information set, and assigning a preset initial weight to each piece of driving environment information; the driving environment information set contains all the driving environment information of the external vehicle received by the ego vehicle and the driving environment information of the ego vehicle;

[0018] counting the number of the remaining driving environment information in the driving environment information set that points to the same event or object pointed to by the current driving environment information;

[0019] determine a first weight adjustment coefficient of the current driving environment information based on the number, and dynamically adjust a weight of the current driving environment information to a first target weight according to the first weight adjustment coefficient;

[0020] obtain the credibility of each piece of driving environment information according to the first target weight;

[0021] The remaining driving environment information refers to driving environment information in the driving environment information set except the current driving environment information; and the event or object includes but is not limited to an obstacle, road construction, a traffic accident, a traffic congestion state or a weather condition.

[0022] generate a driving environment model based on each piece of driving environment information in the driving environment information set, the corresponding credibility, the driving intention of the external vehicle and the driving environment information of the ego vehicle, and the comprehensive map.

[0023] In some embodiments, when the number is at least two, the obtaining the credibility of each piece of driving environment information according to the first target weight includes: calculating a relative distance between the remaining driving environment information and the occurrence position of the event or object based on the external vehicle position information and the occurrence position of the event or object.

[0024] determine a second weight adjustment coefficient of the current driving environment information according to the relative distance;

[0025] dynamically adjust the weight of the current driving environment information from the first target weight to a second target weight according to the second weight adjustment coefficient, and obtain the credibility of each piece of driving environment information according to the second target weight.

[0026] In some embodiments, the vehicle situation information data packet further includes a generation timestamp of the vehicle situation information.

[0027] The analyzing the external vehicle situation information data packet to obtain the driving environment information of the external vehicle and the driving intention of the external vehicle includes:

[0028] obtain a generation timestamp of the external vehicle situation information, calculate an information age of the external vehicle situation information based on a current time and the generation timestamp;

[0029] filter out the external vehicle situation information data packet with the information age within a preset valid time length as valid external vehicle situation information data packet, and obtain the driving environment information of the external vehicle and the driving intention of the external vehicle based on the valid external vehicle situation information data packet.

[0030] In some embodiments, the obtaining the vehicle situation information data packet broadcasted by the at least one external vehicle comprises:

[0031] The at least one external vehicle broadcasts the vehicle situation information data packet to the surrounding; the ego vehicle communicates with the at least one external vehicle and receives the vehicle situation information data packet broadcasted by the at least one external vehicle.

[0032] The at least one external vehicle re-obtains new vehicle situation information of the at least one external vehicle after a preset time interval, compresses the new vehicle situation information into a new vehicle situation information data packet, and broadcasts the new vehicle situation information data packet to the surrounding.

[0033] In some embodiments, the method further comprises:

[0034] When the external vehicle driving environment information satisfies a predefined special event condition, the external vehicle obtains current external vehicle situation information, compresses the current external vehicle situation information into a current external vehicle situation information data packet, and broadcasts the current external vehicle situation information data packet to the surrounding; wherein the special event comprises at least one of road construction, traffic congestion, and traffic accident.

[0035] In some embodiments, the external vehicle obtains current external vehicle situation information, compresses the current external vehicle situation information into a current external vehicle situation information data packet, and broadcasts the current external vehicle situation information data packet to the surrounding, comprising:

[0036] The external vehicle generates a unique event identifier of the special event, the unique event identifier being generated based on a time stamp and a location of occurrence of the special event; the external vehicle obtains a target transmission distance and a target message lifetime corresponding to the special event predefined;

[0037] The unique event identifier, the target transmission distance, and the target message lifetime are added to the vehicle situation information data packet to be broadcasted to generate a data packet containing the special event, and the external vehicle broadcasts the data packet containing the special event to the outside;

[0038] And / or, the analyzing the vehicle situation information data packet further comprises:

[0039] When the unique event identifier, the target transmission distance, and the target message lifetime are included in the vehicle situation information data packet, a duration of the special event and a relative distance between the ego vehicle and an event source are calculated.

[0040] If the special event has occurred for less than the target message lifetime, and the relative distance is less than the target transmission distance, the current vehicle situation information of the ego vehicle is acquired, and the unique event identifier, the target transmission distance and the target message lifetime are added to the current vehicle situation information, a data packet containing a special event is generated, and the data packet containing the special event is sent in a broadcast form.

[0041] In some embodiments, in a scenario where there is no traffic signal at the intersection, the automatic driving operation of the ego vehicle is controlled based on the driving environment model, including:

[0042] From the driving environment model, the driving intention and position information of all external vehicles in the intersection area are acquired.

[0043] Based on the preset traffic priority rule and in combination with the driving intention and position information of all external vehicles, the traffic order of the ego vehicle and each external vehicle is determined.

[0044] According to the traffic order, the speed and trajectory of the ego vehicle are controlled.

[0045] In a second aspect, the embodiments of the present application provide a storage medium having a computer program stored thereon, the program being executed by a processor to implement the automatic driving method based on broadcast communication according to the first aspect.

[0046] Compared with the related art, the automatic driving method based on broadcast communication provided by the embodiments of the present application solves the technical problems of limited perception range, great influence of occlusion and weather, and inability to accurately determine the intention of other vehicles due to the physical limitations of single-vehicle sensors and the consumption of a large amount of computing power to infer the intention of other vehicles in the prior art, by establishing a sharing mechanism of driving environment information and driving intention between vehicles based on broadcast, and realizes "over-the-horizon" environment perception beyond the physical limit of a single vehicle, direct and reliable acquisition of the driving intention of surrounding vehicles, and long-distance relay warning of major dangerous information, thereby significantly improving the environment perception robustness, decision accuracy, driving safety of the automatic driving system, and the overall traffic efficiency of the road.

[0047] Details of one or more embodiments of the present application are presented in the following drawings and description to make other features, objects and advantages of the present application more apparent. BRIEF DESCRIPTION OF DRAWINGS

[0048] The drawings described herein are intended to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0049] Figure 1is a schematic diagram of an automatic driving method based on broadcast communication according to an embodiment of the present application;

[0050] Figure 2 is a flow chart of an automatic driving method based on broadcast communication according to an embodiment of the present application;

[0051] Figure 3 is a schematic diagram of an automatic driving method based on broadcast communication according to an embodiment of the present application;

[0052] Figure 4 is a structural block diagram of an automatic driving system based on broadcast communication according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the objects, technical solutions and advantages of the present application clearer, the present application is described and explained below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application. In addition, it can be understood that, although the efforts made in this development process can be complex and lengthy, some changes in design, manufacture or production and the like based on the technical content disclosed in the present application are only routine technical means for those of ordinary skill in the art related to the content disclosed in the present application, and should not be understood as insufficient disclosure of the content disclosed in the present application.

[0054] In the present application, the phrase "embodiment" means that the specific features, structures or characteristics described in combination with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily mean the same embodiment, nor is it an independent or alternative embodiment to other embodiments. Those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0055] Unless otherwise defined, technical terms and scientific terms used in the present application shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. Unless otherwise defined, the terms "one" and "a" or "an" used in the present application shall not be limited to singular aspects but can include both singular and plural aspects. The terms "comprising," "including," "containing," and any variations thereof in the present application shall be taken to cover both cases where a process, method, system, product, or apparatus includes a stated step or element, and cases where a process, method, system, product, or apparatus consists essentially of a stated step or element. The terms "connected," "coupled," and "pathway" in the present application shall not be limited to direct physical or mechanical connections, but can include electrical connections, whether direct or indirect. The term "plurality" in the present application means two or more. The term "and / or" describes associative relationships of associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. The terms "first," "second," "third," and the like in the present application are merely to distinguish similar objects, and do not represent a specific order of the objects.

[0056] The method embodiments provided by the present embodiment can be executed in a terminal, a computer, or a similar computing device. Taking the case of running on a terminal, Figure 1 is a hardware structure block diagram of a terminal according to an automatic driving method based on broadcast communication. As shown in Figure 1 , the terminal can include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above terminal can also include a transmission device 106 for communication function and an input and output device 108. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above terminal. For example, the terminal can include more or fewer components than those shown in Figure 1 , or have a different configuration from that shown in Figure 1 .

[0057] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the automatic driving method based on broadcast communication in the embodiments of the present application. The processor 102 performs various functional applications and data processing, i.e., implements the above method, by running the computer program stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, which can be connected to the terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0058] The transmission device 106 is configured to transmit a vehicle situation information data packet of the vehicle by wireless broadcast, and receive a vehicle situation information data packet broadcast by an external vehicle. Specifically, the transmission device 106 is a radio frequency (RF) broadcast module working in a preset dedicated frequency band (for example, a 5.9 GHz intelligent transportation system frequency band). The module modulates the data packet generated by the vehicle into a wireless signal in a broadcast communication mode without a specific target address, and transmits the wireless signal to the surrounding space. At the same time, the module continuously monitors the same frequency band, receives and demodulates broadcast signals from other vehicles. In order to further ensure communication security, a specific encrypted message header can be set in the frame structure of the data packet to be broadcast. After capturing the signal, the receiving end needs to first decrypt and verify the encrypted message header, and only after the verification is passed, the subsequent valid information content can be parsed.

[0059] The embodiments of the present application provide an automatic driving method based on broadcast communication, Figure 2 is a flowchart of the automatic driving method based on broadcast communication according to the embodiments of the present application, as shown in Figure 2 The flowchart includes the following steps:

[0060] In step S201, vehicle situation information of the vehicle is acquired, and the vehicle situation information of the vehicle includes driving environment information of the vehicle.

[0061] The vehicle situation information of the vehicle refers to a comprehensive data set for comprehensively and dynamically describing the state of the vehicle itself, the driving environment and the future motion planning, which at least includes driving environment information, driving state information, position information, driving intention, time information, etc.

[0062] In detail, the driving environment information refers to external environmental elements perceived by the vehicle sensor module (such as a camera, radar, lidar, etc.), including but not limited to: detected various types of obstacles (such as vehicles, pedestrians, animals), road abnormal conditions (such as road construction, slippery road surface, traffic accident), real-time traffic conditions (such as traffic congestion), and weather conditions, etc.

[0063] The driving state information refers to data representing the current real-time motion state of the vehicle, including but not limited to: the instantaneous speed, acceleration (including deceleration), heading angle, turn signal on / off state, brake state, and gear state of the vehicle, etc.

[0064] The position information refers to the positioning of the vehicle in the absolute geographic coordinate system, usually provided by a geographic position module (such as a GPS / Beidou module), specifically represented as the latitude and longitude coordinates of the current map, and can be combined with an electronic map for more rich semantic expression. In specific applications, limited by the accuracy of the specific positioning module, this position information may have a meter-level error, and a high-precision positioning module (such as RTK or PPP enhanced positioning technology) can be used as the core positioning module in this scheme to provide centimeter-level or even millimeter-level accurate position data, thereby effectively reducing the error.

[0065] The driving intention refers to high-level information used to represent the driving planning or strategy of the vehicle in the short term future, which is the key to realizing cooperative driving between vehicles, and its purpose is to directly inform surrounding vehicles of the next action of the vehicle, thereby avoiding the other party from making complex and possibly erroneous predictions through algorithms. Driving intention includes but is not limited to: straight ahead, left turn, right turn, lane keeping, lane changing, overtaking, deceleration yielding, ordering intention in intersection traffic sequence, etc.

[0066] The time information refers to the timestamp when the vehicle situation information is generated, which is used to identify the "freshness" of the information and provides a reference for subsequent information age calculation and multi-vehicle information space-time alignment.

[0067] In addition, the vehicle situation information can also include vehicle identification information, which refers to an ID that can uniquely identify the vehicle, such as a vehicle frame number, used to track and distinguish information sources in a complex vehicle networking environment.

[0068] Specifically, the vehicle acquires the vehicle situation information of the vehicle through the sensor module (such as a camera, radar, lidar, etc.) mounted on the vehicle, which at least includes the driving environment information of the vehicle obtained through environmental perception.

[0069] Step S202, receiving at least one external vehicle broadcasting external vehicle situation information data packets; the external vehicle situation information data packets are obtained by the external vehicle acquiring and compressing the external vehicle situation information; the external vehicle situation information includes external vehicle driving environment information and external vehicle driving intention; the external vehicle driving intention is used to represent the future driving plan of the external vehicle; the external vehicle situation information data packets are parsed to obtain the external vehicle driving environment information and the external vehicle driving intention.

[0070] Among them, the external vehicle refers to other vehicles within the communication range of the communication module of the vehicle, which can send its own vehicle situation information (its content structure is the same as or compatible with the vehicle situation information obtained by the vehicle) through wireless broadcasting. The vehicle continuously monitors the preset frequency band through its own wireless signal receiving module, and can directly capture and parse these broadcast data packets without establishing any form of communication connection or networking with the external vehicle. In this communication mode, each vehicle with broadcasting function operates independently. For any vehicle, it is the "vehicle" that performs perception, decision and control, and other vehicles using its broadcast information as a data source are regarded as "external vehicles". Therefore, the roles of "vehicle" and "external vehicle" are functional and relative, and dynamically change with the movement of the vehicle, and together form a distributed information interaction environment based on self-broadcasting and independent receiving.

[0071] Specifically, at least one external vehicle broadcasts external vehicle situation information data packets, and the external vehicle situation information data packets are parsed to obtain external vehicle driving environment information and external vehicle driving intention. Further, inter-vehicle broadcast communication can be sent using the spectrum of a dedicated frequency band, for example, the 5.9GHz ITS frequency band in cellular vehicle networking communication can be used to ensure that communication will not be disturbed by other frequency bands.

[0072] Through the above step S202, the driving environment information and driving intention between vehicles are shared through inter-vehicle broadcast communication, the expansion of information perception range is realized, the "over-the-horizon" perception ability beyond the single vehicle perspective is achieved, and the real driving intention of the surrounding vehicles is directly obtained, solving the problems of limited perception range caused by visual blind area, physical limit of sensor and shielding, and difficulty in inferring the intention of other vehicles and large consumption of computing power, thereby laying a data foundation for building a global and accurate environment cognition model.

[0073] Step S203, generating a driving environment model based on the external vehicle driving environment information and the external vehicle driving intention, and the vehicle situation information of the vehicle; controlling the vehicle to perform automatic driving operation based on the driving environment model.

[0074] The driving environment model is characterized by a comprehensive and predictive environment representation for high-level autonomous driving decision-making, which not only includes static and dynamic object information, but also integrates the explicit driving intentions of surrounding vehicles. It should be noted that all or part of the received external vehicle information is processed, for example, the real-time computing power of the processor, the decision-making delay requirement or the information priority can be used to dynamically select the situation information of part of the external vehicle, and it is not necessary to process all received external vehicle situation information. Information screening can occur at different stages of receiving, analyzing or fusion decision-making. In particular, for special events such as geological disasters, traffic congestion, road construction, etc., which are given high priority information, the system can be forced to receive and process them first.

[0075] Specifically, based on the situation information data of the external vehicle, including the driving environment information and the driving intention of the external vehicle, a driving environment model for comprehensively understanding the current traffic situation and predicting its short-term evolution is generated at the host vehicle end, and based on the driving environment model, a safer, smoother and more efficient autonomous driving strategy is developed for the host vehicle to control the host vehicle to perform autonomous driving operations.

[0076] Through the above step S203, by combining the driving environment information of the external vehicle with the directly obtained driving intention, a leap from passive perception to active cooperation is achieved, so that the autonomous driving decision is no longer based on the limited observation and unreliable guess of itself, but on a nearly "panoramic view" global model containing the "thoughts" of other vehicles, thereby greatly improving the predictability and safety of the decision.

[0077] Through the above steps S201 to S203, by establishing a broadcast-based driving environment information sharing mechanism between vehicles, an environment perception beyond the physical limit of a single vehicle sensor is achieved, effectively expanding the perception range of the host vehicle and overcoming the problem of perception blind area caused by obstacles, weather and limited visibility; at the same time, by directly obtaining the driving intention of the external vehicle, the problem of consuming a large amount of computing resources and the uncertainty of the prediction result due to relying on complex algorithms to infer the intention of other vehicles in the prior art is solved, achieving the saving of computing resources and the improvement of decision-making real-time.

[0078] In some embodiments, the vehicle situation information of the host vehicle further includes host vehicle position information; the external vehicle situation further includes external vehicle position information; based on all external vehicle driving environment information and external vehicle driving intention, and the vehicle situation information of the host vehicle, a driving environment model is generated, including: taking the position information of the host vehicle as a reference, converting the position information of the external vehicle to generate a comprehensive map containing the position information of the external vehicle; based on all external vehicle driving environment information and external vehicle driving intention, and the driving environment information of the host vehicle, a driving environment model is generated in combination with the above comprehensive map.

[0079] wherein the coordinate transformation refers to the process of unifying location information from different sources into the same reference coordinate system. Since the location information sent by vehicles in the surrounding environment is based on their own positioning modules and electronic maps, there may be differences in map data versions and accuracy errors of positioning modules among different vehicles, leading to slight deviations in the description of the same geographical location.

[0080] Specifically, after receiving the location information (usually latitude and longitude coordinates) of the surrounding vehicles, the vehicle uses its own electronic map module and positioning data to establish a transformation relationship from the coordinate system of the surrounding vehicles to the map coordinate system of the vehicle. This process may include translation, rotation, and scaling of the coordinate system to ensure that the positions of all vehicles can be accurately and unambiguously mapped onto the map base used by the vehicle. Subsequently, the system accurately labels each piece of driving environment information (such as "accident ahead," "vehicle on the left," etc.) on the corresponding map location after transformation.

[0081] Through the above steps, by unifying and spatially aligning multi-source and heterogeneous location information, a comprehensive map centered on the vehicle's perspective and consistent in time and space is obtained. This realizes the accurate fusion and visualization of all driving environment information in the vehicle's coordinate system, integrates a discrete piece of information reported by multiple vehicles into a coherent and unified global environment view, thereby fundamentally eliminating information confusion or misjudgment caused by inconsistent coordinates, providing a reliable spatial foundation for generating high-precision fused environment information, and greatly improving the accuracy and safety of subsequent automatic driving decisions.

[0082] In some embodiments, based on all driving environment information and driving intentions of the surrounding vehicles, as well as the driving environment information of the vehicle, a driving environment model is generated in combination with the comprehensive map, including:

[0083] Iterate through each piece of driving environment information in the driving environment information set, and assign each piece of driving environment information an initial preset weight; the driving environment information set contains all driving environment information of the surrounding vehicles received by the vehicle and the driving environment information of the vehicle;

[0084] For the event or object pointed to by the current driving environment information, count the number of the remaining driving environment information in the driving environment information set that points to the same event or object;

[0085] Determine a first weight adjustment coefficient for the current driving environment information based on the number, and dynamically adjust the weight of the current driving environment information to a first target weight according to the first weight adjustment coefficient;

[0086] According to the first target weight, the credibility of each piece of driving environment information is obtained;

[0087] wherein the rest of driving environment information refers to driving environment information in the driving environment information set except the current driving environment information; the event or object includes but is not limited to: an obstacle, road construction, a traffic accident, a traffic congestion state or a weather condition;

[0088] Based on each piece of driving environment information in the driving environment information set, its corresponding credibility, the driving intention of the external vehicle, and the driving environment information of the ego vehicle, a driving environment model is generated in combination with the comprehensive map.

[0089] In the present scheme, the driving environment information of the external vehicle received by the ego vehicle and the driving environment information of the ego vehicle are cross-verified and credibility evaluated, and a quantitative credibility weight is given to each piece of driving environment information.

[0090] Specifically, each piece of driving environment information in the driving environment information set is traversed, and each piece of driving environment information is given a preset initial weight; the number of the rest of driving environment information in the driving environment information set pointing to the same event or object is counted for the event or object pointed to by the current driving environment information traversed; a first weight adjustment coefficient of the current driving environment information is determined based on the number, and the weight of the current driving environment information is dynamically adjusted to a first target weight according to the first weight adjustment coefficient; the credibility of each piece of driving environment information is derived according to the first target weight.

[0091] wherein the rest of driving environment information refers to driving environment information in the driving environment information set except the current driving environment information; the above-mentioned event or object includes but is not limited to: an obstacle, road construction, a traffic accident, a traffic congestion state or a weather condition.

[0092] It should be particularly noted that the cross-verification mechanism in the present scheme is based on positive and affirmative driving environment information. That is, only information that explicitly reports detection of an event or object is counted in the above-mentioned "number" and subjected to weight superposition. Information that does not detect the event (i.e. information missing), or negative information such as reporting "no obstacle", is not used as a basis for reducing the weight of other information in the cross-verification stage, but is regarded as a kind of "unconfirmed" default state. This design can effectively overcome the interference of the "missed detection" problem caused by sensor capability difference, temporary obstruction or perception range limitation on the overall judgment of the system.

[0093] In detail, the present application embodiment realizes the above-mentioned process by a quantitative algorithm based on the "consensus principle". The system sets an initial weight for each piece of driving environment information Subsequently, for the currently traversed driving environment information, the system checks whether there are N other (N≥0 and integer) pieces of affirmative information pointing to the same event or object in the driving environment information set, and determines the value of the first weight coefficient R based on the detection result. If each such confirming piece of information exists, the weight of the current information is multiplied by a reinforcement coefficient α greater than 1, i.e., R = Therefore, its first objective weight It can be represented as: If no other corroborating information exists (i.e., N=0), its weight is multiplied by a weakening coefficient β less than 1, i.e., R=β. The first target weight in this case... .

[0094] For example, on a straight highway with good visibility, this vehicle, along with vehicles A and B traveling ahead, all report the driving environment information that "road construction is underway 1 kilometer ahead." Assume initial weights... Strengthening coefficient Regarding the information reported by this vehicle, since there are two external corroborating pieces of information, vehicle A and vehicle B (N=2), its final first objective weight is calculated as follows: The weights of the information reported by vehicles A and B were also calculated in the same way, and both were increased. Therefore, the information about "road construction" was given a very high overall credibility. Conversely, if only vehicle C reported "debris in the left lane" and there was no other confirming information (N=0), a weakening coefficient was set. Then its first objective weight is calculated as If the credibility is judged to be low by the system, the fusion algorithm will not primarily rely on it for decision-making.

[0095] Through the above steps, by quantifying the mutual corroboration relationship between affirmative information into an exponential increase or punitive decay of weights, high confidence in the adoption of group-perceived events and automatic filtering of isolated abnormal information are achieved. Thus, the robustness and reliability of the environmental perception model are significantly improved without the need for a pre-set trust database.

[0096] Furthermore, when the number is at least two, the credibility of each piece of driving environment information is determined according to the first objective weight, including: based on the location information of external vehicles and the location of the event or object, calculating the relative distance between the external vehicles pointing to the same event or object and the location of the event or object;

[0097] The second weighting adjustment coefficient for the current driving environment information is determined based on the relative distance.

[0098] Based on the second weight adjustment coefficient, the weight of the current driving environment information is dynamically adjusted from the first target weight to the second target weight, and the credibility of each piece of driving environment information is obtained based on the second target weight.

[0099] Specifically, when the aforementioned quantity N≥2, this scheme introduces a distance factor to refine the weights. This process is based on the first target weights derived from the aforementioned "consensus principle". This is based on the calculation of the relative distance between each information source and the location where the event occurred. The weights are then adjusted a second time based on a distance decay function. In a preferred embodiment, the second weight coefficient... and relative distance Inversely proportional, for example (k is a constant). Therefore, the final weight of the second objective after distance correction... .

[0100] Figure 3 This is a schematic diagram of an autonomous driving method based on broadcast communication according to an embodiment of this application. The following is in conjunction with... Figure 3 Let me now introduce the details of this plan. Figure 3 The scenario depicts a sharp turn where an obstacle appears in front of vehicle 1, causing vehicles 2, 3, and 4 behind to brake and become congested. However, vehicles 5 and 6, which have not yet completed the turn, are unable to perceive the driving environment ahead due to the obstruction.

[0101] In this scenario, vehicles 1, 2, and 7 all clearly reported the affirmative information that "an obstacle exists ahead." First, based on the "consensus principle" in the above embodiment, the initial weights of the three vehicles are determined... All have increased from the initial value of 1.0 to 1.44. Although vehicles 3 and 4 did not perceive the obstacle, this "information deficiency" does not trigger the weighted penalty mechanism for the information of vehicles 1, 2, and 7. The system then calculates their relative distances to the obstacle, finding that vehicle 1 is 50 meters away, vehicle 2 is 150 meters away, and vehicle 7 is 200 meters away. Let... Their second weighting coefficients are as follows: , , After distance correction, the weights of their respective second targets are: , , .

[0102] Therefore, the second target weight of the driving environment information reported by the first vehicle is significantly enhanced by the second weight factor, which is much higher than that of other vehicles. This enables the fifth vehicle behind to give priority to the environment information provided by the first vehicle with the closest distance and the most direct view when fusing information, so as to accurately perceive the obstacles and congestion on the other side of the curve. The system ultimately generates an accurate driving environment model based on the positive evidence chain formed by those high-weighted and mutually corroborative positive information (vehicles 1, 2, and 7, especially vehicle 1), and the "silence" or "undetected" state of vehicles 3 and 4 is not enough to overturn the evidence chain.

[0103] Through the above steps, by introducing a weight refinement correction mechanism based on relative distance on the basis of quantity consensus, and always adhering to the principle of accepting positive information chain, the system can intelligently give priority to the information source with better observation angle and potentially higher reliability when fusing information, so as to generate a driving environment model with higher precision and greater decision value in complex scenes such as blind area and curve.

[0104] Through the above scheme, by introducing a multi-source information cross-validation and dynamic credibility evaluation mechanism, the authenticity / credibility of the driving environment information is verified, effectively overcoming the problems of false positives, false negatives or insufficient accuracy that may exist in a single information source, thereby solving the robustness problem of environment perception and improving the accuracy and reliability of the finally fused environment information.

[0105] In some embodiments, the vehicle situation information data packet further includes a generation timestamp of the vehicle situation information; the external vehicle situation information data packet is parsed to obtain the external vehicle driving environment information and the external vehicle driving intention, including:

[0106] The generation timestamp of the external vehicle situation information is obtained, and based on the current time and the generation timestamp, the information age of the external vehicle situation information is calculated;

[0107] The external vehicle situation information data packet with an information age within a preset valid time length is screened out as valid external vehicle situation information data packet, and based on the valid external vehicle situation information data packet, the external vehicle driving environment information and the external vehicle driving intention are obtained.

[0108] The information age refers to the length of time experienced from information generation to the current time, which is a key indicator for measuring the freshness of information. The preset valid time length is a time threshold set according to the dynamic characteristics of specific driving scenes (such as urban roads and highways), which is used to judge whether the information still has reference value.

[0109] Specifically, when parsing any one of the external vehicle data packets, the host vehicle first extracts the generation timestamp carried therein and compares it with the current time of the host vehicle's system to calculate the information age of the information. Subsequently, the system compares the information age with the preset valid duration. Only the data packets with an information age less than or equal to the valid duration are determined to be "valid" and enter the subsequent information fusion and decision-making process; those "expired" data packets with an information age exceeding the valid duration are directly discarded or ignored by the system.

[0110] Through the above steps, by introducing the information age mechanism and performing timeliness screening, it is ensured that the system always relies on the freshest and most relevant driving environment information at the current moment for fusion and decision-making. This effectively solves the problem of decision-making errors that may be caused by "outdated" information due to communication delay or vehicle movement, thereby greatly improving the real-time performance and accuracy of the automatic driving system in understanding the dynamic traffic environment, while reducing unnecessary computational load of the system in processing outdated data.

[0111] In some embodiments, obtaining the external vehicle situation information data packet broadcast by at least one external vehicle comprises:

[0112] At least one external vehicle broadcasts the external vehicle situation information data packet to the surroundings; the host vehicle communicates with the external vehicle and receives the external vehicle situation information data packet broadcast by the external vehicle;

[0113] After the preset time interval, the external vehicle re-obtains new vehicle situation information of the external vehicle, compresses the new vehicle situation information into a new vehicle situation information data packet, and broadcasts the new vehicle situation information data packet to the surroundings.

[0114] The preset time interval is a periodic update period set according to the dynamic change characteristics of the driving environment. The broadcast form of the external vehicle means that the information is not intended for a specific recipient, but is published to all nodes within the communication coverage, which constitutes a decentralized communication foundation.

[0115] Specifically, from the perspective of the host vehicle, it continuously monitors the communication channel, and the received external vehicle data packets exhibit periodic update characteristics. This indicates that the external vehicle, as an active information source, continuously and periodically broadcasts its latest vehicle situation information. For example, the external vehicle may collect and broadcast its latest environmental perception, position, speed, and driving intention information several times every 100 milliseconds or every second, thereby forming a continuous information flow.

[0116] It can be understood that in the technical solutions provided in the present application, the definition of "the vehicle" and "the external vehicle" is relative and functional, rather than absolute and structural. In the entire network composed of a large number of vehicles with broadcasting communication capability, any vehicle is in the role of "the vehicle" when it performs the method of the present application (i.e. obtaining its own information, broadcasting, receiving information of other vehicles, and fusing decision). For other vehicles receiving its broadcast information, the vehicle is regarded as "the external vehicle". This role is instantaneous and dynamically changing. The entire system relies on all participants to periodically switch between the roles of "information sender" and "information receiver", forming a peer-to-peer, distributed perception and communication network. Therefore, for any networked vehicle that implements the above functions of the present application, it can be "the vehicle" and "the external vehicle" in the eyes of other vehicles during its operation. The essence of this design is to jointly build a global driving environment cognition beyond the perception limit of a single vehicle through peer-to-peer information sharing and collaboration between vehicles.

[0117] Through the above steps, by relying on the periodic broadcasting mechanism of the external vehicle, the vehicle can continuously and low-delay obtain the latest dynamic information of the surrounding vehicles. This provides a stable and reliable data source for realizing real-time and dynamic driving environment fusion and modeling, ensures the timeliness and continuity of the vehicle's understanding of the environment, and thus provides important data support for high-level automatic driving decisions.

[0118] In some embodiments, the above method further comprises: when the external vehicle driving environment information meets a predefined special event condition, the external vehicle obtains the current external vehicle situation information, compresses the current external vehicle situation information into a current external vehicle situation information data packet, and sends it to the surrounding in a broadcast form; wherein the special event includes at least one of road construction, traffic congestion, and traffic accident.

[0119] The above predefined special event condition refers to those driving environment conditions that have a significant impact on traffic safety and efficiency, and need to be informed in a timely and extensive manner. Such events usually have the characteristics of suddenness, high risk and strong timeliness.

[0120] Specifically, when the sensor module of any vehicle (at this time as a potential external vehicle) detects a predefined special event such as road construction, traffic congestion, or traffic accident, the system of the vehicle will immediately trigger an event-driven emergency broadcasting process. The vehicle will immediately collect the latest vehicle situation information containing the details of the special event, package it into a data packet marked with a special event identifier, and broadcast it externally with the highest priority. From the perspective of the vehicle, it will receive such a data packet with an emergency mark and containing a significant risk prompt.

[0121] Through the above steps, by establishing an instant broadcast mechanism based on special event triggering, low-delay and high-priority propagation of major dangerous road condition information is realized. This enables rear vehicles to learn about the key risks in front of them in near real time without waiting for the next regular broadcast period, gaining valuable warning time for emergency braking, path re-planning and other risk avoidance operations, thereby effectively improving road traffic safety and the overall emergency response capability of the transportation system.

[0122] In some embodiments, the external vehicle obtains current external vehicle situation information, compresses the current external vehicle situation information into a current external vehicle situation information data packet, and sends it to the surrounding in the form of broadcast, including: the external vehicle generates a unique event identifier of a special event, the unique event identifier being generated based on the occurrence timestamp and occurrence location of the special event; the external vehicle obtains the target transmission distance and target message lifetime corresponding to the predefined special event;

[0123] The unique event identifier, target transmission distance and target message lifetime are added to the external vehicle situation information data packet to be broadcast to generate a data packet containing the special event, and the external vehicle sends the data packet containing the special event to the outside in the form of broadcast;

[0124] And / or, the parsing of the external vehicle situation information data packet further includes:

[0125] When the unique event identifier, target transmission distance and target message lifetime are parsed from the external vehicle situation information, the occurred duration of the special event and the relative distance between the vehicle and the event source are calculated;

[0126] If the occurred duration of the special event is less than the target message lifetime, and the relative distance is less than the target transmission distance, the current vehicle situation information of the vehicle is obtained, and the unique event identifier, target transmission distance and target message lifetime are added to the current vehicle situation information to generate a data packet containing the special event, and the data packet containing the special event is sent to the outside in the form of broadcast.

[0127] The unique event identifier is used to uniquely identify a specific special event in the global information space, preventing vehicles from repeatedly recording and forwarding the same event; the target transmission distance defines the geographical range that the event information needs to be propagated; and the target message lifetime specifies the maximum duration that the event information is valid on the network.

[0128] Specifically, the present scheme designs a controlled multi-hop forwarding mechanism. When the vehicle receives a data packet containing special event information, it will execute the following logic: First, parse the unique event identifier, target transmission distance (d_target) and target message lifetime (t_life) in it. Then, calculate the distance between the vehicle and the event occurrence location (d_current), and the time difference from the event occurrence timestamp to the current time, i.e. the time of occurrence (t_age). Then, the judgment is made: if t_age < t_life and d_current < d_target, it means that the event information is neither expired nor has reached the boundary where it should be propagated. At this time, the vehicle will act as a "relay node" and integrate the received complete event information (including unique identifier, target distance and lifetime) into its own data packet to be broadcast, and continue to send it out. This process will continue until the information is transmitted to the target distance boundary or exceeds its lifetime.

[0129] For example, consider a scenario of a road collapse. Vehicle A in front first detects the collapse, and its system determines based on preset rules that such an event needs to be transmitted 2 kilometers (d_target=2000m) and the lifetime is 10 minutes (t_life=600s). A vehicle generates a unique event ID and broadcasts it together with d_target and t_life. Suppose the direct communication range of A vehicle's broadcast is 500 meters. Vehicle B 400 meters behind A receives the message, calculates its distance to the collapse as about 400 meters (d_current=400m), which is much smaller than 2000 meters, and the information is just issued (t_age is almost 0), which is less than 10 minutes. Therefore, B vehicle integrates the event information into its own data packet and forwards it. Similarly, C vehicle 400 meters behind B can also receive this information. Through this relay method, the warning information about the road collapse can break through the distance limit of direct communication between vehicles and be quickly transmitted to all vehicles within a 2-kilometer range, rather than being limited to a 500-meter area around A vehicle.

[0130] Through the above steps, by introducing a controlled multi-hop forwarding mechanism and using the three key parameters of unique event identifier, target transmission distance and message lifetime to accurately manage the forwarding process, the present scheme successfully solves the inherent problem of limited communication distance of single vehicle broadcast. This enables special event information that has a significant impact on traffic safety to be reliably and efficiently transmitted in the vehicle network like a relay race, providing valuable warning time for vehicles in a larger area, thereby greatly avoiding secondary accidents and relieving traffic congestion, significantly improving road safety and traffic efficiency.

[0131] In some embodiments, in a scenario where there is no traffic light at the intersection, based on the driving environment model, the host vehicle is controlled to perform automatic driving operations, including: obtaining driving intentions and position information of all external vehicles in the intersection area from the driving environment model; determining the passing order of the host vehicle and each external vehicle based on a preset passing priority rule and in combination with the driving intentions and position information of all external vehicles; and controlling the speed and trajectory of the host vehicle according to the passing order.

[0132] The passing priority rule is a set of predefined logical criteria for resolving right-of-way conflicts without a central dispatcher, which can be based on traffic laws, road structures (such as main roads and branch roads), and real-time traffic conditions.

[0133] Specifically, when the host vehicle approaches the intersection without a traffic light, it can clearly grasp the accurate positions of all vehicles participating in the intersection interaction (including the host vehicle) and their declared driving intentions (such as straight, left turn, right turn) in the driving environment model by continuously receiving and analyzing the broadcast information of surrounding vehicles. The system then inputs this information into the passing priority rule engine for distributed negotiation calculation. This calculation not only considers the static right-of-way of vehicles (such as priority of vehicles on main roads), but also dynamically combines the real-time positions and intentions of each vehicle (such as distance from the intersection entrance, whether there is a path conflict, etc.), to calculate a passing sequence that maximizes traffic efficiency and safety.

[0134] For example, in a typical intersection scenario, vehicles A, B, C, and D approach the intersection from four directions, and the traffic light is malfunctioning. Each vehicle is broadcasting its driving intention (A vehicle straight, B vehicle left turn, C vehicle right turn, D vehicle straight). Based on the received information, each vehicle runs the same collaborative decision-making algorithm. The algorithm may quickly negotiate an optimal passing order according to the rules (such as yielding to vehicles on the right and turning to yield to straight vehicles) and in combination with real-time positions, for example, "A vehicle straight goes first --> B vehicle left turn --> C vehicle right turn --> D vehicle straight". After the negotiation is completed, the automatic driving systems of each vehicle will automatically control their speed and trajectory according to this consensus order: A vehicle maintains speed through; B, C, and D vehicles perform corresponding deceleration at the intersection entrance, and after the previous vehicle passes, they start and complete their intended actions in turn. The entire process does not require vehicles to completely stop, achieving smooth, efficient, and safe collaborative passing.

[0135] Through the above steps, by combining the explicit vehicle driving intention with the preset traffic rules for distributed collaborative decision-making, the automatic and optimized determination of the passing order between vehicles in the no-signal intersection scenario is realized. This replaces the high-power and high-uncertainty mode of intention prediction in the traditional automatic driving system relying on complex game theory, so that vehicles can pass efficiently and safely based on the clear shared information, thereby greatly improving the passing efficiency of the intersection and completely eliminating the risk of traffic jam or accident caused by unclear intention.

[0136] It should be noted that the steps shown in the above flow or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0137] The embodiment also provides an automatic driving system based on broadcast communication, which is used to realize the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the terms "module", "unit", "sub-unit" and the like can be a combination of software and / or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably realized in software, hardware or a combination of software and hardware is also possible and is conceived.

[0138] Figure 4 is a structural block diagram of an automatic driving system based on broadcast communication according to the embodiment of the application, as shown in the figure, the system comprises: a vehicle situation information acquisition module 10, used to acquire vehicle situation information of the vehicle, the vehicle situation information of the vehicle comprising driving environment information of the vehicle;

[0139] A data processing module 20 is configured to receive a vehicle situation information data packet broadcast by at least one external vehicle; the vehicle situation information data packet is obtained by the external vehicle by acquiring and compressing the vehicle situation information of the external vehicle; the vehicle situation information of the external vehicle comprises external vehicle driving environment information and external vehicle driving intention of the external vehicle; the external vehicle driving intention is used to represent the future driving plan of the external vehicle; the vehicle situation information data packet is analyzed to obtain the external vehicle driving environment information and the external vehicle driving intention;

[0140] A decision control module 30 is configured to generate a driving environment model based on all external vehicle driving environment information and external vehicle driving intention, and vehicle situation information of the vehicle; and control the vehicle to perform automatic driving operation based on the driving environment model.

[0141] It should be noted that the above various modules can be functional modules or program modules, which can be implemented by software or hardware. For the modules implemented by hardware, the above various modules can be located in the same processor; or the above various modules can also be located in different processors in any combination. The specific examples in the embodiment can refer to the examples described in the above embodiments and optional implementation manners, which will not be described herein.

[0142] The embodiment also provides a vehicle comprising the automatic driving system based on broadcast communication.

[0143] The embodiment also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform the steps in any of the method embodiments.

[0144] Optionally, the electronic device can further comprise a transmission device and an input / output device, wherein the transmission device is connected with the processor, and the input / output device is connected with the processor.

[0145] Optionally, in the embodiment, the processor can be configured to execute the following steps through the computer program:

[0146] S1, obtaining vehicle situation information of the vehicle, wherein the vehicle situation information of the vehicle comprises driving environment information of the vehicle.

[0147] S2, receiving a vehicle situation information data packet broadcast by at least one external vehicle; the vehicle situation information data packet is obtained and compressed by the external vehicle; the vehicle situation information comprises driving environment information and driving intention of the external vehicle; the driving intention of the external vehicle is used to represent the future driving plan of the external vehicle; analyzing the vehicle situation information data packet to obtain the driving environment information and the driving intention of the external vehicle.

[0148] S3, generating a driving environment model based on all the driving environment information and the driving intention of the external vehicle, and the vehicle situation information of the vehicle; and controlling the vehicle to perform an automatic driving operation based on the driving environment model.

[0149] It should be noted that the specific examples in the embodiment can refer to the examples described in the above embodiments and optional implementation manners, which will not be described herein.

[0150] In addition, in combination with the automatic driving method based on broadcast communication in the above embodiments, an application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; the computer program is executed by a processor to implement any one of the automatic driving methods based on broadcast communication in the above embodiments.

[0151] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0152] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., but is not limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0153] Those skilled in the art should understand that each technical feature of the above-described embodiments can be combined arbitrarily, and for the sake of brevity, each technical feature of the above-described embodiments is not described in all possible combinations, however, as long as the combinations of the technical features do not exist, it should be considered that it is within the scope of the description.

[0154] The above-described embodiments only express several implementation manners of the present application, the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. An automatic driving method based on broadcast communication, characterized by, The method comprises the following steps: acquiring vehicle situation information of the host vehicle, the vehicle situation information of the host vehicle comprising driving environment information of the host vehicle; receiving a vehicle situation information data packet broadcast by at least one external vehicle, the vehicle situation information data packet being obtained by the external vehicle from vehicle situation information and being compressed, the vehicle situation information comprising driving environment information and driving intention of the external vehicle; the driving intention of the external vehicle being used to represent a future driving plan of the external vehicle; analyzing the vehicle situation information data packet to obtain the driving environment information and the driving intention of the external vehicle; generating a driving environment model based on the driving environment information and the driving intention of the external vehicle and the vehicle situation information of the host vehicle; controlling the host vehicle to perform an automatic driving operation based on the driving environment model. 2.The broadcast communication-based automatic driving method of claim 1, wherein, The vehicle situation information of the host vehicle further comprises position information of the host vehicle; The vehicle situation information of the external vehicle further comprises position information of the external vehicle; The method of generating a driving environment model based on the driving environment information and the driving intention of the external vehicle and the vehicle situation information of the host vehicle comprises: performing coordinate conversion on the position information of the external vehicle based on the position information of the host vehicle to generate a comprehensive map comprising the position information of the external vehicle; and generating a driving environment model based on the driving environment information and the driving intention of the external vehicle, the driving environment information of the host vehicle and the comprehensive map. 3.The broadcast communication-based automatic driving method of claim 2, wherein, The method of generating a driving environment model based on the driving environment information and the driving intention of the external vehicle and the driving environment information of the host vehicle and the comprehensive map comprises: traversing each piece of driving environment information in a driving environment information set and assigning a preset initial weight to each piece of driving environment information, the driving environment information set comprising all the driving environment information of the external vehicle received by the host vehicle and the driving environment information of the host vehicle; counting the number of the remaining driving environment information in the driving environment information set that points to the same event or object pointed to by the current driving environment information; determining a first weight adjustment coefficient of the current driving environment information based on the number and dynamically adjusting the weight of the current driving environment information to a first target weight according to the first weight adjustment coefficient; obtaining the credibility of each piece of driving environment information according to the first target weight; wherein the remaining driving environment information refers to the driving environment information in the driving environment information set other than the current driving environment information; and the event or object comprises but is not limited to an obstacle, road construction, a traffic accident, a traffic congestion state or a weather condition; generating a driving environment model based on each piece of driving environment information in the driving environment information set and the corresponding credibility, the driving intention of the external vehicle and the driving environment information of the host vehicle and the comprehensive map. 4.The broadcast communication-based automatic driving method of claim 3, wherein, In the case where the number is at least two, the method of obtaining the credibility of each piece of driving environment information according to the first target weight comprises: Based on the position information of the external vehicle and the occurrence position of the event or object, the remaining driving environment information is calculated to point to the external vehicle of the same event or object, and the relative distance from the occurrence position of the event or object is calculated. According to the relative distance, a second weight adjustment coefficient of the current driving environment information is determined. According to the second weight adjustment coefficient, the weight of the current driving environment information is dynamically adjusted from the first target weight to a second target weight, and according to the second target weight, the credibility of each piece of driving environment information is obtained. 5.The broadcast communication-based automatic driving method of claim 1, wherein, The vehicle situation information data packet also includes a generation timestamp of the vehicle situation information; The analysis of the external vehicle situation information data packet includes: The generation timestamp of the external vehicle situation information is obtained, and based on the current time and the generation timestamp, the information age of the external vehicle situation information is calculated. The information age of the external vehicle situation information data packet within the preset effective time length is filtered out as the effective external vehicle situation information data packet, and based on the effective external vehicle situation information data packet, the external vehicle driving environment information and the external vehicle driving intention are obtained. 6.The broadcast communication-based automatic driving method of claim 1, wherein, The method further includes: The at least one external vehicle broadcasts the external vehicle situation information data packet to the surrounding; the host vehicle communicates with the external vehicle and receives the external vehicle situation information data packet broadcasted by the external vehicle; The external vehicle reacquires the new vehicle situation information of the external vehicle after a preset time interval, and compresses the new vehicle situation information into a new vehicle situation information data packet, and broadcasts it to the surrounding. 7.The broadcast communication-based automatic driving method of claim 6, wherein, The method further includes: When the external vehicle driving environment information meets the pre-defined special event condition, the external vehicle acquires the current external vehicle situation information, compresses the current external vehicle situation information into a current external vehicle situation information data packet, and broadcasts it to the surrounding; wherein the special event includes at least one of road construction, traffic congestion, and traffic accident. 8.The broadcast communication-based automatic driving method of claim 7, wherein, The external vehicle acquires the current external vehicle situation information, compresses the current external vehicle situation information into a current external vehicle situation information data packet, and broadcasts it to the surrounding, including: The external vehicle generates a unique event identifier of the special event, and the unique event identifier is generated based on the occurrence timestamp and occurrence position of the special event; the external vehicle acquires the target transmission distance and target message lifetime corresponding to the pre-defined special event; The unique event identifier, target transmission distance and target message lifetime are added to the external vehicle situation information data packet to be broadcasted to generate a data packet containing the special event, and the external vehicle broadcasts the data packet containing the special event to the outside; And / or, the analysis of the external vehicle situation information data packet further includes: When it is parsed that the unique event identifier, the target transmission distance and the target message lifetime are contained in the external vehicle situation information, a duration of the special event and a relative distance between the ego vehicle and an event source are calculated; If the duration of the special event is less than the target message lifetime and the relative distance is less than the target transmission distance, current vehicle situation information of the ego vehicle is acquired, the unique event identifier, the target transmission distance and the target message lifetime are added to the current vehicle situation information, a data packet containing the special event is generated, and the data packet containing the special event is sent in a broadcast form. 9.The broadcast communication-based automatic driving method of claim 1, wherein, In a scenario where there is no traffic signal at the intersection, the ego vehicle is controlled to perform automatic driving operation based on the driving environment model, including: From the driving environment model, driving intentions and position information of all external vehicles in the intersection area are acquired; Based on a preset passing priority rule and in combination with the driving intentions and position information of all the external vehicles, a passing order of the ego vehicle and each external vehicle is determined; According to the passing order, the speed and the driving trajectory of the ego vehicle are controlled.

10. A storage medium, characterized by The storage medium has a computer program stored therein, wherein the computer program is configured to execute the automatic driving method based on broadcast communication according to any one of claims 1 to 9 when running.

Images