Unmanned vehicle remote high-precision control method and system based on digital twinning

Abstract

The invention relates to an unmanned vehicle remote high-precision control method and system based on digital twinning. The method comprises the following steps: acquiring image data sent by an edge cooperative processing terminal located at a node position; delimiting a suspected range area in the image data according to the self-positioning data, and determining a vehicle object located in the suspected range area; acquiring surrounding environment information; determining a local position in the suspected range area according to information included in the image data or determining the local position in the suspected range area according to the surrounding environment information; and sending the local position and the driving data to an edge co-processing terminal located at the node position. According to the unmanned vehicle remote high-precision control method and system based on digital twinning disclosed by the invention, high-precision control of the unmanned vehicle is realized by means of node auxiliary positioning and image matching positioning modes, and the economy of the unmanned vehicle in a multi-vehicle cooperative control scene is improved.

Description

Technical Field

[0001] This application relates to the field of driving automation technology, and in particular to a remote high-precision control method and system for unmanned vehicles based on digital twins. Background Technology

[0002] The autonomous driving technology routes for vehicles can be broadly divided into high-precision map routes and end-to-end routes. High-precision map routes refer to achieving autonomous driving based on the collected high-precision data, while end-to-end routes refer to achieving autonomous driving based on the vehicle's driving capabilities.

[0003] In actual use, it was found that high-precision map routes have problems such as insufficient coverage, high data update costs, difficulty in scene adaptation, and over-reliance on positioning. They are only suitable for use in small-scale scenarios (unmanned ports, open-pit mines, and park logistics). End-to-end routes, on the other hand, directly get rid of the dependence on high-precision maps and are suitable for use in large-scale commercial scenarios (mainly for individuals).

[0004] The core of remote high-precision control of autonomous vehicles based on digital twins is to construct a closed loop of "vehicle-road-cloud-twin". Through real-time mapping, predictive simulation, and low-latency command issuance, it achieves centimeter-level positioning, millisecond-level response, and dynamic disturbance rejection, while ensuring safe and efficient collaboration between autonomous control and remote intervention. Technically, it can be divided into four parts: perception and data acquisition, digital twin modeling and simulation, decision-making and control, and execution and feedback. These four parts work together to achieve high-precision autonomous driving of vehicles.

[0005] In open-pit mines, there are problems such as harsh environment, high equipment failure rate and great difficulty in adaptation. This leads to the problem of control command lag in the current control method that relies on wireless communication and sensor information collection. Especially in the case of multi-vehicle collaborative control, it is necessary to reduce operating efficiency to ensure safety, resulting in low economic efficiency of autonomous driving in this scenario. Summary of the Invention

[0006] This application provides a remote high-precision control method and system for unmanned vehicles based on digital twins. It achieves high-precision control of unmanned vehicles by means of node-assisted positioning and image-assisted positioning, thereby improving the economy of unmanned vehicles in multi-vehicle cooperative control scenarios.

[0007] The above-mentioned objective of this application is achieved through the following technical solution: In a first aspect, this application provides a remote high-precision control method for unmanned vehicles based on digital twins, including: Acquire image data sent by the edge collaborative processing terminal located at the node position; Based on its own positioning data, the system delineates a suspected area in the image data and identifies vehicles located within that area. Acquire surrounding environmental information, which includes feature information and location information of surrounding vehicle objects; Determine the local location within the suspected area based on information included in the image data, or determine the local location within the suspected area based on information from the surrounding environment. Send local location and driving data to the edge collaborative processing terminal located at the node location.

[0008] In one possible implementation of the first aspect, delineating a suspected area region in the image data based on its own positioning data and identifying vehicle objects located within the suspected area region includes: Calculate the current position coordinates based on the received signals; Obtain the position coordinates of a reference object in the image data; Create a potential range region on the image data using the current location coordinates and the location coordinates of a reference object in the image data; Vehicles that are wholly or partially located within the suspected range area are considered as vehicles located within the suspected range area.

[0009] In one possible implementation of the first aspect, when the image data does not include the position coordinates of the reference object, the edge position coordinates of the image data are used in conjunction with the current position coordinates to create a suspected range region. When creating a suspected range area using the edge position coordinates of image data in conjunction with the current position coordinates, the edge collaborative processing terminal crops the image data after generating the image data and assigns edge position coordinates to the cropped image data.

[0010] In one possible implementation of the first aspect, after obtaining the image data sent by the edge collaborative processing terminal located at the node position, the method further includes: Determine processing priority based on the characteristic information of surrounding vehicles; Image data sent by edge collaborative processing terminals located at node positions is collected multiple times in time series according to priority. When the received image data includes the location information of surrounding vehicles, the local location is determined based on the location information of surrounding vehicles included in the image data.

[0011] In one possible implementation of the first aspect, when determining the processing priority based on the feature information of surrounding vehicle objects, the method further includes: Define the priority range associated with the priority and determine the vehicle objects within the priority range. The vehicle objects within the priority range are denoted as reference objects. When receiving image data from edge collaborative processing terminals located at node positions multiple times in a time series, only the region in the image data associated with the reference object is processed.

[0012] In one possible implementation of the first aspect, determining the local location within the suspected range area based on surrounding environmental information includes: Use information about the surrounding environment to build an environmental feature model; The environmental feature model is compared with the received image data to determine the location; Calculate the local location based on the determined location.

[0013] In one possible implementation of the first aspect, establishing an environmental feature model includes: Determine the number of surrounding vehicles; Calculate the relative position and relative distance with each surrounding vehicle object; An environmental feature model is established using the calculated relative positions and distances. The environmental feature model includes a planar rectangular reference map, in which the relative positions and distances between adjacent rectangles are calculated.

[0014] Secondly, this application provides a remote high-precision control device for unmanned vehicles based on digital twins, comprising: The first data acquisition unit is used to acquire image data sent by the edge collaborative processing terminal located at the node position; The first processing unit is used to delineate a suspected range area in the image data based on its own positioning data and to identify vehicle objects located within the suspected range area. The second data acquisition unit is used to acquire surrounding environment information, which includes the feature information and positioning information of surrounding vehicle objects. The second processing unit is used to determine the local location within the suspected range area based on the information included in the image data or based on the surrounding environment information. The data communication unit is used to send local location and driving data to the edge collaborative processing terminal located at the node location; Thirdly, this application provides a remote high-precision control system for unmanned vehicles based on digital twins, the system comprising: One or more memories for storing instructions; and One or more processors are configured to call and execute the instructions from the memory to perform the methods described in the first aspect and any possible implementation thereof.

[0015] Fourthly, this application provides a computer-readable storage medium, the computer-readable storage medium comprising: The program, when run by a processor, is executed as described in the first aspect and any possible implementation thereof.

[0016] Fifthly, this application provides a computer program product, including program instructions that, when run by a computing device, execute the method described in the first aspect and any possible implementation thereof.

[0017] Sixthly, this application provides a chip system including a processor for implementing the functions involved in the foregoing aspects, such as generating, receiving, transmitting, or processing the data and / or information involved in the foregoing methods.

[0018] This chip system can consist of chips or include chips and other discrete components.

[0019] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means, or the processor and the memory can be coupled to the same device. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating the steps of a remote high-precision control method for unmanned vehicles based on digital twins, as provided in this application.

[0021] Figure 2 This is a schematic diagram of an edge collaborative processing terminal provided in this application, which is responsible for broadcasting within a regional area.

[0022] Figure 3 This is a schematic diagram of a suspected range area provided in this application.

[0023] Figure 4 This is a schematic diagram illustrating the prioritization of vehicle objects as provided in this application.

[0024] Figure 5 This is a schematic diagram of collecting image data multiple times over a time series, as provided in this application.

[0025] Figure 6 This is a schematic diagram of calculating position coordinates based on the relative positions of two vehicles, as provided in this application. Detailed Implementation

[0026] To better understand the technical solutions in this application, the relevant technologies will be introduced first.

[0027] The specific requirements for sensors, data transmission, and control in remote, high-precision control of autonomous vehicles are as follows: Vehicle-mounted devices: LiDAR, cameras, IMU, millimeter-wave radar, wheel speedometers, etc. are used to collect images of vehicle pose, chassis status, environmental obstacles and road conditions, at a frequency of 10–100Hz.

[0028] Roadside: Centimeter-level positioning and vehicle-road cooperative environmental data are provided using RSU, LiDAR, high-definition cameras and BeiDou / RTK base stations, at a frequency of 5–20Hz.

[0029] Data transmission: Using a 5G private network, the end-to-end latency is controlled within 50ms, and the bit error rate is ≤0.001%.

[0030] Remote control platform: VR / AR visual cockpit, providing manual takeover, human-machine collaboration, and autonomous control.

[0031] Based on actual scenario requirements, the following problems exist: The large number of sensors makes maintenance difficult, especially in harsh environments, where sensor lifespan is generally shortened. The data formats and sampling frequencies of vehicle-mounted / roadside sensors (LiDAR, cameras, IMU, etc.) are not uniform, resulting in noise and drift. After fusion, the positioning error is likely to exceed 5cm. In environments with obstructions or weak networks, the end-to-end latency of 5G private networks is prone to exceeding the 50ms threshold, and the delayed command issuance can lead to security risks. When high-definition video and control commands are transmitted concurrently, bandwidth consumption is high, which can easily lead to network congestion and data packet loss.

[0032] The current solution is to use a combination of central computing and edge computing. Central computing is used for overall planning, while edge computing is used for local basic information processing. When there is no solution, manual intervention is used.

[0033] Considering the actual conditions of open-pit mines, the instruction lag caused by data transmission delays and obstruction delays is particularly significant. To solve this problem, this application uses the method of deploying nodes at key locations, with the nodes assisting vehicles passing through the nodes to perform local precise positioning.

[0034] The technical solutions in this application will be further described in detail below with reference to the accompanying drawings.

[0035] This application discloses a remote high-precision control method for unmanned vehicles based on digital twins. Please refer to [link / reference]. Figure 1 In some examples, the remote high-precision control method for unmanned vehicles based on digital twins disclosed in this application includes the following steps: S101, acquire image data sent by the edge collaborative processing terminal located at the node location; S102, Based on its own positioning data, it delineates a suspected range area in the image data and identifies vehicle objects located within the suspected range area; S103, Obtain surrounding environment information, which includes feature information and location information of surrounding vehicle objects; S104, determine the local location within the suspected range area based on the information included in the image data or based on the surrounding environment information; S105 sends local location and driving data to the edge collaborative processing terminal located at the node location.

[0036] Overall, in step S101, the vehicle's onboard computer or intelligent controller first acquires image data sent by the edge collaborative processing terminal located at the node position. This image data is captured by the image sensor at the intersection, and then the edge collaborative processing terminal is responsible for broadcasting it within the area. Figure 2 As shown.

[0037] In some possible implementations, node location refers to road intersections, congestion-prone areas, and newly developed road sections in a given scenario. Road intersections and congestion-prone areas are prone to vehicle convergence, while newly developed road sections, due to unclear conditions, require the use of edge collaborative processing terminals for assistance, with adjustments made based on actual traffic conditions.

[0038] Next, in step S102, a suspected area is delineated in the image data based on the self-positioning data, and vehicle objects located within the suspected area are identified. Here, the self-positioning data is approximate location data, such as... Figure 3 As shown, instead of precise local location data.

[0039] It should be noted that satellite positioning accuracy is 1-3 meters. If pseudorange differential or carrier differential technology is used, the positioning accuracy can reach the centimeter level. However, in mining applications, the positioning accuracy will be affected because: Slopes, mine pits, large machinery, and dust can cause satellites to lose lock or reflect signals, with multipath errors reaching several meters. Harmonics and in-band interference generated by mining motors, frequency converters, and high-voltage lines cause frequent receiver loss and data loss rate of up to 30%; blasting vibrations and heavy-duty mining truck bumps affect the stability of antenna phase center and cause significant dynamic positioning drift. The ionospheric / tropospheric delay is amplified when there are large elevation fluctuations and drastic diurnal temperature differences in the mining area.

[0040] To address this issue, this application employs node localization. Node coordinates are precise, known quantities; by processing the image at the node's location, accurate local coordinates can be obtained. In step S103, surrounding environment information is acquired simultaneously. The surrounding environment information includes the feature information and location information of surrounding vehicle objects. Both the feature information and the location information belong to the surrounding vehicles. The feature information of surrounding vehicle objects includes three types: color information, license plate information, and vehicle body feature information.

[0041] In step S104, the local location is determined within the suspected range area based on the information included in the image data or based on the surrounding environment information.

[0042] Once the local location is obtained, step S105 is executed, sending the local location and driving data to the edge collaborative processing terminal located at the node location. Sending the local location to the edge collaborative processing terminal at the node location facilitates the edge collaborative processing terminal in transmitting image data with more useful information during subsequent regional broadcasts.

[0043] The purpose of sending driving data to the edge collaborative processing terminal located at the node is to facilitate data collection by the edge collaborative processing terminal. The collected data can be directly packaged into the image data sent by the edge collaborative processing terminal in step S101.

[0044] Another advantage of this approach is that it avoids communication between vehicle objects. If direct communication between vehicle objects is used, multiple vehicle objects will be working simultaneously, which will directly affect signal quality. The delay caused by complex signal processing and the sudden decline in signal quality will lead to delays in positioning data, posing a safety hazard.

[0045] Another approach involves the vehicle using millimeter-wave radar or binocular vision for distance measurement. However, the effectiveness of these methods decreases in dusty environments because dust directly interferes with millimeter-wave reflection and the imaging quality of the edge-processing terminal at the node location. This may necessitate multiple measurements, which could lead to issues with obtaining local distance measurement results. As can be seen from the preceding description, the scenario addressed in this application is multi-vehicle cooperative control at a certain location. In this scenario, some vehicles may be unable to use millimeter-wave radar or binocular vision for ranging when obstructed.

[0046] The digital twin involved in this application involves modeling an open-pit mine and a vehicle. The virtual vehicle moves in the virtual open-pit mine, and its movement is the same as that of a vehicle in the open-pit mine. Based on this, the driving scenario can be divided into single-vehicle passing node positions and multi-vehicle passing node positions. When a multi-vehicle passing node position occurs, the technical solution described in this application needs to be used for processing.

[0047] One purpose of modeling open-pit mines is that there is insufficient road information reference in open-pit mines, making it impossible to determine the current location and driving strategy through a purely visual solution. By modeling and locating open-pit mines, vehicles can easily obtain road condition information.

[0048] In some cases, the steps for delineating a suspected area in image data based on self-location data and identifying vehicle objects located within that area are as follows: S201, Calculate the current position coordinates based on the received signals; S202, Obtain the position coordinates of the reference object in the image data; S203, Use the current position coordinates and the position coordinates of the reference object in the image data to create a suspected range region on the image data; S204, vehicles that are wholly or partially located within the suspected range area are considered as vehicles located within the suspected range area.

[0049] In steps S201 to S204, a suspected range region is created on the image data using the current position coordinates and the position coordinates of the reference object in the image data, such as... Figure 3 As shown, vehicles that are all or partly located within the suspected range area are then considered as vehicles located within the suspected range area.

[0050] The current location coordinates are calculated by the positioning device carried on the vehicle, while the location coordinates of the reference object in the image data are obtained by parsing the received image data.

[0051] The purpose of creating a suspected range area is to determine the approximate location of the vehicle object. The advantage of this method is that when multiple image data are received, only a part of the image data can be processed. This can achieve pre-compression of the data processing volume and obtain results in a shorter time.

[0052] In addition, the suspected range area is even smaller. If one of the vehicle objects within this range has coordinates, its own coordinates can be calculated based on those coordinates.

[0053] In some possible implementations, when the image data does not include the position coordinates of the reference object, the edge position coordinates of the image data are used in conjunction with the current position coordinates to create a suspected range region; When creating a suspected range area using the edge position coordinates of image data in conjunction with the current position coordinates, the edge collaborative processing terminal crops the image data after generating the image data and assigns edge position coordinates to the cropped image data.

[0054] It should be understood that when image data is generated, the coordinates and orientation of the corresponding edge collaborative processing terminal are known quantities. At this time, the generated image data has coordinates. After the image data is cropped, the edges of the image data will have edge position coordinates.

[0055] If the above process is performed by the edge collaborative processing terminal, then the edge collaborative processing terminal generates image data, crops the image data, and then assigns edge position coordinates to the cropped image data.

[0056] In some examples, after obtaining the image data sent by the edge collaborative processing terminal located at the node position, the following steps are added: S301, determine the processing priority based on the feature information of surrounding vehicle objects; S302, according to priority, collect image data sent by the edge collaborative processing terminal located at the node location multiple times in time sequence; S303, when the received image data includes the location information of surrounding vehicle objects, the local location is determined based on the location information of surrounding vehicle objects included in the image data.

[0057] In steps S301 to S303, the vehicle objects located at the node positions are prioritized for processing, and then their local locations are determined based on these priorities. Figure 4 As shown, vehicle objects marked as 1 have higher priority than other vehicle objects. Vehicle objects marked as 1 first determine their precise local coordinates using the method described above. The remaining vehicle objects begin to calculate their own precise local coordinates after their adjacent vehicle objects marked as 1 have precise local coordinates.

[0058] For example, determining the local location of a vehicle object located on the outermost edge is significantly easier than determining the local location of a vehicle object located in the middle. Therefore, in this application, the processing priority is determined based on the characteristic information of surrounding vehicle objects. For instance, when a vehicle object is located on the outermost edge, its processing priority is set to the highest level, and the processing priority of vehicle objects decreases sequentially from the outside to the inside.

[0059] Step S302 involves collecting image data from the edge collaborative processing terminal located at the node position multiple times in time series according to priority, such as... Figure 5 As shown, an image object will not proceed to subsequent processing if other vehicle objects in its surrounding environment do not carry local location information.

[0060] In step S303, when the received image data includes the location information of surrounding vehicle objects, the local location is determined based on the location information of surrounding vehicle objects included in the image data.

[0061] This sequential processing method can avoid processing invalid data.

[0062] In some examples, when determining processing priorities based on the characteristic information of surrounding vehicle objects, the following additional content has been added: Define the priority range associated with the priority and determine the vehicle objects within the priority range. The vehicle objects within the priority range are denoted as reference objects. When receiving image data from edge collaborative processing terminals located at node positions multiple times in a time series, only the region in the image data associated with the reference object is processed.

[0063] Vehicle objects within the priority range are closer together, which allows for a more accurate local location calculation.

[0064] One specific way to calculate local location is to add or subtract the x and y coordinates based on the relative positions of the two vehicles, such as... Figure 6 As shown. The influence of vehicle attitude also needs to be considered here; therefore, the minimum calculated value is used as a reference value to calculate the precise local position coordinates.

[0065] In some cases, the specific methods for determining the local location within a suspected area based on surrounding environmental information are as follows: Use information about the surrounding environment to build an environmental feature model; The environmental feature model is compared with the received image data to determine the location; Calculate the local location based on the determined location.

[0066] This method uses a comparison approach based on environmental feature models built from surrounding environmental information to determine the location. The advantage of this method is that it is easy to implement, because the relative position and distance between vehicles can be directly obtained through LiDAR and image sensors, which is not difficult to implement.

[0067] Image comparison requires extensive processing and is susceptible to interference from the surrounding environment and vehicles (such as snow, rain, and dust), leading to uncertainty in both processing time and results. However, comparing images using environmental feature models built from surrounding information avoids this problem.

[0068] The specific methods for establishing an environmental feature model are as follows: Determine the number of surrounding vehicles; Calculate the relative position and relative distance with each surrounding vehicle object; An environmental feature model is established using the calculated relative positions and distances. The environmental feature model includes a planar rectangular reference map, in which the relative positions and distances between adjacent rectangles are calculated.

[0069] An environmental feature model is established using the calculated relative positions and relative distances. The environmental feature model includes a planar rectangular reference map, and the relative positions and relative distances between adjacent rectangles in the planar rectangular reference map. Figure 6 The relative position and relative distance are obtained by referring to S1-S4 in the calculation.

[0070] In the image data received by the vehicle objects, the relative positions and distances between vehicles can be obtained through calculation.

[0071] Of course, at this point, relative position and distance can also be correlated with vehicle body color to increase the distinctiveness of the environmental feature model. Alternatively, the vehicle object can be moved slightly to compare the data from two images, and its position can be determined by observing the changes it undergoes.

[0072] This application also provides a remote high-precision control device for unmanned vehicles based on digital twins, including: The first data acquisition unit is used to acquire image data sent by the edge collaborative processing terminal located at the node position; The first processing unit is used to delineate a suspected range area in the image data based on its own positioning data and to identify vehicle objects located within the suspected range area. The second data acquisition unit is used to acquire surrounding environment information, which includes the feature information and positioning information of surrounding vehicle objects. The second processing unit is used to determine the local location within the suspected range area based on the information included in the image data or based on the surrounding environment information. The data communication unit is used to send local location and driving data to the edge collaborative processing terminal located at the node location; Furthermore, based on its own positioning data, the process of delineating a suspected area in the image data and identifying vehicle objects located within that area includes: Calculate the current position coordinates based on the received signals; Obtain the position coordinates of a reference object in the image data; Create a potential range region on the image data using the current location coordinates and the location coordinates of a reference object in the image data; Vehicles that are wholly or partially located within the suspected range area are considered as vehicles located within the suspected range area.

[0073] Furthermore, when the image data does not include the position coordinates of the reference object, the edge position coordinates of the image data are used in conjunction with the current position coordinates to create a suspected range region; When creating a suspected range area using the edge position coordinates of image data in conjunction with the current position coordinates, the edge collaborative processing terminal crops the image data after generating the image data and assigns edge position coordinates to the cropped image data.

[0074] Furthermore, after obtaining the image data sent by the edge collaborative processing terminal located at the node position, it also includes: Determine processing priority based on the characteristic information of surrounding vehicles; Image data sent by edge collaborative processing terminals located at node positions is collected multiple times in time series according to priority. When the received image data includes the location information of surrounding vehicles, the local location is determined based on the location information of surrounding vehicles included in the image data.

[0075] Furthermore, when determining processing priority based on the characteristic information of surrounding vehicle objects, it also includes: Define the priority range associated with the priority and determine the vehicle objects within the priority range. The vehicle objects within the priority range are denoted as reference objects. When receiving image data from edge collaborative processing terminals located at node positions multiple times in a time series, only the region in the image data associated with the reference object is processed.

[0076] Furthermore, determining the local location within the suspected area based on surrounding environmental information includes: Use information about the surrounding environment to build an environmental feature model; The environmental feature model is compared with the received image data to determine the location; Calculate the local location based on the determined location.

[0077] Furthermore, establishing an environmental characteristic model includes: Determine the number of surrounding vehicles; Calculate the relative position and relative distance with each surrounding vehicle object; An environmental feature model is established using the calculated relative positions and distances. The environmental feature model includes a planar rectangular reference map, in which the relative positions and distances between adjacent rectangles are calculated.

[0078] In one example, the unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0079] For example, when the units in the device can be implemented through a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these units can be integrated together to form a system-on-a-chip (SOC).

[0080] In this application, various objects such as messages / information / devices / network elements / systems / apparatus / actions / operations / processes / concepts may be named. It is understood that these specific names do not constitute a limitation on the relevant objects. The names may be changed depending on the scenario, context, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from their functions and technical effects embodied / performed in the technical solution.

[0081] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0083] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0085] It should also be understood that in the various embodiments of this application, the terms "first," "second," etc., are merely to indicate that multiple objects are different. For example, a first time window and a second time window are only to indicate different time windows. They should not have any effect on the time windows themselves, and the aforementioned terms "first," "second," etc., should not impose any limitations on the embodiments of this application.

[0086] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0087] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0088] This application also provides a remote high-precision control system for unmanned vehicles based on digital twins, the system comprising: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory, performing the methods described above.

[0089] This application also provides a computer program product including instructions that, when executed, cause the terminal device and the network device to perform operations corresponding to the methods described above.

[0090] This application also provides a chip system including a processor for implementing the functions involved in the above description, such as generating, receiving, transmitting, or processing the data and / or information involved in the above methods.

[0091] This chip system can consist of chips or include chips and other discrete components.

[0092] The processor mentioned above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits that execute a program to control the method of transmitting the feedback information described above.

[0093] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means to support the chip system in implementing the various functions described in the above embodiments. Alternatively, the processor and the memory can also be coupled to the same device.

[0094] Optionally, the computer instructions are stored in memory.

[0095] Optionally, the memory can be a storage unit within the chip, such as a register or cache. Alternatively, the memory can be a storage unit located outside the chip within the terminal, such as a ROM or other types of static storage devices that can store static information and instructions, such as RAM.

[0096] It is understood that the memory in this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0097] Non-volatile memory can be ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0098] Volatile memory can be RAM, which is used as an external cache. There are many different types of RAM, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory.

[0099] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A digital-twin-based remote high-precision control method for unmanned vehicles, characterized in that, The method comprises: acquiring image data sent by an edge collaborative processing terminal located at a node position; determining a vehicle object located in a suspected range area in the image data according to self-positioning data; acquiring surrounding environment information, which comprises feature information and positioning information of surrounding vehicle objects; determining a local position in the suspected range area according to information included in the image data or according to the surrounding environment information; sending the local position and driving data to the edge collaborative processing terminal located at the node position. 2.The digital-twin-based remote high-precision control method of an unmanned vehicle according to claim 1, characterized in that, Determining a vehicle object located in a suspected range area in the image data according to self-positioning data comprises: calculating a current position coordinate according to the received signal; acquiring a position coordinate of a reference object in the image data; creating a suspected range area on the image data using the current position coordinate and the position coordinate of the reference object in the image data; regarding a vehicle object located in the suspected range area as a vehicle object located in the suspected range area. 3.The digital-twin-based remote high-precision control method of an unmanned vehicle according to claim 2, characterized in that, When the position coordinate of the reference object is not included in the image data, creating the suspected range area using an edge position coordinate of the image data in cooperation with the current position coordinate; When the suspected range area is created using the edge position coordinate of the image data in cooperation with the current position coordinate, the edge collaborative processing terminal cuts the image data after generating the image data and assigns an edge position coordinate to the cut image data. 4.The digital-twin-based remote high-precision control method of an unmanned vehicle according to any one of claims 1 to 3, characterized in that, After acquiring the image data sent by the edge collaborative processing terminal located at the node position, the method further comprises: determining a processing priority according to the feature information of the surrounding vehicle objects; collecting image data sent by the edge collaborative processing terminal located at the node position multiple times in a time sequence according to the priority; When the positioning information of the surrounding vehicle objects is included in the collected image data, determining a local position according to the positioning information of the surrounding vehicle objects included in the image data.

5. The digital-twin-based remote high-precision control method of an unmanned vehicle according to claim 4, characterized in that, When determining a processing priority according to the feature information of the surrounding vehicle objects, the method further comprises: determining a vehicle object in a priority range associated with the priority and regarding the vehicle object in the priority range as a reference object; When collecting image data sent by the edge collaborative processing terminal located at the node position multiple times in a time sequence, only processing a region associated with the reference object in the image data. 6.The digital-twin-based remote high-precision control method of an unmanned vehicle according to any one of claims 1 to 3, characterized in that, Determining a local position in the suspected range area according to the surrounding environment information comprises: establishing an environment feature model using the surrounding environment information; placing the environment feature model in the received image data for comparison to obtain a determined position; calculating the local position according to the determined position.

7. The digital-twin-based remote high-precision control method of an unmanned vehicle according to claim 6, characterized in that, Establishing an environment feature model comprises: determining the number of surrounding vehicle objects; calculating a relative position and a relative distance of each surrounding vehicle object; establishing the environment feature model using the calculated relative position and relative distance, wherein the environment feature model comprises a planar rectangular reference graph, and the relative position and relative distance between adjacent rectangles in the planar rectangular reference graph are referenced to calculate the relative position and relative distance.

8. A digital-twin-based remote high-precision control device for unmanned vehicles, characterized in that, The method comprises: a first data acquisition unit, configured to acquire image data sent by an edge collaborative processing terminal located at a node position; The first processing unit is configured to delimit a suspected range area in the image data according to the self-positioning data and determine a vehicle object located in the suspected range area; The second data acquisition unit is configured to acquire surrounding environment information, the surrounding environment information including feature information and positioning information of surrounding vehicle objects; The second processing unit is configured to determine a local position in the suspected range area according to information included in the image data or determine the local position in the suspected range area according to the surrounding environment information; The data communication unit is configured to send the local position and the driving data to an edge collaborative processing terminal located at a node position.

9. A remote high-precision control system for unmanned vehicles based on digital twinning, characterized by, The system comprises: one or more memories for storing instructions; and one or more processors for calling and running the instructions from the memories to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises: a program, when the program is run by a processor, the method of any one of claims 1 to 7 is performed.

Images