An autonomous driving method based on multi-object synchronous control

Abstract

The present invention relates to an autonomous driving method based on multi-object synchronous control, which senses and detects all driving devices and the external environment within the driving area, combines with the route requirements, calculates the optimal next action within the driving area in combination with the real-time state of each driving device, realizes indirect trusted interaction between all objects and events within the same driving area, and when any element within the driving area changes, the corresponding object related to it obtains a new optimal next action, thereby realizing autonomous driving with a high safety value within the driving area. The present invention gets rid of single-vehicle recognition and electronic maps, and based on the global perception of the driving area, eliminates blind spots. For each driving device, there are no longer objects that suddenly appear; after all objects enter the driving area, they are immediately discovered and their next actions are known. Other driving devices affected by them no longer need to perform active recognition, and only need to perform operations according to the optimal next action.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and more specifically, to an autonomous driving method based on multi-object synchronous control. Background Art

[0002] The so-called autonomous driving generally combines a set route and environment recognition (including road information recognition, road condition recognition, etc.) to automatically travel from a starting point to a destination. During the travel, the road conditions are judged and an automatic reaction is made, so as to achieve "autonomous driving". In the prior art, whether for conventional cars or car-like vehicles for specific purposes (usually various automatic walking devices with various functions or shapes), the control is actively carried out on the vehicle itself starting from the vehicle itself, and then autonomous driving is completed.

[0003] Regarding environment recognition in the prior art, whether using a vision solution or a radar solution, the objects within the vehicle's own perception range are recognized, and then the next action is determined. Furthermore, due to factors such as different solutions, differences in software and hardware technologies, and differences in configurations (the quantity and quality of software and hardware vary among different vehicle models and different configuration models of the same vehicle model), there are significant performance differences in the recognition capabilities of different vehicles themselves. As a result, the so-called "autonomous driving" levels achieved by different vehicles are uneven. The "autonomous driving" achieved by the prior art not only has poor practical effects, but also causes the dilemma of being unable to formulate more explicit traffic regulations for autonomous driving technology, which in turn restricts the development of autonomous driving.

[0004] On the other hand, since the vehicle recognizes the objects within its own perception range to determine the next action, and there are obvious limit boundaries in the recognition level and mechanical performance of "autonomous driving", including "visual" blind spots (such as occlusion of image acquisition and radar signals), recognition range (especially close-range recognition), braking distance, etc. Beyond the limit, especially in sudden situations, such as "ghost probes", adjacent vehicle accelerating and merging, and a vehicle approaching rapidly from behind, due to mechanical performance limitations and the inability of vehicles to directly or indirectly interact with each other, no associated judgment or pre-judgment can be made. Therefore, if driving is completely handed over to "autonomous driving", it will undoubtedly increase the occurrence of accidents, and this is also the case in reality. Moreover, when "autonomous driving" vehicles and non-"autonomous driving" vehicles are mixed, based on the technical idea of the vehicle's own environment recognition and determination of the next action, it still cannot be called "autonomous driving" at present, and can only be used as one of the means of assisted driving. If the driver chooses to take over the vehicle with "autonomous driving", it will instead increase the driver's mental burden when ensuring safety.

[0005] Another component of "autopilot" in the prior art, namely the set route, highly relies on electronic maps. If there are significant errors or information mistakes in the electronic maps compared with the actual road conditions, including situations such as accident congestion, traffic control, and road construction, even if it can combine environmental recognition and automatically change the route according to the existing navigation technology. However, the lagging environmental recognition seriously affects the convenience of use. Meanwhile, to achieve the autopilot of a vehicle according to the set route also highly depends on the environmental recognition ability, especially intersection recognition (although some existing technologies also provide satellite positioning solutions, but the reliability is relatively low and it cannot achieve acceptable application effects). Currently, based on the technical idea of combining the set route with environmental recognition, the best level in the industry can only achieve autopilot on expressways, that is, roads with limited favorable conditions such as closed roads, simple road conditions, small errors in electronic maps, and clear markings.

[0006] In terms of social security, the in-vehicle host of "autopilot" in the prior art is a single-point computing device, which is easily hijacked and controlled, causing potential safety hazards. Moreover, the high-precision detection of the environment by the radar and camera on the "autopilot" device in the prior art, the data is related to public safety and national security. Autopilot enterprises are not sufficient to ensure the security of such data, which is likely to cause serious confidentiality breaches and affect public safety or national security.

[0007] In summary, the "autopilot" in the prior art highly depends on the single-vehicle recognition of the vehicle itself and electronic maps. However, due to the easy emergence of blind spots in the "field of vision" of a single vehicle and the inability to conduct safe and reliable interactions between vehicles, the electronic maps basically cannot be 100% consistent with the real situation. Consequently, misjudgments are likely to occur, resulting in inconvenient use and even accidents in severe cases. Summary of the Invention

[0008] The object of the present invention is to overcome the deficiencies of the prior art and provide an autopilot method based on multi-object synchronous control, which no longer adopts the mode of combining single-vehicle recognition and electronic maps. Vehicles achieve multi-object synchronous control through indirect interactions, and real-time infer the optimal next action of the driving device to achieve the autopilot of the driving device.

[0009] The technical solution of the present invention is as follows:

[0010] An autonomous driving method based on multi-object synchronous control, which obtains the route requirements of driving devices in the driving area, the performance parameters, speed information, position information of each control component of the driving devices, and the external environment data of the external environment in the driving area except the driving devices; based on the real-time position information, speed information, route requirements, performance parameters of each control component and external environment data of all driving devices, calculates the optimal next action for each driving device in real time, and each driving device performs automatic control based on the corresponding optimal next action to achieve autonomous driving.

[0011] Preferably, the environmental factors corresponding to the external environment data include but are not limited to weather, obstacles, pedestrians, public events, public opinion, travel arrangements of citizens, rickshaws, special service requirements, parking space conditions, and logistics requirements.

[0012] Preferably, based on the route requirements, calculate the driving route of the driving device. For a certain driving device, combine the performance parameters, speed information, and position information of each control component, and according to the preset safety criteria, based on the driving speed and / or driving position of other driving devices and the optimal next action of each control component of other driving devices currently calculated, calculate the optimal next action of each control component of this driving device.

[0013] Preferably, through sensors of the corresponding type deployed in the driving area and covering the driving area, obtain the performance parameters, speed information, and position information of each control component of all driving devices in the driving area, obtain the route requirements of all driving devices in the driving area through the human-computer interaction device associated with the driving device, and through the computing system, calculate the optimal next action of each control component of each driving device in real time.

[0014] Preferably, the computing system is a peer-to-peer network, which uses the peer-to-peer network to perform non-specific feature recognition and position recognition on targets, and the targets include driving devices and other fixed or moving objects except driving devices;

[0015] The peer-to-peer network includes multiple node devices, and there is no primary-secondary relationship among all node devices; the node devices are provided with data acquisition devices and operation modules. The data acquisition devices include at least one type of sensor for collecting different corresponding types of perception data; the node devices set at different acquisition positions collect at least one point sample of the target, and the point sample is the perception data of the corresponding sensor type.

[0016] For a certain node device, the sensed data collected is processed to obtain result data, and the result data is propagated to other node devices; for other node devices that receive the result data, the result data is used as one of the original data collected, and the result data of other node devices is affected by the result data; based on this, without the need to obtain the identity information of the target, multiple node devices in the peer-to-peer network perform collaborative computing to determine each unique target as itself, realizing non-specific feature recognition, and position recognition of the driving device and other fixed or moving objects other than the driving device.

[0017] Preferably, the current node device receives the result data output by other node devices; for the current node device, the sensed data collected is combined with the result data from other node devices to calculate the result data of the current node device, and is sent to other node devices; the node devices in the peer-to-peer network perform collaborative computing as the sensed data is collected and the result data is calculated.

[0018] Preferably, in the peer-to-peer network, for a certain point sample of a certain target, among the result data transmitted from the node device that collects the point sample to other node devices, the subsequent node devices adjust the sensing attention according to the characteristics of the point sample, or report the characteristics of the point sample for the subsequent node devices to adjust the sensing attention; if the subsequent other node devices do not detect the characteristics of the point sample, but it can be determined from the characteristics of other point samples that the characteristics of the undetected point sample still belong to the target, then the characteristics of the undetected point sample are still expressed in the result data of the current node device and transmitted to other node devices.

[0019] Preferably, the method of reporting the characteristics of the point sample for the subsequent node devices to adjust the sensing attention is: for the result data expressing the characteristics of the point sample provided by the previous node device, or the characteristics of the point sample adjust the parameters of the data processing model of the subsequent node device, so that the subsequent node device improves the computing power for identifying the characteristics of the point sample; or, the subsequent node device uses the sensing attention model to match the characteristics of the received point sample or the result data expressing the characteristics of the point sample for computing power adjustment.

[0020] Preferably, when the node device processes the result data output by several previous node devices, based on the data processing model, when the targets described by several previous node devices can be determined to be the same target through some common point sample characteristics, the point sample characteristics and other information described by each node device are merged into the same target.

[0021] Preferably, when the result data received by the node device indicates that, before the current node device receives the result data this time, the flag used to identify the target is different from the flag used by other node devices to identify the same target, and the flag assigned by other node devices to the target is updated, then the flag used by the current node device to identify the target before receiving the result data this time is converted.

[0022] Preferably, the method for converting the flag used by the current node device to identify the target before receiving the result data this time is as follows:

[0023] Replace the flag used by the current node device to identify the target before receiving the result data this time with the latest flag assigned by other node devices to the target;

[0024] Alternatively, record the conversion relationship between the flag used by the current node device to identify the target before receiving the result data this time and the updated flag assigned by other node devices to the target, and perform the conversion when the result data received by the current node device this time needs to be referenced.

[0025] Alternatively, the node device deploys a conversion model and performs corresponding conversions on the flags of multiple targets according to the input raw data or result data.

[0026] Preferably, for one or more point samples successively collected by node devices at different collection positions, if the characteristic values of a certain one or more point samples at different collection positions respectively meet the preset similar conditions or are determined by a specific model to have a correlation reaching the threshold and are unique at each collection position, then it is determined that the point samples of this type at different collection positions have a correlation.

[0027] Preferably, for one or more point samples simultaneously collected by node devices at different collection positions, if the node devices at different collection positions collect the same spatial field, when there is only a single target in the spatial field, or the collected point samples can correctly point to one of the multiple targets to which they belong, then for a certain target, the one or more point samples collected by the node devices at different collection positions have a correlation.

[0028] Preferably, the data acquisition device of the node device includes one or several combinations of an image acquisition device, an electromagnetic induction device, a temperature measurement device, a vibration frequency sensing device, and a lidar. The data collected by the above devices and the three-dimensional point cloud collected by the lidar or the point cloud generated from the images collected by multiple image acquisition devices are jointly calculated to obtain three-dimensional points with data. The image color, contour, line, reflectivity, motion trend, electromagnetic characteristics, temperature, temperature change trend, vibration frequency, and vibration frequency change trend based on two-dimensional perception are used as additional attributes of the corresponding three-dimensional points to form a three-dimensional point cloud with attributes. Combining the electromagnetic induction, temperature law, change characteristics of vibration frequency, motion correlation, and reflectivity, the corresponding relationship between each region of the three-dimensional point cloud with attributes and each part or associated part of the 3D appearance of the consumer is determined.

[0029] Preferably, when the identity information of the target needs to be obtained, an identity information acquisition command is triggered, and the identity information acquisition command is used as one of the inputs to participate in the calculation of the result data of the node device. By driving the node device in the peer-to-peer network that is connected with the barrier-free data acquisition conditions capable of obtaining the identity information of the target to respond to the corresponding result data, the identity information of the target is obtained.

[0030] Preferably, the peer-to-peer network verifies the authenticity of the identity information of the target and then determines its permissions. Among them, the node devices in the peer-to-peer network that can obtain identity information do not provide identity information, but only express the verification result in the result data of the node device according to the verification requirement of the authenticity of the identity information in the received result data.

[0031] Preferably, the node devices in the peer-to-peer network that can obtain identity information do not provide identity information, but drive the information source device that provides identity information to establish an encrypted file transfer channel or an encrypted information transfer channel in other network communication modes between the input terminal of the node device that needs to obtain identity information. The identity information is used as one of the inputs of the node device.

[0032] Preferably, the data acquisition device includes one or more of an image acquisition device, an audio acquisition device, a temperature measurement device, a vibration frequency sensing device, a lidar, a chemical sensor, and an electromagnetic induction device.

[0033] Preferably, the human-machine interaction device associated with the driving device is connected to the node device as an access device and submits a route requirement to the peer-to-peer network; each control component or a combination of multiple control components forming the same function joins the peer-to-peer network through one or more node devices; if it is determined based on collaborative computing that a certain control component or a combination of multiple control components of the driving device needs to be automatically controlled based on the corresponding optimal next action, the current node device will send an instruction to the control component connected to the current node device according to the calculated result data to control the control component to complete the control action.

[0034] Preferably, the optimal next action is characterized into result data; the control component receives the result data output by the connected node device. If a specific element in the result data indicates that the control component needs to be automatically controlled, or if the result data is one of the inputs of the data processing model of the node device and it is calculated and determined that the corresponding control component needs to be automatically controlled, the control component performs the corresponding control action.

[0035] Preferably, when automatic control of the control component is required, the control component combines the result data output by other node devices, calculates its own result data, and controls the control component on the control component to perform the corresponding control action through the obtained result data.

[0036] Preferably, for the driving device, the result data calculated by its control component includes the optimal solution of all situations obtained by collaborative computing of all driving devices in the driving area and the external environment at the current moment; the optimal next action of the driving device is reflected by the control component on the control component performing the control action corresponding to the optimal solution.

[0037] Preferably, the control component receives the result data output by other node devices. The principle is that when the request command requires automatic control of the corresponding control component, if the result data calculated by one or more node devices can determine the control component that needs to be automatically controlled, the corresponding control component will be added to the node list that transmits the current result data, and the one or more node devices directly transmit the result data to the control component or the node device connected to the control component; or, the control component receives the result data output by other node devices in a layer-by-layer transmission manner.

[0038] Preferably, according to the preset conditions or algorithm outputs, model outputs, the corresponding control components are added to the node list for transmitting the result data.

[0039] Preferably, the control component is a node device connected to an execution component with a specific function, and the execution feedback information of the control component of the control component is fed back to the control component and participates in the calculation of the subsequent result data of the control component.

[0040] Preferably, the control component of the driving device is used as a node device and joins the peer-to-peer network; if it is determined based on collaborative computing that the control component is abnormal, the abnormal data is used as one of the inputs to participate in the calculation of the result data, and a processing solution is obtained through collaborative computing.

[0041] Preferably, each driving device sets a safety mechanism in read-only storage mode. If all the node devices connected to the control component are damaged and it is found based on collaborative computing that a corresponding safety accident will occur to the driving device, the safety mechanism of the driving device is activated, and other control components are taken over according to the mechanism preset in read-only storage to control the driving device to decelerate or stop; if some braking components fail, other braking components adjust the braking force to keep the driving device in a stable posture until it stops.

[0042] Preferably, the control components of the driving device include, but are not limited to, a driving component, a braking component for each tire, a steering component, a throttle control component, an energy component, a lighting device, a door lock, a door closing induction device, a wiper module, and a wiper fluid spraying device.

[0043] The beneficial effects of the present invention are as follows:

[0044] The automatic driving method based on multi-object synchronous control described in the present invention senses and detects all driving devices and the external environment in the driving area, combines with the route requirements, calculates the optimal next action in the driving area in combination with the real-time state of each driving device, realizes indirect trusted interaction between all objects (including all moving or fixed objects such as driving devices) and events in the same driving area. When any element in the driving area changes, the corresponding objects related to it obtain new optimal next actions, and then realize high-safety automatic driving in the driving area. The present invention gets rid of the single-vehicle recognition of the vehicle itself and the electronic map, and based on the global perception of the driving area, eliminates blind spots. For each driving device, there are no suddenly emerging objects; after all objects enter the driving area, they are immediately discovered and included in the comprehensive calculation to realize identification and positioning, know their next actions, and other driving devices affected by them no longer need to perform active recognition, but only need to be controlled according to the optimal next action obtained by calculation.

[0045] The present invention is also applicable to the scenario where "automatic driving" and non-"automatic driving" vehicles travel together. Although the driving devices that are not "automatic driving" cannot be controlled, based on their identification and positioning, they are regarded as uncontrollable external environment data, which does not affect other "automatic driving" driving devices to perform automatic driving based on the present invention.

[0046] The present invention no longer relies too much on electronic maps. After an event in the driving area is detected, the event is incorporated into comprehensive calculations, and then the new optimal next action can be calculated. Through the perception of the driving device, (compared with actively identifying intersections), the driving device is reversely guided to drive along the calculated route. In the present invention, the driving device is in a passive state. After being detected, it is controlled to drive in the correct direction, thus being completely different from the prior art and getting rid of the limitations of single-vehicle identification and electronic maps.

[0047] When the present invention is implemented, when only driving devices with "automatic driving" are allowed to enter the driving area, the motor vehicle traffic lights can be cancelled, and only the pedestrian and rickshaw traffic lights are retained, reducing the facility cost and management cost.

[0048] The present invention uses a peer-to-peer network for collaborative calculations to perform non-specific feature recognition and position recognition on all targets in the driving area to complete identity recognition and positioning. In the peer-to-peer network, there is no primary or secondary relationship among all node devices, there is no fixed connection path between node devices, and node devices only receive the calculation results of other node devices and send out the result data of their own calculations. The discovery of events and / or the response to the corresponding control components do not rely on a single node device for recognition and control, but are jointly confirmed through collaborative calculations by multiple node devices in the peer-to-peer network. Furthermore, the present invention does not rely on the driving device for single-vehicle identification (i.e., single-point identification), distributes the computing function throughout the network, reduces the software and hardware requirements for single-point operations, has high execution efficiency, and greatly improves the anti-attack ability. There is a relatively symmetric information state among node devices, which can immunize against the problem of illegal data tampering. Even if a single node device is physically cracked and its sent data is tampered with, because the network-wide operation is a super-highly redundant complex calculation and a super-multi-dimensional verification, the data sent by a single node device being tampered with does not affect the network-wide calculation result, and the faulty and tampered node device can be quickly located, ensuring the credibility of the network-wide calculation result. Furthermore, the contradiction between data sharing and information security among departments can be solved.

[0049] The present invention can determine each unique target as itself without the need for specific features and obtaining specific identity information, realizing non-specific feature recognition. The present invention performs target recognition, identity confirmation or event monitoring through non-specific feature recognition, not only with a high accuracy rate of recognition results, but also with precise position recognition. The present invention can perform target recognition and identity confirmation without relying on specific features, protecting privacy, and at the same time can also solve problems such as transportation, education, medical convenience, epidemic prevention, people's livelihood services, emergency, public security, anti-terrorism, community management and services, market behavior, work safety, and civilized behavior.

[0050] The present invention adopts non-specific feature recognition. On the one hand, it can effectively prevent the risks caused by theft or imitation of specific features, greatly enhancing security. The present invention adopts a non-contact passive method to perform non-intrusive recognition of the identity of the target, greatly enhancing the convenience of execution. Based on the described peer-to-peer network, the present invention can be easily deployed with a coverage range at the level of hundreds of meters or hundreds of kilometers, suitable for various geographical ranges.

[0051] In the present invention, the control of the driving device is actually reflected by the manipulation actions of the manipulation component. The computing system does not directly perform stand-alone control on the driving device; the manipulation actions of the manipulation component are corresponding manipulation actions based on the calculation results obtained by collaborative computing, with high response efficiency, avoiding illegal responses such as false execution or non-execution when it should be executed caused by network attacks. To avoid hijacking, the present invention can also use multiple node devices to cooperate in controlling the manipulation component, further improving the immunity to hijacking attacks. Detailed implementation manner

[0052] The present invention will be further described in detail below in conjunction with embodiments.

[0053] In order to solve the deficiencies of the existing technology of autonomous driving based on single-vehicle recognition and electronic maps, such as many recognition blind spots, no interaction between targets, and easy errors in electronic maps, which comprehensively result in the current situation that autonomous driving is still at a relatively low level, the present invention provides an autonomous driving method based on multi-object synchronous control, getting rid of the limitations of single-vehicle recognition and electronic maps, and realizing passive guidance of the driving device through comprehensive calculation of all targets in the driving area, thereby improving safety and effectiveness. It can be applied to automobiles and other automatically controlled devices and intelligent devices with specific uses, such as controllable walking devices.

[0054] The automatic driving method based on multi-object synchronous control according to the present invention takes all driving devices or multiple driving devices that have relevance at a certain stage (the driving devices with relevance are different in different stages, and thus the driving devices with relevance are dynamically adjusted, and the relevance means that there is an influence between each other) as objects, performs synchronous control, and realizes the cooperation between multiple objects through different actions between different objects, adjusts each object to the optimal position, and ensures the safety of the traveling process. Specifically, obtain the route requirements of the driving devices in the driving area, the performance parameters of each control component of the driving devices, the speed information of the driving devices, the position information of the driving devices, and the external environment data other than the driving devices in the driving area (in the present invention, the environmental factors corresponding to the external environment data include but are not limited to weather, obstacles, pedestrians, public events, public opinion, the travel arrangements of citizens, rickshaws, special service requirements, parking space conditions, and logistics requirements); based on the real-time position information, speed information, route requirements, performance parameters of each control component, and external environment data of all driving devices, calculate in real time the optimal next action for each control component of each driving device, and each control component of each driving device performs automatic control based on the corresponding optimal next action to realize automatic driving. The present invention uses the past state and current state of all targets in the driving area to deduce the optimal next state, and correspondingly realizes the optimal next action of each control component of the driving device. For driving devices with relevance, the current optimal next actions of different targets may directly affect the current optimal next action of a certain driving device or may affect a certain future optimal next action of a certain driving device according to the specific relevance, specific targets, positions, etc. In the present invention, the influence between targets with relevance can be either at that time or an indirect influence formed in the future by accumulating and influencing a third target (one or more other targets other than the two targets forming the influence). Based on this, in the driving area, the present invention obtains the optimal next actions of all driving devices at any moment by comprehensively considering all targets.

[0055] In the present invention, based on route requirements (including locations to pass through, sequence, time, desired roads to travel on, etc.), the driving route of a driving device is calculated. For a certain driving device, in combination with the performance parameters, speed information, and position information of each control component, according to a preset safety criterion, based on the driving speed and / or driving position of other driving devices and the optimal next action of each control component of other driving devices calculated currently, the optimal next action of each control component of this driving device is calculated. Similarly, it can be used to make early adjustments to other driving devices. Furthermore, through the self-adjustment of the driving device, early adjustments to all driving devices are achieved. That is, the present invention considers other driving devices that may affect the current driving device in the past, present, or future, and in combination with the current driving device, according to the calculation results, early adjustments can be made to the current driving device. For example, if according to the current conditions, the current driving device will be caught up by another driving device at a certain moment in the future at the current speed, and this other driving device will block the lane change of the current driving device; then, all targets can be controlled in a variety of different ways, including changing the speed of the current driving device, adjusting the lane of the current driving device, changing the speed of this other driving device, adjusting the lane of this other driving device, controlling the driving situation of the current driving device or this other driving device through traffic lights, etc., as long as the safety criterion is met, to avoid this other driving device from blocking the current driving device and ensure the safety of all objects at the same time.

[0056] In order to get rid of the influence of satellite positioning or electronic maps, the present invention obtains the performance parameters, speed information, and position information of each control component of all driving devices in the driving area through sensors of the corresponding type deployed in and covering the driving area, so as to collect the state of the driving device at the set position; and obtains the route requirements of all driving devices in the driving area through a human-machine interaction device associated with the driving device, and through a calculation system, calculates the optimal next action of each control component for each driving device in real time.

[0057] In specific implementation, the traditional single-point recognition method can be adopted to identify the identity of the traveling device and other objects moving within the traveling area (including other moving targets except the traveling device with "automatic driving") at the set position, so as to achieve the purpose of identity confirmation and associated position information; or the identity recognition of non-specific features can be carried out by using the collaborative computing based on the peer-to-peer network provided by the present invention. The peer-to-peer network of the present invention is based on collaborative computing, does not rely on single-point recognition, distributes the computing function throughout the whole network, reduces the software and hardware requirements for single-point computing, has high execution efficiency, and greatly improves the anti-attack ability; the information between node devices is relatively symmetric, and the problem of illegal data tampering can be immunized. Even if a single node device is physically cracked and the data it sends is tampered with, because the whole network computing is a super-highly redundant complex calculation and a super-multi-dimensional verification, the data sent by a single node device being tampered with does not affect the whole network computing result, and the faulty and tampered node device can be quickly located, ensuring the credibility of the whole network computing result. Furthermore, the contradiction between data sharing and information security among departments can be solved.

[0058] The result data transmitted between node devices can be the processing result of information, rather than the information itself. Furthermore, the original data collected (i.e., perception data) does not need to be stored. The node device only receives the computing results output by other node devices and sends out its own computing results. The amount of information contained in a single computing result is not enough to restore any event and target information. It is necessary to jointly perform collaborative computing by the computing results on the whole peer-to-peer network, the multi-dimensional data matrix elements and the corresponding relationship between the physical space and facilities to obtain a definite result. The collaborative computing has less dependence on the information transmitted by a small number of node devices, and thus can fundamentally change the nature of the traditional information-based single-point security sensitivity.

[0059] In the present invention, the acquisition of identity information and location information of a driving device and other fixed or moving objects other than the driving device can be obtained through collaborative computing by the peer-to-peer network provided by the present invention. Specifically, the computing system is a peer-to-peer network, and the peer-to-peer network is used to perform non-specific feature recognition and location recognition on the target, where the target includes a driving device and other fixed or moving objects other than the driving device. The "non-specific feature recognition" is, in a strict conceptual definition, different from the "recognition" in the general sense. The "recognition" in the general sense means determining the concrete image or specific identity information of the target, such as who exactly (including name, specific information indicating the identity of the target), what it is (such as a car, a person, etc.). However, the "recognition" in the "non-specific feature recognition" of the present invention means determining each unique target (i.e., a driving device and other fixed or moving objects other than the driving device) as itself; that is, for a certain object to be recognized, its existence is unique. After the present invention realizes "non-specific feature recognition", it is determined that the object to be recognized (i.e., the target that has not been recognized or had its identity confirmed) is itself, rather than other objects to be recognized. The result of "non-specific feature recognition" does not need to determine the specific features of the object to be recognized, nor does it need to determine the identity information or concrete image of the object to be recognized. For example, for a person regarded as the object A to be confirmed and an object regarded as the object B to be confirmed, after realizing "non-specific feature recognition", it is not necessary to recognize that the object A to be confirmed is a person and who the specific identity is, nor to recognize that the object B to be confirmed is an object and what specific item it is; instead, it is necessary to determine that the object A to be confirmed is the object A itself and the object B to be confirmed is the object B itself. Then, corresponding services or controls can be carried out for the object A to be confirmed or the object B to be confirmed.

[0060] A peer-to-peer network includes multiple node devices. There is no primary or secondary relationship among all node devices, forming a decentralized network and computing framework. Different from the traditional information-based single-point convergence computing mode, there is no fixed or preset path relationship for the direction of data transfer between the node devices of the present invention. In the peer-to-peer network of the present invention, for a certain node device, the original data collected is processed to obtain result data, and the result data is propagated to other node devices; other node devices that receive the result data use the result data as one of the original data collected, and the result data affects the result data of other node devices through the result data. For the convenience of description, the aforementioned "certain node device" is hereinafter referred to as the "current node device", and the "other node devices" are hereinafter referred to as the "subsequent node devices". Then one of the effects is that the result data calculated by the subsequent node devices is not completely determined by the original data collected by itself, but is jointly determined by the result data output by the current node device; among them, the result data output by the current node device may change the data processing model and parameters, etc. used by the subsequent node devices to calculate the result data, thereby affecting the result data of the subsequent node devices. For example, if there is a correlation between the result data output by the current node device and the original data collected by the subsequent node device, it is necessary to consider the impact of the result data output by the current node device on the accuracy of the result data of the subsequent node device; specifically, for the perception of a certain specific target, if the result data calculated only based on the original data collected by the subsequent node device can only reflect the real-time (including real-time location and time) single-point result judgment of the target within the perception range of the subsequent node device; while the result data output by the current node device reflects the direct perception data and result judgment of the target at other locations and other times, or other perception data and result judgment that are indirectly related, which helps to improve the accuracy and comprehensiveness of the result data of the subsequent node device, including the superposition calculation of the same dimension and the correlation reference of different dimensions.

[0061] Since there is no master-slave relationship between node devices in a peer-to-peer network, point-to-point transmission can be carried out between node devices. Furthermore, for the calculation result corresponding to a certain sensed data of a certain target reflected in the result data output by a certain node device, the information is relatively symmetric among other node devices that receive the result data; other node devices use the received result data as input, combine it with the sensed data of their own sensors, calculate their own result data, and their own result data naturally covers the received result data and the information reflected by their own sensors, and transmits it to other node devices in the next layer. Furthermore, for a certain sensed data of a certain target, the information is in a relatively symmetric state among all node devices, which can immunize the impact on the result data caused by the tampering and forgery of the calculation process and calculation result of a single node device, and at the same time become a means to discover faulty or tampered node devices and node devices with non-compliant performance, fundamentally solving the fundamental hidden danger of traditional information technology, that is, due to information asymmetry, false information, forged information, and wrong information are caused, and then become the entry points for fraud and cyber attacks, with poor accuracy, long time consumption, poor credibility, and poor adaptability in complex comprehensive applications. Furthermore, it can truly become the information infrastructure for large-area comprehensive management and the infrastructure of the digital economy. The present invention is different from the blockchain technology that still adopts the technical solution of each node independently calculating and determining the result and paying attention to the preservation of original data. The present invention focuses on the peer-to-peer collaborative calculation between node devices. Through peer-to-peer collaborative calculation, when each node device processes data, it can adjust its own data processing model (i.e., the algorithm of the calculation result data) and parameters. The adjustment is the feedback of all node devices on their own adjustments, so that the calculations of all node devices become a whole. Each node device no longer independently completes the calculation, but all node devices jointly complete the calculation. After the data processing model of the node device is adjusted, it is an objective adjustment and will affect the next data processing.

[0062] The node device is provided with a data acquisition device (in specific implementation, it may include one or more of an image acquisition device, an audio acquisition device, a temperature measurement device, a vibration frequency sensing device, a lidar, a chemical sensor, and an electromagnetic induction device), and an operation module. The data acquisition device includes at least one type of sensor for acquiring different corresponding types of sensed data. The operation module calculates and obtains result data based on the data processing model. Node devices set at different acquisition positions (i.e., located at different physical installation positions) acquire at least one point sample of the target, and the point sample is the sensed data corresponding to the sensor type. Based on this, without the need to obtain the identity information of the target, multiple node devices in the peer-to-peer network perform collaborative calculations to determine each unique target as its own, realizing non-specific feature recognition; and realizing position recognition of driving devices and other fixed or moving objects except driving devices.

[0063] Specifically, taking a certain node device as the current node device, combining the data transmission of its previous node device and subsequent node device (the previous node device and subsequent node device in the present invention are only used to describe the front and back relationships with the current node device during the current calculation and data transmission process, and do not indicate an inevitable front and back relationship and priority relationship between them). Correspondingly, the current node device receives the result data output by other node devices (including the previous node device), and the subsequent node device receives the result data output by other node devices (including the current node device). For the current node device, the collected sensing data is combined with the result data from other node devices (including the previous node device), and the result data of the current node device is calculated and sent to other node devices (including the subsequent node device). Similarly, the working process of the subsequent node device is the same as that of the current node device, and the previous node device also receives the result data of the previous node device of the previous node device and performs the same working process as the current node device; that is, the node devices in the peer-to-peer network perform the same working process. Furthermore, the node devices in the peer-to-peer network perform collaborative calculations as the sensing data is collected and the result data is calculated. Among them, for the result data output by a certain node device, it is only received by the subsequent layer of node devices and used as input, and the result data of the subsequent layer of node devices will cover the result data of the previous layer of node devices (including the aforementioned certain node device).

[0064] In the peer-to-peer network, all events are processed synchronously, and it is not necessarily required to explicitly generate phased result outputs such as what event has been discovered and what the specific content of the event is; in the peer-to-peer network, the only things that are clear are the sensing of the sensors and the response of the corresponding execution devices, and other intermediate processes are all processed simultaneously through collaborative calculations, that is, during the operation process of the present invention, the intermediate process of discovering events is imperceptible, and as the collaborative calculation progresses and the result data of the node devices is obtained, the corresponding execution devices automatically respond and execute.

[0065] To ensure the further credibility of the data source and the calculation process, in the present invention, all node devices encrypt the result data calculated by them based on an encryption consensus mechanism to obtain an encrypted result, and then send the encrypted result to other node devices. The encryption consensus mechanism includes one or more consensus mechanisms, and different consensus mechanisms correspond to changing the encryption algorithm structure and parameters of the node devices.

[0066] Node devices communicate with each other using standard-sized data packets (i.e., result data or calculation results). In the present invention, the node devices of the peer-to-peer network are similar to human neurons. Each neuron does not transmit specific data that directly describes external events. Similarly, the node devices do not output raw data, but process the raw data obtained by the connected sensors and data acquisition devices into standard-sized data packets (i.e., result data or calculation results, similar to the nerve impulses of neurons) according to their own data processing models (similar to the biological characteristics of nerve cells). The amount of information contained in a single data packet is not enough to restore any event and target information. The calculation results, multi-dimensional data matrix elements, and physical space and facility correspondences on the entire peer-to-peer network must be jointly calculated in a collaborative manner to obtain a definite result. The collaborative calculation is not very dependent on the data output by a few node devices, and the collaborative calculation simultaneously processes the needs received or initiated by all node devices. It is a collaborative verification calculation of super-multi-dimensional related information, which can fundamentally change the nature of traditional information technology that is sensitive to single-point security.

[0067] In order to ensure the integrity of data and the effective execution of collaborative computing, in the present invention, the peer-to-peer network deploys a QoS mechanism, and the QoS mechanism is to give priority to ensuring the transmission quality of the result data between node devices.

[0068] In specific implementation, the networking mode of the peer-to-peer network is one or a combination of 4G mode, 5G mode or MESH mode, so as to adapt to different application scenarios, comprehensively implement feasibility, cost considerations and other factors, and achieve the best solution. Among them, the MESH mode is based on the LTE standard, and communicates at the physical layer of the LTE standard; a customized frame structure is used to carry data, and a dedicated wireless communication protocol is used for interaction. The frame structure is customized to be suitable for peer-to-peer network computing, and a proprietary wireless communication protocol developed for urban agglomeration peer-to-peer network computing is used to further improve its security and reliability. In addition, the wireless algorithm fully adapts to the multipath channel environment based on consensus mechanism control required for peer-to-peer network computing. The communication distance in the city is 100 meters to 10 kilometers, and the omnidirectional antenna can also achieve efficient transmission of 120 kilometers in the field. In this embodiment, the communication distance of the Mesh network is: the distance between node devices indoors is 50-150 meters, the distance between node devices outdoors is 50 meters to 120 kilometers, and the number of node devices that can be accessed by each node is 65535. In addition, when networking in 4G mode or 5G mode, there is no limit on the communication distance, and the number of accessible node devices depends on the computing power of the computing chip and the communication delay.

[0069] In a peer-to-peer network, for a certain type of point sample of a to-be-identified object, in the result data transmitted from the node device that collects the point sample to other node devices, it enables subsequent node devices to adjust their perceptual attention according to the characteristics of the point sample (it is not necessarily required to include the characteristics of the point sample in the result data, but the characteristics of the point sample participate in the calculation of the previous node device, so that when the result data of the previous node device is used as the input of the data processing model of the subsequent node device, the data processing model of the subsequent node device can achieve the effect of adjusting perceptual attention in the calculation); or, report the characteristics of the point sample for subsequent node devices to adjust their perceptual attention (directly state the characteristics of the point sample in the result data). If other subsequent node devices do not detect the characteristics of the point sample, but it can be determined from the characteristics of other point samples that the undetected characteristics of the point sample still belong to the to-be-identified object, then continue to state the characteristics of the undetected point sample in the result data of the current node device and transmit it to other node devices. For example, the previous node device senses the color on the to-be-identified object A. When the current node device does not sense the color on the to-be-identified object A, but it can be determined from the perceptual data of other node devices that in addition to other to-be-identified objects, there is also the to-be-identified object A, then continue to state the still undetected color on the to-be-identified object A in the result data of the current node device.

[0070] In this embodiment, the method of reporting the characteristics of the point sample for subsequent node devices to adjust their perceptual attention is as follows: adjust the parameters of the data processing model of the subsequent node device according to the characteristics of the point sample provided by the previous node device, so that the subsequent node device can improve its computing power for identifying the characteristics of the point sample; or, the subsequent node device uses a perceptual attention model to match the characteristics of the received point sample for computing power adjustment.

[0071] Among them, the above-mentioned "characteristics" have a different meaning from "feature recognition" in the prior art. "Feature recognition" in the prior art usually refers to information that can determine the identity of a target, while the "characteristics" of the present invention represent a kind of perceived perceptual data belonging to the to-be-identified object, such as coordinates, color on the to-be-identified object, etc. The "non-specific feature recognition" of the to-be-identified object cannot be directly completed only through the "characteristics" perceived by a single point.

[0072] In this embodiment, the method for reporting the features of the point sample for subsequent node devices to adjust the sensing attention is as follows: for the result data expressing the features of the point sample provided by the previous node device (in the present invention, usually not the features of the point sample itself, but the features of the point sample are expressed in the result data), or the features of the point sample (i.e., the features of the point sample itself), adjust the parameters of the data processing model of the subsequent node device, so that the subsequent node device improves the computing power for identifying the features of the point sample; or, the subsequent node device uses the sensing attention model to match the received features of the point sample or the result data expressing the features of the point sample for computing power adjustment.

[0073] When the node device processes the result data output by several previous node devices, based on the data processing model, when the objects to be recognized described by several previous node devices can be determined as the same target through some common point sample features, the point sample features and other information described by each node device are merged into the same target. For example, the point sample features in the physical space that almost completely overlap within the same time can be determined to be the same target.

[0074] When the result data received by the node device indicates that before the current node device received the result data this time, the flag used to identify the object to be recognized is different from the flag used by other node devices to identify the object to be recognized, and the flag assigned by other node devices to the object to be recognized is updated, then the flag used by the current node device to identify the object to be recognized before receiving the result data this time is converted. Specifically, the method for converting the flag used by the current node device to identify the object to be recognized before receiving the result data this time is as follows:

[0075] Replace the flag used by the current node device to identify the object to be recognized before receiving the result data this time with the latest flag assigned by other node devices to the object to be recognized; this is a relatively simple implementation method provided by the present invention.

[0076] Or, record the conversion relationship between the flag used by the current node device to identify the object to be recognized before receiving the result data this time and the updated flag assigned by other node devices to the object to be recognized, and perform the conversion when it is necessary to refer to the result data received by the current node device this time; this is a relatively complex implementation method provided by the present invention.

[0077] Or, the node device deploys a conversion model, and performs corresponding conversions on the flags of multiple objects to be recognized according to the input original data or result data; this is a more complex implementation method provided by the present invention.

[0078] In the present invention, in order to improve the effectiveness of "non-specific feature recognition", for one or more point samples successively collected by node devices at different collection positions, if the feature values of one or more point samples at different collection positions respectively meet the preset similar conditions or are determined by a specific model to have a correlation reaching a threshold and are unique at each collection position, then it is determined that the point samples of this type at different collection positions have a correlation.

[0079] On the other hand, for one or more point samples simultaneously collected by node devices at different collection positions, if the node devices at different collection positions collect the same spatial field, when there is only a single object to be recognized in the spatial field, or the collected point samples can correctly point to one of the multiple objects to be recognized to which they belong, then for a certain object to be recognized, one or more point samples collected by the node devices at different collection positions have a correlation.

[0080] In the present invention, the data collection device of the node device includes one or several combinations of an image acquisition device, an electromagnetic induction device, a temperature measurement device, a vibration frequency sensing device and a lidar. The data collected by the above devices (that is, one or several combinations of the image acquisition device, the electromagnetic induction device, the temperature measurement device, the vibration frequency sensing device) and the three-dimensional point cloud collected by the lidar or the point cloud generated according to the images collected by multiple image acquisition devices are jointly calculated to obtain three-dimensional points with data; the image color, contour, line, reflectivity, motion trend, electromagnetic characteristics, temperature, temperature change trend, vibration frequency, vibration frequency change trend based on two-dimensional perception are used as additional attributes of the corresponding three-dimensional points to form a three-dimensional point cloud with attributes; in combination with the change characteristics of electromagnetic induction, temperature law, vibration frequency, motion correlation (different motion correlations presented by different materials such as ropes and fabrics), and reflectivity, the corresponding relationship between each region of the three-dimensional point cloud with attributes and each part or associated part of the 3D appearance of the object to be recognized is determined. This embodiment uses the attributes of the three-dimensional point cloud with attributes and their correlations to judge the relationships between points, and the corresponding relationships between each region to which the relevant points belong and each part or associated part of the 3D appearance of the object to be recognized, and can more accurately judge the point sample characteristics belonging to the object to be recognized, improving the efficiency and accuracy of "non-specific feature recognition".

[0081] In the process of "non-specific feature recognition", the present invention can also obtain the identity information of the object to be recognized when necessary. Specifically, when it is determined that the identity information of the object to be recognized needs to be obtained, an identity information acquisition command is triggered, and the identity information acquisition command is used as one of the inputs to participate in the calculation of the result data of the node device. By driving the node device in the peer-to-peer network that is connected with the barrier-free data acquisition condition capable of obtaining the identity information of the object to be recognized to respond to the corresponding result data, the identity information of the object to be recognized is obtained. The acquisition of identity information is also the result of collaborative calculation, that is, the determination of the need to obtain identity information triggers the acquisition of identity information, rather than being triggered additionally through a specific request command. Based on the present invention, if the permission calculation is triggered by a request command, in most cases, the identity information does not need to be obtained to complete the calculation. Only when it is found that the permission calculation cannot be completed without obtaining the identity information in a few cases, a determination of the need to obtain the identity information is generated according to the implementation requirements. For example, through collaborative calculation, it is known that the identity information of a certain person exists in the code scanning registration systems at several locations, the express pick-up registration systems at several locations, or the consumption registration systems at several locations, and the person has given prior authorization or the query permission has been obtained in accordance with the law, then the peer-to-peer network can drive the node devices connected to these systems in a barrier-free data acquisition manner, and the relevant information obtained is sent to the peer-to-peer network through each node device, and information comparison is performed to provide accurate identity information. Based on this, the present invention can also minimize the possibility of forging identities by tampering with a certain system.

[0082] Specifically, the peer-to-peer network determines its permission by verifying the authenticity of the identity information of the object to be recognized; among them, the node device in the peer-to-peer network that can obtain the identity information may not provide the identity information (according to the implementation requirements, it can also provide the identity information), and only according to the verification requirement of the authenticity of the identity information in the received result data, the verification result is expressed in the result data of the node device. That is, in the present invention, in the case where the node device that can obtain the identity information does not provide the identity information, only according to the verification requirement of the authenticity of the identity information in the received result data, the verification result is expressed in the result data of the node device.

[0083] When the node device in the peer-to-peer network that can obtain the identity information does not provide the identity information, the information source device that provides the identity information is driven to establish an encrypted file transfer channel or an encrypted information transfer channel in other network communication modes between the input terminal of the node device that needs to obtain the identity information; the identity information is used as one of the inputs of the node device.

[0084] When necessary, in order to meet the requirements of other traditional computing modes for raw data, such as the evidence preservation required for traditional proof, in this embodiment, the node can be additionally provided with a data storage device for storing the raw data sensed by the sensor.

[0085] In specific implementation, the node device can also be provided with functions such as leakage protection in its power supply device. The node device can also provide various communication interfaces, including optical fiber interfaces, wireless communication interfaces, etc.; it can also provide data interfaces for external storage devices. The node device can be powered by solar energy or mains power. When the node device is implemented outdoors, it can be installed on poles such as street lamps (without cross arms, mounted on the main pole, or integrated into the lampshade); in pole-free areas, when implemented indoors, it can be wall-mounted or integrated into the ceiling.

[0086] When the present invention is implemented indoors and outdoors, the node device, as an artificial intelligence facility installed in public spaces, can be used as the digital economic infrastructure of the urban agglomeration to provide 24-hour uninterrupted seamless coverage. Through collaborative computing across node devices, vehicle identity recognition with an accuracy close to 100% can be achieved at any position within the coverage area, and the position recognition accuracy is related to the sensor accuracy.

[0087] In the architecture of the peer-to-peer computing network of the present invention, all node devices are of the same type and have the same function. Each node device adjusts its own data processing model in real time and dynamically according to the consensus mechanism of the whole network. The raw data collected by the data collection devices (including sensors, cameras, etc.) connected to each node device is processed and encrypted by the node device according to its own data processing model to generate a byte-level processing and encryption result (i.e., the result data). This result data will be sent to other node devices (the calculation and encryption results output by other node devices received by the current node device at the same time also belong to the raw data collected by the current node device). Therefore, the effects generated by the raw data sensed by each sensor will spread among a large number of peer node devices in a power-law manner. If each node device sends its result data to 100 surrounding node devices, after four unit time periods, hundreds of millions of node devices will be affected by the event sensed by the sensor. In this computing mode, information is relatively symmetric, immune to tampering and forgery, fundamentally solving the fundamental hidden dangers of traditional information technology, namely false information, forged information, and incorrect information caused by information asymmetry, which then become the entry points for fraud and cyberattacks, as well as problems such as long complex comprehensive application cycles, poor accuracy, and poor adaptability. Furthermore, it truly becomes the information infrastructure for comprehensive management of a relatively large area and the digital economic infrastructure.

[0088] The present invention utilizes the collaborative computing of the peer-to-peer network. When the result data of the collaborative computing can determine an event, the discovery of the event is completed. In this embodiment, the discovery of events by the peer-to-peer network includes the content of the event, the location where the event occurs, and the corresponding response handling, etc. In the peer-to-peer network, all events are processed synchronously. It is not necessarily required to explicitly generate phased result outputs such as what event has been discovered and what the specific content of the event is. In the peer-to-peer network, all that is clear is the sensing of the sensor and the response of the corresponding execution device. All other intermediate processes are processed simultaneously by the collaborative computing. That is, during the operation of the present invention, the intermediate process of event discovery is imperceptible. As the collaborative computing progresses and the result data of the node devices is obtained, the corresponding execution device automatically responds and executes.

[0089] For the discovery of events, the present invention may include the entry of non-"autonomous driving" driving devices, the entry of pedestrians, the occurrence of accidents, traffic control, and other such events that may affect "autonomous driving" driving devices, which can be regarded as the said external environment, and the corresponding external environment data is obtained. Furthermore, the events corresponding to the external environment are added to the collaborative computing of the peer-to-peer network to calculate in real time the optimal next action for each control component of each driving device.

[0090] In the present invention, the control components of the driving device include but are not limited to the driving component, the braking component of each tire, the steering component, the throttle control component, the energy component, the lighting device, the door lock, the door closing induction device, the wiper module, and the wiper fluid spraying device. Each control component is respectively used to perform the corresponding function and has corresponding performance parameters. Each control component or a combination of multiple control components forming the same function is added to the peer-to-peer network through one or more node devices. To avoid hijacking, the present invention can use multiple node devices to cooperate in controlling the control components, further improving the immunity to hijacking attacks.

[0091] The human-machine interaction device associated with the driving device is connected to the node device as an access device and submits a route requirement to the peer-to-peer network. In the present invention, the route requirement can be regarded as a request command, that is, it is desired that the driving device automatically drive from a certain location to another location. For the response to the request command, there are various different situations, including "requirement - execution", "request - reply", or others. When the result data calculated by one or more node devices in the peer-to-peer network matches the request command, the result corresponding to the request command is represented in the result data output by the one or more node devices, according to the preset conditions or the program deployed in advance or the output of the data processing model deployed on the node device. If it is determined based on collaborative computing that the current node device needs to respond to the request command, the current node device will send an instruction to the execution device connected to the current node device according to the calculated result data, and control the execution device to complete the response action; that is, the situation of "requirement - execution". In the present invention, if it is determined based on collaborative computing that a certain control component or a combination of multiple control components of the driving device needs to be automatically controlled based on the corresponding optimal next action, the current node device will send an instruction to the control component connected to the current node device according to the calculated result data, and control the control component to complete the control action.

[0092] Based on the collaborative computing of the peer-to-peer network, the execution device can be one of the node devices. As the collaborative computing progresses, when the result data obtained by the execution device can perform relevant operations corresponding to the request command, the execution device completes the response to the request command. In the present invention, the optimal next action is represented in the result data; the control component receives the result data output by the connected node device. If a specific element in the result data indicates that the control component needs to be automatically controlled, or the result data is one of the inputs of the data processing model of the node device, and it is calculated that the corresponding control component needs to be automatically controlled, the control component performs the corresponding control action.

[0093] When automatic control of the control component is required, the control component combines the result data output by other connected node devices, calculates its own result data, and controls the control components on the control component to perform the corresponding control action through the obtained result data. In the present invention, the control component does not need to first determine whether it needs to perform a control action, but combines the result data output by other connected node devices with the perception data collected by its own sensors, inputs them into its own data processing model, and the output result data is whether each control component of the control component acts and what action to take.

[0094] In the present invention, for a driving device, the result data calculated by its control component includes the optimal solution for all situations obtained by collaborative calculation of all driving devices within the driving area and the external environment at the current moment; the optimal next action of the driving device is reflected by the control component on the control component executing the control action corresponding to the optimal solution. In the present invention, the results of the calculation of various types of information by the peer-to-peer network are all reflected in the result data. All control components of all driving devices are used as one of the node devices. When participating in the collaborative calculation of the peer-to-peer network, their output includes the optimal solution for all situations; furthermore, all control instructions of all control components are the optimal solution instructions output after collaborative calculation by the node devices connected to them. There are no traditional generation instructions and sending instructions in the present invention, that is, to avoid the security vulnerabilities existing in the generation instructions and sending instructions, and make the control component a risk point.

[0095] In this embodiment, the control component is a node device connecting a control component with a specific function, and the execution feedback information of the control component of the control component is fed back to the control component and participates in the calculation of the subsequent result data of the control component.

[0096] In the present invention, since the control component can be used as one of the node devices, the control component responds and executes based on the calculation result obtained by collaborative calculation, with high response efficiency, avoiding illegal responses such as false execution or non-execution when it should execute due to network attacks. To avoid hijacking, the present invention can also use multiple node devices to cooperate in controlling the control component to further improve the immunity to hijacking attacks.

[0097] In the peer-to-peer network, the result data calculated and output by the node device can be implemented as a state corresponding to the characterization of sensing data (i.e., raw data), which can be represented by a state value. Furthermore, the node device does not need to store and send the raw data. In this embodiment, the data or elements in the multi-dimensional matrix are related to the installation positions, attributes, etc. of each node device. Therefore, when transmitting the result data, what is actually transmitted is the transcoding result after transcoding multiple groups of parameters. The so-called multi-dimensional matrix is actually a combination of multiple groups of parameters. For example, the path of a certain target is from a-b-c-d, and the physical positions of the abcd node devices are fixed. Therefore, the sequence of abcd can be expressed by a character or a similar concept when transmitting the transcoding of multiple groups of parameters.

[0098] Based on the technical characteristics of the peer-to-peer network, it can be applied to various usage scenarios that provide targeted services or controls for a certain target or event. Based on this, since the result data transmitted between node devices is the processing result of information, rather than the information itself, the original data collected (i.e., sensing data) does not need to be stored. Node devices only receive the calculation results output by other node devices and send out their own calculation results. The amount of information contained in a single calculation result is not sufficient to restore any event and target information. It is necessary to jointly perform collaborative calculations using the calculation results on the entire peer-to-peer network, the elements of the multi-dimensional data matrix, and the corresponding relationship between the physical space and facilities to obtain a definite result. The collaborative calculation has less dependence on the information transmitted by a small number of node devices, and thus can fundamentally change the nature of the single-point security sensitivity of traditional informatization.

[0099] In the present invention, since the state evolution of the result data output by the previous node devices is reflected in the result data output by each node device, then, based on the result data received by the current node device, the behavior, attributes, state, or event of the target when it was sensed by the previous node devices can be inferred. For example, when it is necessary to find the location of target a 15 minutes ago, the location corresponding to the node device that sensed target a at the current moment can be obtained, and then the location where target a is located can be inferred; then, according to the transmission path of the result data, it can be traced back to 15 minutes ago, and the location where target a was located 15 minutes ago can be determined (determined by the node device that sensed target a); furthermore, the node device does not need to store the original data about target a. That is, based on the present invention, it is not necessary to identify the original data to achieve the search for target a. Instead, the node device that sensed target a can be inferred first, and if necessary, the original data about target a at the moment when it needs to be searched can be obtained from the storage device connected to the node device.

[0100] In the present invention, the control component receives the result data output by other node devices. The principle is as follows: when a request command requires the corresponding control component to perform automatic control, if the result data calculated by one or more node devices can determine the control component that needs to perform automatic control, the corresponding control component is added to the node list for transmitting the current result data. The one or more node devices directly transmit the result data to the control component or the node device connected to the control component. Among them, according to the preset conditions, algorithm output, or model output, the corresponding control component is added to the node list for transmitting the result data. Alternatively, the control component receives the result data output by other node devices in a layer-by-layer transmission manner. During the collaborative calculation of the peer-to-peer network, when each node device calculates the result data each time, it also calculates the node list that needs to receive the result data. According to the current result data, it clearly knows one or more control components that need to be added, and these will be added to the node list. The control component or the node device connected to the control component is directly used as the subsequent node device in the next layer to directly receive the current result data, realizing a leap over the normal layer-by-layer transmission and turning the peer-to-peer network into a three-dimensional architecture. For example, the result data of the current node device can clearly know that evidence needs to be provided. If calculated according to the normal layer-by-layer transmission method, the result data of the current node device needs at least one or more layers of transmission to reach the corresponding node device. If the corresponding node device is added to the node list, the corresponding node device can directly receive the result data of the current node device during the next layer of transmission, thereby greatly shortening the handling time and improving the response ability. The present invention adopts a peer-to-peer network, so this kind of temporary construction is precisely the advantage of the present invention. The traditional information-based layer-by-layer aggregation architecture cannot bear the complex calculation requirements brought by this kind of temporarily constructed network.

[0101] Since the driving device moves in and out of the driving area, in the present invention, when the driving device in the original driving area arrives (that is, the driving device originally in the driving area arrives at the destination, stops driving or exits the driving area), starts (switches from a stopped state to a driving state in the driving area), or a new driving device enters the driving area, it is equivalent to a change in the target quantity collected by the node devices of the peer-to-peer network. Based on the collaborative calculation of the peer-to-peer network, the optimal next action for each control component of each driving device currently in the driving area can be obtained, thereby realizing seamless automatic driving control and adjustment of the optimal next action.

[0102] In the event of an inevitable failure, in the present invention, since the control component of the driving device serves as a node device and joins the peer-to-peer network; furthermore, if it is determined through collaborative computing that the control component is abnormal, that is, there are factor changes in the driving area, the abnormal data is used as one of the inputs to participate in the calculation of the result data, and a processing solution is obtained through collaborative computing. The processing solution can be based on collaborative computing. The peer-to-peer computing network discovers that a certain component of the current driving device has failed (in the peer-to-peer network, through a large number of node devices for collaborative computing to discover events. In most cases, there is even no intermediate process of discovering events. After a large number of features are incorporated into the calculation by the peer-to-peer network, the control components connected to the corresponding node devices can respond and execute). Vehicles of relevant departments perform "automatic driving", converge with the faulty driving device, and rescue or intercept the faulty driving device, etc.; if an accident occurs, the processing solution can also be based on collaborative computing. The node devices of the medical department discover that the current driving device has failed, and the vehicles of the medical department perform "automatic driving", converge with the faulty driving device, and rescue the injured; that is, automatic alarm and automatic convergence are completed, greatly improving the efficiency of dispatching and rescue. When necessary, if it is found through collaborative computing that the faulty driving device needs to record the original data, after the current node device receives the result data transmitted by other node devices, it is used as the original input and saved on the original data storage device connected to it.

[0103] For the driving device itself, each driving device sets a safety mechanism in read-only storage mode. If all the node devices connected to the control component are damaged and it is found through collaborative computing that the corresponding driving device will have a safety accident, the safety mechanism of the driving device is activated, and other control components are taken over according to the preset mechanism in read-only storage to control the driving device to decelerate or stop; if some braking components fail, other braking components adjust the braking force to keep the driving device in a stable posture until it stops.

[0104] The above embodiments are only used to illustrate the present invention and are not intended to limit the present invention. As long as it is based on the technical essence of the present invention, changes, variations, etc. made to the above embodiments will fall within the scope of the claims of the present invention.

Claims

1. An autonomous driving method based on multi-object synchronous control, characterized in that, Obtain the route requirements of the driving equipment within the driving area, the performance parameters, speed information, position information of each control component of the driving equipment, and the external environment data of the driving area other than the driving equipment; Based on the real-time position information, speed information, route requirements, performance parameters of each control component and external environment data of all driving equipment, calculate the optimal next action for each driving equipment in real time, and each driving equipment performs automatic control based on the corresponding optimal next action to achieve autonomous driving; Through sensors of the corresponding type deployed in and covering the driving area, obtain the performance parameters, speed information, and position information of each control component of all driving equipment within the driving area, obtain the route requirements of all driving equipment within the driving area through the human-machine interaction device associated with the driving equipment, and calculate the optimal next action for each control component of each driving equipment in real time through the computing system; The computing system is a peer-to-peer network, which uses the peer-to-peer network to perform non-specific feature recognition and position recognition on targets, and the targets include driving equipment, other fixed or moving objects other than driving equipment; The peer-to-peer network includes multiple node devices, and there is no primary or secondary relationship between all node devices; The node device is provided with a data acquisition device and an operation module. The data acquisition device includes at least one type of sensor for collecting different corresponding types of perception data; Node devices set at different acquisition positions collect at least one point sample of the target, and the point sample is the perception data of the corresponding sensor type; For a certain node device, process the collected perception data to obtain result data, and transmit the result data to other node devices; Other node devices that receive the result data use the result data as one of the collected original data, and the result data of other node devices is affected by the result data; Based on this, without the need to obtain the identity information of the target, multiple node devices in the peer-to-peer network perform collaborative calculations to determine each unique target as itself, realizing non-specific feature recognition and position recognition of driving equipment and other fixed or moving objects other than driving equipment; In the peer-to-peer network, for a certain point sample of a certain target, in the result data transmitted from the node device that collects the point sample to other node devices, subsequent node devices adjust the perception attention according to the characteristics of the point sample, or report the characteristics of the point sample for subsequent node devices to adjust the perception attention; If subsequent other node devices do not detect the characteristics of the point sample, but it can be determined from the characteristics of other point samples that the characteristics of the undetected point sample still belong to the target, then continue to express the characteristics of the undetected point sample in the result data of the current node device and transmit it to other node devices.

2. The automatic driving method based on multi-object synchronization control according to claim 1, wherein The environmental factors corresponding to the external environment data include but are not limited to weather, obstacles, pedestrians, public events, public opinion, citizens' itinerary arrangements, rickshaws, special service requirements, parking space conditions, and logistics requirements.

3. The automatic driving method based on multi-object synchronous control according to claim 1, wherein Based on the route requirements, calculate the driving route of the driving device. For a certain driving device, combine the performance parameters, speed information, and position information of each control component, and calculate the optimal next action of each control component of the driving device according to the preset safety criteria, based on the driving speed and / or driving position of other driving devices and the optimal next action of each control component of other driving devices currently calculated.

4. The automatic driving method based on multi-object synchronous control according to claim 1, characterized in that The current node device receives the result data output by other node devices; for the current node device, combine the collected sensing data with the result data from other node devices, calculate the result data of the current node device, and send it to other node devices; The node devices in the peer-to-peer network perform collaborative calculations as the sensing data is collected and the result data is calculated.

5. The automatic driving method based on multi-object synchronous control according to claim 1, characterized in that The method of reporting the characteristics of the point sample for subsequent node devices to adjust the sensing attention is as follows: for the result data expressing the characteristics of the point sample provided by the previous node device, or adjust the parameters of the data processing model of the subsequent node device with the characteristics of the point sample, so that the subsequent node device can improve the computing power for identifying the characteristics of the point sample; or, the subsequent node device uses the sensing attention model to match the received characteristics of the point sample or the result data expressing the characteristics of the point sample for computing power adjustment.

6. The automatic driving method based on multi-object synchronous control according to claim 5, characterized in that, When the node device processes the result data output by several previous node devices, based on the data processing model, when the targets described by several previous node devices can be determined as the same target through certain common point sample characteristics, merge the point sample characteristics and other information described by each node device into the same target.

7. The automatic driving method based on multi-object synchronous control according to claim 6, characterized in that, When the result data received by the node device indicates that before the current node device received the result data this time, the flag used to identify the target is different from the flag used by other node devices to identify the target, and the flag assigned by other node devices for this target is updated, then convert the flag used by the current node device to identify the target before it received the result data this time.

8. The automatic driving method based on multi-object synchronous control according to claim 6, characterized in that The method of converting the flag used by the current node device to identify the target before it received the result data this time is as follows: Replace the flag used by the current node device to identify the target before it received the result data this time with the latest flag assigned by other node devices for this target; Or, record the conversion relationship between the flag used by the current node device to identify the target before it received the result data this time and the updated flag assigned by other node devices for this target, and perform the conversion when the result data received by the current node device this time needs to be referenced; Or, the node device deploys a conversion model and performs corresponding conversions on the flags of multiple targets according to the input original data or result data.

9. The automatic driving method based on multi-object synchronous control according to claim 1, wherein For one or more point samples collected successively by node devices at different collection positions, if the characteristic values of a certain one or more point samples at different collection positions respectively meet the preset similar conditions or are determined by a specific model to have a correlation reaching the threshold, and are unique at each collection position, then it is determined that the point samples at different collection positions have relevance.

10. The automatic driving method based on multi-object synchronous control according to claim 1, wherein For one or more point samples simultaneously collected by node devices at different collection positions, if the node devices at different collection positions collect data from the same spatial field, when there is only a single target in the spatial field, or the collected point samples can correctly point to one of the multiple targets to which they belong, then for a certain target, the one or more point samples collected by the node devices at different collection positions are relevant.

11. The automatic driving method based on multi-object synchronous control according to claim 10, wherein, The data collection device of the node device includes one or a combination of an image acquisition device, an electromagnetic induction device, a temperature measurement device, a vibration frequency sensing device, and a lidar. The data collected by the above devices and the three-dimensional point cloud collected by the lidar or the point cloud generated from the images collected by multiple image acquisition devices are jointly calculated to obtain three-dimensional points with data. The image color, contour, lines, reflectivity, motion trend, electromagnetic characteristics, temperature, temperature change trend, vibration frequency, and vibration frequency change trend based on two-dimensional perception are used as additional attributes of the corresponding three-dimensional points to form a three-dimensional point cloud with attributes. The corresponding relationship between each region of the three-dimensional point cloud with attributes and each part or associated part of the 3D appearance of the consumer is determined by combining the change characteristics of electromagnetic induction, temperature law, vibration frequency, motion correlation, and reflectivity.

12. The automatic driving method based on multi-object synchronous control according to claim 1, characterized in that When the identity information of the target needs to be obtained, an identity information acquisition command is triggered and used as one of the inputs to participate in the calculation of the result data of the node device. By driving the node devices in the peer-to-peer network that are connected with unobstructed data collection conditions capable of obtaining the identity information of the target to respond to the corresponding result data, the identity information of the target is obtained.

13. The automatic driving method based on multi-object synchronization control according to claim 12, characterized in that, The peer-to-peer network verifies the authenticity of the identity information of the target and then determines its permissions. Among them, the node devices in the peer-to-peer network that can obtain identity information do not provide identity information, but only express the verification result in the result data of the node device according to the verification requirement of the authenticity of the identity information in the received result data.

14. The automatic driving method based on multi-object synchronization control according to claim 13, characterized in that, The node devices in the peer-to-peer network that can obtain identity information do not provide identity information, but drive the information source device that provides identity information to establish an encrypted file transfer channel or an encrypted information transfer channel in other network communication modes between the input terminal of the node device that needs to obtain identity information. The identity information is used as one of the inputs of the node device.

15. The automatic driving method based on multi-object synchronous control according to claim 1, wherein The data collection device described above includes one or more of an image acquisition device, an audio acquisition device, a temperature measurement device, a vibration frequency sensing device, a lidar, a chemical sensor, and an electromagnetic induction device.

16. The automatic driving method based on multi-object synchronous control according to claim 1, characterized in that The human-machine interaction device associated with the driving device is connected to the node device as an access device and submits a route requirement to the peer-to-peer network. Each control component or a combination of multiple control components that form the same function joins the peer-to-peer network through one or more node devices. If it is determined based on collaborative calculation that a certain control component or a combination of multiple control components of the driving device needs to be automatically controlled based on the corresponding optimal next action, the current node device will send an instruction to the control component connected to the current node device according to the calculated result data to control the control component to complete the control action.

17. The automatic driving method based on multi-object synchronous control according to claim 16, characterized in that, Optimal next action representation to result data; The control component receives the result data output by the connected node devices. If a specific element in the result data indicates that the control component needs to perform automatic control, or if the result data is one of the inputs to the data processing model of the node device and it is calculated and determined that the corresponding control component needs to perform automatic control, then the control component executes the corresponding control action.

18. The automatic driving method based on multi-object synchronization control according to claim 17, characterized in that, When automatic control of the control component is required, the control component combines the result data output by other node devices it receives, calculates its own result data, and controls the control component on the control component to execute the corresponding control action through the obtained result data.

19. The automatic driving method based on multi-object synchronous control according to claim 18, characterized in that, For a driving device, the result data calculated by its control component includes the optimal solution for all situations obtained through collaborative calculation of all driving devices and the external environment within the driving area at the current moment; The optimal next action of the driving device is reflected by the control component on the control component executing the control action corresponding to the optimal solution.

20. The automatic driving method based on multi-object synchronous control according to claim 18, wherein The control component receives the result data output by other node devices. The principle is: when the request command requires automatic control of the corresponding control component, if the result data calculated by one or more node devices can determine the control component that needs to be automatically controlled, then the corresponding control component is added to the node list that transmits the current result data, and the one or more node devices directly transmit the result data to the control component or the node device connected to the control component; Or, the control component receives the result data output by other node devices in a layer-by-layer transmission manner.

21. The automatic driving method based on multi-object synchronous control according to claim 20, wherein, According to preset conditions or algorithm outputs, model outputs, the corresponding control component is added to the node list that transmits the result data.

22. The automatic driving method based on multi-object synchronous control according to claim 17, wherein The control component is a node device connected to an execution component with a specific function, and the execution feedback information of the control component of the control component is fed back to the control component and participates in the calculation of the subsequent result data of the control component.

23. The automatic driving method based on multi-object synchronization control according to claim 1, characterized in that The control component of the driving device, as a node device, joins the peer-to-peer network; If it is determined through collaborative calculation that the control component is abnormal, then the abnormal data is used as one of the inputs and participates in the calculation of the result data, and a processing solution is obtained through collaborative calculation.

24. The automatic driving method based on multi-object synchronous control according to claim 23, wherein, Each driving device sets a safety mechanism in read-only storage mode. If all the node devices connected to the control component are damaged and it is found through collaborative calculation that the corresponding driving device will have a safety accident, then the safety mechanism of the driving device is activated, takes over other control components according to the preset mechanism in read-only storage, and controls the driving device to decelerate or stop; If some braking components fail, other braking components adjust the braking force to keep the driving device in a stable posture until it stops.

25. The automatic driving method based on multi-object synchronization control according to claim 16, wherein, The control components of the driving device include but are not limited to driving components, braking components for each tire, steering components, throttle control components, energy components, lighting devices, door locks, door closing induction devices, wiper modules, and wiper fluid spraying devices.