Transfer control method, device and system after vehicle is off-line

Abstract

The invention discloses a transfer control method, device and system after a vehicle is offline, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining vehicle basic data and intelligent driving special data of a to-be-transferred vehicle; acquiring site sensing data, generating a plurality of candidate paths based on the site sensing data, and determining a current planned path in the candidate paths according to the intelligent driving special data; determining a path end point of the current planned path, and inputting the parking space state data, the path end point and the vehicle basic data into a preset parking space distribution model to obtain a target parking space; and updating the current planning path according to the target parking space, and controlling the to-be-transferred vehicle to run to the target parking space along the updated current planning path. According to the method, manual driving or traction of external transfer equipment is not needed, the intelligent driving capacity of the vehicle can be directly reused to achieve transfer after the vehicle leaves the line, and then the transfer cost is reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a method, device and system for controlling the transfer of vehicles after they have rolled off the production line. Background Technology

[0002] With the maturity and widespread adoption of intelligent driving technology, the automotive manufacturing industry is gradually moving towards a high degree of automation and intelligence. In large-scale production scenarios, how to efficiently and reliably transfer vehicles to designated warehousing areas after they roll off the assembly line has become a key link in connecting production and warehousing logistics.

[0003] Currently, the industry primarily relies on external transfer equipment such as Automated Guided Vehicles (AGVs) to tow and move vehicles after they roll off the production line. However, the transfer costs are high due to the need for additional towing robots and ground guidance facilities. Furthermore, because the external transfer equipment is completely disconnected from the vehicle's integrated intelligent driving system, the transfer process can only achieve physical handling, making it difficult to adapt to the specific transfer needs of intelligent driving vehicles. In other words, it fails to address the different parking space requirements of various intelligent driving vehicles, still requiring manual intervention and resulting in high transfer costs. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device and system for controlling the transfer of vehicles after they have rolled off the production line, in order to solve the technical problem that the existing methods of transferring vehicles after they have rolled off the production line rely on external transfer equipment and manual intervention, resulting in high transfer costs.

[0005] To achieve the above objectives, this application proposes a method for controlling the transfer of vehicles after they have rolled off the production line, the method comprising: Obtain basic vehicle data and intelligent driving-specific data of the vehicles to be transferred; Acquire site perception data, generate several candidate paths based on the site perception data, and determine the current planned path from each of the candidate paths according to the intelligent driving-specific data; Determine the endpoint of the current planned path, and input the parking space status data, the endpoint of the path, and the basic vehicle data into a preset parking space allocation model to obtain the target parking space; The current planned route is updated based on the target parking space, and the vehicle to be transferred is controlled to travel along the updated current planned route to the target parking space.

[0006] In one embodiment, the step of obtaining the vehicle's basic data and intelligent driving-specific data for the vehicle to be transferred includes: Upon receiving a communication request from a vehicle to be transferred, a communication connection is established with the vehicle based on a preset two-layer communication protocol, which includes a data transmission protocol and a command transmission protocol. Based on the communication connection, the vehicle's basic data and intelligent driving-specific data are obtained according to the data transmission protocol.

[0007] In one embodiment, the basic vehicle data includes: vehicle off-line location information, and the intelligent driving-specific data includes: vehicle intelligent driving readiness. The steps of acquiring site perception data, generating several candidate paths based on the site perception data, and determining the current planned path from each of the candidate paths according to the intelligent driving-specific data include: Obtain the location information of the target transfer area, and determine the current map range to be perceived based on the vehicle off-line location information and the location information of the target transfer area; The site perception data corresponding to the current map area to be perceived is obtained by calling the electronic map interface. The site perception data includes: road planning information, traffic facility information and real-time traffic information. Based on a preset path planning algorithm, several candidate paths are generated according to the road planning information, the traffic facility information, and the real-time traffic information; The current planned path is determined from the candidate paths based on the vehicle's intelligent driving readiness.

[0008] In one embodiment, the step of generating several candidate paths based on a preset path planning algorithm, according to the road planning information, the traffic facility information, and the real-time traffic information, includes: Based on the vehicle's off-line location information, the target transfer area's location information, and the road planning information, several initial paths are generated. The path congestion coefficient corresponding to each initial path is determined based on the traffic facility information and the real-time traffic information. Several initial paths with congestion coefficients higher than a preset congestion value are filtered out from the initial paths to obtain several candidate paths.

[0009] In one embodiment, the step of inputting parking space status data, the path endpoint, and the vehicle basic data into a preset parking space allocation model to obtain a target parking space includes: The vacancy status of each candidate parking space is determined based on the parking space status data, and the distance between each candidate parking space and the end point of the path is determined based on the end point of the path. The matching degree between each candidate parking space and the vehicle to be transferred is determined based on the vehicle's basic data, and the intelligent driving status adaptability of the vehicle to be transferred is determined based on the intelligent driving specific data. The idle state, the parking space distance, the parking space vehicle matching degree, and the intelligent driving state adaptability are substituted into the preset parking space allocation model to obtain the matching score of each candidate parking space. The candidate parking space with the highest matching score is selected as the target parking space.

[0010] In one embodiment, the preset parking space allocation model is represented as:

[0011] In the formula, Let be the matching score for the k-th candidate parking space. In idle state For parking space vehicle matching degree, For parking space distance, For intelligent driving state adaptation, - All of these are pre-configured dynamic weighting coefficients.

[0012] In one embodiment, the step of updating the current planned route based on the target parking space and controlling the vehicle to be transferred to travel along the updated current planned route to the target parking space includes: A planned route within the target transfer area is generated based on the destination of the current planned route and the target parking space; Control the vehicle to be transferred to travel along the currently planned path until the vehicle to be transferred reaches the target transfer area, then control the vehicle to be transferred to travel along the planned path within the target transfer area until it reaches the target parking space.

[0013] In one embodiment, after the step of controlling the vehicle to be transferred to travel along the currently planned route, the method further includes: While the vehicle to be transferred is traveling along the current planned route, the perception data along the route corresponding to the current planned route is acquired. The system acquires real-time operating data of the vehicle to be transferred, and determines whether there are any abnormalities based on the real-time operating data and the sensing data along the route. The abnormalities include: route abnormalities, parking space abnormalities, and vehicle abnormalities. If so, an abnormal decision path is generated based on the abnormal situation, and the vehicle to be transferred is controlled to travel along the abnormal decision path.

[0014] In addition, to achieve the above objectives, this application also proposes a vehicle off-line transfer control device, the device comprising: a memory, a processor, and a vehicle off-line transfer control program stored in the memory and executable on the processor, the vehicle off-line transfer control program being configured to implement the steps of the vehicle off-line transfer control method as described above.

[0015] Furthermore, to achieve the above objectives, this application also proposes a vehicle transfer control system after it rolls off the production line. The system includes: a transfer control subsystem and a vehicle to be transferred; the transfer control subsystem includes: The data processing module is used to acquire the vehicle's basic data and intelligent driving-specific data of the vehicle to be transferred; The dynamic scheduling module is used to acquire site perception data, generate several candidate paths based on the site perception data, and determine the current planned path from each of the candidate paths according to the intelligent driving special data. The dynamic scheduling module is also used to determine the endpoint of the current planned path, and input the parking space status data, the endpoint of the path and the basic vehicle data into the preset parking space allocation model to obtain the target parking space; The vehicle control module is used to update the current planned route according to the target parking space, and control the vehicle to be transferred to travel along the updated current planned route to the target parking space.

[0016] This application discloses a method for controlling the transfer of vehicles after they have rolled off the production line, comprising: acquiring basic vehicle data and intelligent driving-specific data of the vehicle to be transferred; acquiring site perception data and generating several candidate paths based on the site perception data, and determining the current planned path from among the candidate paths according to the intelligent driving-specific data; determining the endpoint of the current planned path, and inputting parking space status data, the endpoint of the path, and basic vehicle data into a preset parking space allocation model to obtain a target parking space; updating the current planned path according to the target parking space, and controlling the vehicle to be transferred to travel along the updated current planned path to the target parking space.

[0017] This application enables the immediate acquisition of basic and intelligent driving-specific data of vehicles after they roll off the production line. It then combines this data with site perception to generate candidate routes online, selects the current planned route based on intelligent driving capabilities, and collaboratively calculates the optimal parking space allocation based on the route's endpoint. This decouples route planning from parking space allocation and optimizes their sequence, thereby controlling the vehicle to travel along the planned route to the target parking space. Consequently, it eliminates the need for manual driving or external towing equipment, directly reusing the vehicle's own intelligent driving capabilities for post-production vehicle transfer, thus reducing transfer costs. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the first embodiment of the vehicle transfer control method after it rolls off the production line according to this application. Figure 2 This is a flowchart illustrating the second embodiment of the vehicle transfer control method after it rolls off the production line according to this application. Figure 3 This is a flowchart illustrating the third embodiment of the vehicle transfer control method after it rolls off the production line according to this application. Figure 4 This is a schematic diagram of the communication interaction between the modules in the vehicle transfer control system after it rolls off the production line in this application; Figure 5 This is a schematic diagram of the structure of the transfer control equipment for the vehicles after they are off the production line in this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] This application provides a method for controlling the transfer of vehicles after they have rolled off the production line. (Refer to...) Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle transfer control method after it rolls off the production line according to this application. In this embodiment, the method includes steps S10 to S40: Step S10: Obtain the basic vehicle data and intelligent driving-specific data of the vehicle to be transferred.

[0025] It should be noted that the executing entity in this embodiment can be a computing electronic device with data processing, network communication, and program execution functions, such as a computer, mainframe computer, or cloud server. It can also be other electronic devices capable of accessing the vehicle off-line transfer control system and establishing a communication connection with the vehicle to be transferred. The following description uses a vehicle off-line transfer control device (referred to as the "control system") connected to the vehicle off-line transfer control system as an example to illustrate the various embodiments of this application.

[0026] It should be understood that the vehicle to be transferred is an autonomous driving vehicle (hereinafter referred to as "the vehicle") that has just come off the production line. This vehicle needs to be transported from the production line area to the target transfer area to realize the vehicle's off-line transfer. After the autonomous driving vehicle comes off the production line, the production line system can send the production information of the vehicle to be transferred to the control system, including: order number, vehicle ID number, and target transfer area information, to inform the control system that there is a vehicle to be transferred.

[0027] Meanwhile, after the intelligent driving vehicle rolls off the production line, the vehicle's intelligent controller can also send the vehicle's basic data and intelligent driving-specific data to the control system in real time or at regular intervals.

[0028] The vehicle's basic data can be inherent, fundamental status data, such as the Vehicle Identification Number (VIN), vehicle model, dimensions, current battery / fuel level, tire pressure, and other vehicle attributes. It can also include the vehicle's latitude and longitude information, such as the vehicle's off-line location and its real-time location during operation. This latitude and longitude information can be vehicle coordinates obtained based on dual-mode positioning using both GPS and BeiDou satellite navigation systems.

[0029] Intelligent driving-specific data can include the status information of the vehicle's intelligent driving system, including the calibration status of the perception system, the vehicle's intelligent driving readiness, and fault code information. The perception system calibration status refers to whether the cameras, radar, and lidar are calibrated normally; the autonomous driving function readiness can be a comprehensive score indicating whether the vehicle is ready to take over driving; and the fault code information can be the vehicle's historical fault codes.

[0030] In addition, the control system can also obtain vehicle driving capability data through the vehicle's intelligent driving controller. This driving capability data can include dynamic parameters such as vehicle acceleration performance and braking distance, which helps to improve the flexibility of subsequent path planning.

[0031] It should also be noted that, considering that the number of intelligent driving vehicles rolling off the production line at the same time can be multiple, in order to ensure stable communication between the vehicle and the control system in high-concurrency scenarios, a multi-protocol collaborative communication architecture can be constructed, that is, the connection between the vehicle and the control system can be achieved through dual protocols.

[0032] Therefore, step S10 specifically includes: steps S101~S102: Step S101: Upon receiving a communication request from a vehicle to be transferred, establish a communication connection with the vehicle to be transferred based on a preset two-layer communication protocol, which includes a data transmission protocol and an instruction transmission protocol.

[0033] It should be understood that the transfer mode is triggered when the vehicle to be transferred comes off the production line, and it can initiate a communication request to the control system based on the intelligent driving controller to establish a communication connection with the control system.

[0034] It should be noted that the preset two-layer communication protocol can be either Message Queuing Telemetry Transport (MQTT) or WebSocket. MQTT can be used for high-frequency status data transmission (10Hz), while WebSocket can be used for low-latency control command interaction (response time ≤50ms). This separates high-frequency status data from low-latency control commands at the communication layer, avoiding mutual interference.

[0035] In practical implementation, when the control system receives a communication request from a vehicle to be transferred, it can establish a communication connection with the intelligent driving controller in the vehicle to be transferred based on the MQTT protocol + WebSocket protocol and through a 4G / 5G dual-mode network. This solves the problem of data transmission latency and connection stability in high-concurrency scenarios after the production line using a single protocol.

[0036] Step S102: Based on the communication connection, obtain the vehicle basic data and intelligent driving special data of the vehicle to be transferred in accordance with the data transmission protocol.

[0037] It should be understood that since the vehicle basic data, intelligent driving specific data, and driving capability data are all state data, the MQTT protocol can be used to implement data transmission in accordance with the aforementioned data transmission protocol.

[0038] In practice, the control system can use the MQTT protocol to synchronously acquire basic vehicle data, intelligent driving-specific data, and driving capability data from the vehicle's intelligent driving controller. It can also preprocess the above data, remove noisy data, and generate standardized data frames for subsequent path planning.

[0039] Step S20: Obtain site perception data, generate several candidate paths based on the site perception data, and determine the current planned path from each of the candidate paths according to the intelligent driving-specific data.

[0040] It should be noted that the site perception data may include real-time traffic data collected by sensors (such as radar and cameras) deployed on roads between the production line area and the target transfer area, and may also include map data obtained based on an electronic map interface. For example, the scene perception data may include: traffic flow, congestion conditions, and obstacle information on each road.

[0041] It should be understood that the control system can initially generate multiple candidate paths from the vehicle production line area to the target transfer zone based on traffic data and map data.

[0042] It should also be noted that since intelligent driving-specific data can include vehicle intelligent driving readiness, the best path with matching vehicle intelligent driving readiness can be selected from the candidate paths initially generated above as the current planned path based on the vehicle intelligent driving readiness.

[0043] For example, the candidate routes mentioned above can be sorted based on vehicle travel time. However, since different vehicles may have different levels of vehicle intelligent driving readiness, for vehicles with lower vehicle intelligent driving readiness, candidate routes with wider roads and emergency stopping areas along the way can be prioritized as the current planned route; while for vehicles with higher vehicle intelligent driving readiness, the shortest candidate route can be directly prioritized as the current planned route.

[0044] Step S30: Determine the endpoint of the current planned path, and input the parking space status data, the endpoint of the path, and the basic vehicle data into the preset parking space allocation model to obtain the target parking space.

[0045] It should be understood that the aforementioned planned path can be a general route from the vehicle production line area to the target transfer area, meaning the endpoint of the current planned path is the entrance to the target transfer zone. When a vehicle reaches the zone entrance, it is still necessary to determine the specific parking space required within that target transfer zone.

[0046] It should be noted that this preset parking space allocation model can be an allocation model built based on specific parameters in the route endpoint, vehicle basic data, and parking space status data. Unlike the existing allocation logic that only depends on distance, the preset parking space allocation model can allocate parking spaces in the target transfer area with a higher degree of matching to vehicles.

[0047] To illustrate in detail how parking space allocation is performed based on a preset parking space allocation model, step S30 specifically includes: steps S301~S304: Step S301: Determine the vacancy status of each candidate parking space based on the parking space status data, and determine the parking space distance between each candidate parking space and the path endpoint based on the path endpoint.

[0048] It should be understood that the control system can determine the parking space status data through parking space sensors (such as cameras or geomagnetic sensors) installed in each parking space within the target transfer area, and the control system can communicate with the parking space sensors based on the HTTPS protocol.

[0049] The parking space status data can include the vacancy status of each parking space, including whether it is vacant or occupied. A vacant parking space can be numerically marked as 1, and an occupied parking space can be numerically marked as 0.

[0050] In addition, the control system can also obtain the specific location coordinates of each candidate parking space and calculate the distance from each candidate parking space to the end point of the above path, i.e., the parking space distance.

[0051] Step S302: Determine the matching degree between each candidate parking space and the vehicle to be transferred based on the vehicle basic data, and determine the intelligent driving status adaptation degree of the vehicle to be transferred based on the intelligent driving specific data.

[0052] It should be understood that the control system first determines the vehicle's attributes (size and model) based on the vehicle's basic data, and then determines the parking space attributes (space size and type) of each candidate parking space based on the parking space status data, including standard parking spaces, large parking spaces, and charging parking spaces. Finally, the vehicle attributes are matched with the parking space attributes to determine the vehicle-parking space matching degree between the vehicle and each candidate parking space.

[0053] For example, if the vehicle is a large SUV, the vehicle is more likely to be matched with a large charging parking space than with a small, non-charging parking space.

[0054] It should be noted that the control system first determines the vehicle's health status based on the vehicle's perception system calibration, intelligent driving readiness, and fault code information; then, it determines whether each candidate parking space is an emergency parking space, i.e., the emergency attribute of the parking space, based on the parking space status data. An emergency parking space can be the parking space closest to the area exit in the target transfer area or a parking space with maintenance conditions; finally, it matches the vehicle's health status with the emergency attribute of the parking space to determine the vehicle's intelligent driving status compatibility with each candidate parking space.

[0055] For example, if a vehicle is in a faulty health condition, the vehicle may be more compatible with an emergency parking space than with a non-emergency parking space.

[0056] Step S303: Substitute the idle state, the parking space distance, the parking space vehicle matching degree, and the intelligent driving state adaptability into the preset parking space allocation model to obtain the matching score of each candidate parking space.

[0057] Step S304: The candidate parking space with the highest matching score is determined as the target parking space.

[0058] It should be understood that the preset parking space allocation model can be a parking space allocation index model (PAMI model) constructed based on the above-mentioned vacancy status, parking space distance, parking space vehicle matching degree, and intelligent driving state adaptation degree. The preset parking space allocation model can be represented as follows:

[0059] In the formula, Let be the matching score for the k-th candidate parking space. In idle state For parking space vehicle matching degree, For parking space distance, For intelligent driving state adaptation, - All of these are pre-configured dynamic weighting coefficients, which can be set by the user to different or the same value based on historical experience data.

[0060] It should be noted that the matching score mentioned above is a comprehensive quantitative score for each candidate parking space. The higher the score, the more suitable the candidate parking space is for the vehicle.

[0061] In practice, the control system can acquire parking space status data based on parking space sensors, and then combine the path endpoint and vehicle basic data into a preset parking space allocation model to select the candidate parking space with the highest matching score as the target parking space. This improves the vehicle-parking space matching degree compared to parking space allocation schemes based solely on distance.

[0062] Step S40: Update the current planned route according to the target parking space, and control the vehicle to be transferred to travel along the updated current planned route to the target parking space.

[0063] It should be understood that since the current planned route terminates at the entrance of the target transfer zone, in order to ensure that vehicles clearly understand how to enter the corresponding target parking space based on the entrance, the aforementioned current planned route can be extended and refined based on the target parking space to obtain an updated current planned route. This updated planned route is then the complete final route from the vehicle's de-line position to the target parking space.

[0064] It should be noted that the control system can send the updated current planned path to the vehicle's intelligent driving controller, thereby controlling the vehicle to drive directly to the target parking space along the updated current planned path.

[0065] It should also be noted that after generating the current planned path based on the aforementioned step S20, the control system can directly send the current planned path to the intelligent driving controller to control the vehicle to start driving. When the vehicle has driven to a preset distance from the end of the path, the aforementioned step S30 is executed again to obtain the target parking space and update the current planned path, so as to control the vehicle to continue driving to the target parking space, thereby ensuring the timeliness of the target parking space.

[0066] This implementation can instantly acquire basic data and intelligent driving-specific data of vehicles after they roll off the production line. Combined with site perception data, it generates candidate routes online, then selects the currently planned route based on intelligent driving capabilities. Finally, it collaboratively calculates the optimal parking space allocation based on the route's endpoint, achieving decoupling and sequential optimization of route planning and parking space allocation. This allows the vehicle to travel along the planned route to the target parking space. Therefore, it eliminates the need for manual driving or external towing equipment, directly reusing the vehicle's own intelligent driving capabilities for post-production vehicle transfer, thereby reducing transfer costs.

[0067] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the vehicle transfer control method after it rolls off the production line according to this application.

[0068] In this embodiment, to specifically illustrate how the current planned path is generated, step S20 further includes: steps S201~S204: Step S201: Obtain the location information of the target transfer area, and determine the current map range to be perceived based on the vehicle off-line location information and the location information of the target transfer area.

[0069] It should be understood that the location information of the target transfer area can be the end area of ​​the path, which can be the geographical coordinate range of a storage area or parking lot determined by the control system based on the received production information. The vehicle off-line location information is the starting point of the path, that is, the specific location where the vehicle leaves the production line, which can be the vehicle position coordinates determined by the control system based on the received vehicle basic data.

[0070] It should be noted that, based on the location coordinates of the warehouse area and the vehicle location coordinates, a certain range from the starting point to the end point can be determined, which is the current area of ​​the map to be perceived.

[0071] Step S202: Call the electronic map interface to obtain the site perception data corresponding to the current map area to be perceived. The site perception data includes: road planning information, traffic facility information and real-time traffic information.

[0072] It should be noted that the electronic map interface (API) can be an interface provided by external professional electronic map service software. This electronic map service software can provide real-time traffic data. The control system can access the API to obtain the scene perception data, i.e., traffic data, corresponding to the current map area to be perceived, and then obtain road planning information, traffic facility information, and real-time traffic information within that area.

[0073] The road planning information can be static basic information within the scope, including road grade (main road, auxiliary road), number of lanes, direction, whether it is one-way, etc. This road planning information determines all feasible roads from the vehicle's de-line location to the target transfer area.

[0074] Traffic facility information can include information that affects the complexity of road traffic, such as traffic lights, stop signs, and zebra crossings.

[0075] Real-time traffic information can be obtained through APIs or collected in real time by sensors installed on the aforementioned roads. This information can include: current traffic flow, congestion level, and whether there are any sudden accidents or constructions.

[0076] Step S203: Based on a preset path planning algorithm, generate several candidate paths according to the road planning information, the traffic facility information, and the real-time traffic information.

[0077] It should be understood that the preset path planning algorithm can be a mature optimal path determination algorithm such as the A* algorithm or Dijkstra's algorithm.

[0078] In practice, the control device can input the aforementioned road planning information, traffic facility information, and real-time traffic information into a preset path planning algorithm. This algorithm will integrate the above information and calculate several feasible routes from the starting point to the destination, i.e., candidate routes.

[0079] For example, the candidate paths mentioned above may include feasible paths with different optimization objectives such as "shortest path", "fastest path", and "simplest path (fewest traffic lights)".

[0080] Furthermore, for the sake of specificity, step S203 also includes: steps S2031~S2033: Step S2031: Based on the vehicle's off-line location information, the target transfer area's location information, and the road planning information, generate several initial paths.

[0081] It should be noted that the control system can employ path planning algorithms, such as the A* algorithm and Dijkstra's algorithm, to directly generate several initial paths based on static data (vehicle decommissioning location information, target transfer area location information, and road planning information). These initial paths are theoretically feasible and can include: the shortest path, the fastest path, and backup paths.

[0082] Step S2032: Determine the path congestion coefficient corresponding to each initial path based on the traffic facility information and the real-time traffic information.

[0083] It should be understood that since real-time road congestion was not considered when generating the initial path, the initial path can be further filtered based on traffic facility information and real-time traffic information.

[0084] It should be noted that traffic facility information may include the number of traffic lights and intersections on the road; real-time traffic information may include the actual traffic flow and actual vehicle speed on the road.

[0085] In practical implementation, the congestion coefficient for each road can be calculated based on the number of traffic lights, intersections, actual traffic flow, and actual vehicle speed. This allows us to determine the path congestion coefficient for each initial path composed of different roads. This path congestion coefficient is a quantitative and comprehensive score (set between 0 and 1) reflecting the path's congestion situation; a higher coefficient indicates more severe congestion.

[0086] Step S2033: Filter out a number of initial paths whose congestion coefficient is higher than a preset congestion value from each of the initial paths to obtain a number of candidate paths.

[0087] It should be understood that the preset congestion value can be a threshold set in advance for the control system, which can represent the upper limit of the congestion that the control system can tolerate, for example, set to 0.7.

[0088] In practice, the control system can filter out initial paths with a congestion coefficient higher than 0.7 from the above initial paths, and the remaining initial paths can be candidate paths.

[0089] Step S204: Determine the current planned path from each of the candidate paths based on the vehicle's intelligent driving readiness.

[0090] It should be understood that vehicle intelligent driving readiness can be a core quantitative indicator extracted from intelligent driving-specific data, which can comprehensively reflect the health and reliability of the vehicle's intelligent driving system. For example, the vehicle intelligent driving readiness can be a score within the range of 0-100.

[0091] It should be noted that the control system can ultimately select the current planned path from multiple candidate paths based on the vehicle's intelligent driving readiness level. For vehicles with high readiness, the control system can determine that their intelligent driving capabilities are reliable, and thus prioritize the path with the shortest distance or fastest speed as the current planned path to ensure maximum vehicle driving efficiency. For vehicles with low readiness, the control system can determine that their intelligent driving capabilities are unreliable, and thus select the path with simpler road conditions, emergency stopping areas, or safer passage as the current planned path to ensure vehicle driving safety.

[0092] This embodiment generates an initial route based on the vehicle's offline location information and the target transfer area location information. Then, it combines road planning, traffic facilities, and real-time traffic information to determine the congestion coefficient, quickly eliminating initial routes with excessive congestion and obtaining low-congestion candidate routes. Finally, a second screening is performed on the candidate routes based on the vehicle's intelligent driving readiness to ensure that the final planned route matches the vehicle's actual intelligent driving capabilities. This reduces the processing of invalid congested routes, ensures the real-time smoothness of the issued routes, and guarantees vehicle driving safety, thereby improving route planning efficiency and vehicle transfer success rate.

[0093] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the vehicle transfer control method after it rolls off the production line according to this application.

[0094] In this embodiment, to specifically illustrate how to control the vehicle to be transferred to travel along the planned route, step S40 specifically includes: steps S401~S402: Step S401: Generate a planned route within the target transfer area based on the destination of the current planned route and the target parking space.

[0095] It should be noted that the destination of the current planned route is the entrance to the target transfer area, and the target parking space is the final destination of the vehicle determined based on the aforementioned PAMI model.

[0096] Understandably, the control system can also acquire area perception data based on sensors deployed in the target transfer area. This area perception data may include not only the aforementioned parking space status data, but also channel information within the area, such as channel connectivity, channel turning status, and avoidance zones.

[0097] In practical implementation, the control system can take the end point of the path (area entrance) as the starting point and the target parking space as the ending point, and combine the area perception data of the target transfer area to generate the planned path within the target transfer area using the same path planning algorithm as mentioned above (such as A* algorithm, Dijkstra algorithm).

[0098] Step S402: Control the vehicle to be transferred to travel along the current planned path until the vehicle to be transferred reaches the target transfer area, then control the vehicle to be transferred to travel along the planned path within the target transfer area until it reaches the target parking space.

[0099] It should be noted that the control system can convert the currently planned path and / or the planned path within the target transfer area into navigation commands and send them to the intelligent driving controller, which then controls the vehicle to drive based on the navigation commands. Furthermore, to ensure vehicle driving safety, the vehicle's speed can also be set, for example, based on the vehicle's driving capability data, setting the vehicle to travel at a speed of 25-30 km / h.

[0100] In addition, during vehicle operation, the control system can obtain the vehicle's real-time location information from the vehicle's intelligent driving controller via communication connection, and collect the vehicle's driving video data through sensors deployed on the roads between the production line area and the target transfer area. This data is then used to generate the vehicle's dynamic trajectory on the electronic map corresponding to the current area to be perceived, so that users can visually monitor the vehicle.

[0101] In practical applications, vehicles can be controlled in segments: after a vehicle rolls off the production line, the control system can first send the current planned path (first navigation command) to the intelligent driving controller, and then control the vehicle to travel along the aforementioned current planned path until the vehicle reaches the end of the path and identifies the area entrance of the target transfer area.

[0102] It should be understood that the control system can also determine that the vehicle has reached the end of the path based on sensors installed at the entrance of the target transfer area and combined with the vehicle's real-time location information; then, the planned path (second navigation command) within the target transfer area is sent to the intelligent driving controller, which then controls the vehicle to continue driving along the planned path within the target transfer area until it safely reaches the target parking space and completes the parking action.

[0103] It should be noted that, due to path segmentation and instruction relay, the vehicle can follow a stable and unchanging macro path, namely the currently planned path, for most of the driving process. This avoids the instruction jitter or instability that may be caused by frequent global replanning. Then, after reaching the target transfer area, a final local adjustment is made, thus ensuring the smoothness and reliability of the driving process.

[0104] Furthermore, to ensure driving safety while the vehicle travels along the planned route, unlike passive alarms, this embodiment can actively warn of abnormal situations using perception data along the route. Therefore, after controlling the vehicle to be transferred to travel along the current planned route, the method further includes: steps S501~S503: Step S501: When the vehicle to be transferred is traveling along the current planned path, obtain the along-route perception data corresponding to the current planned path.

[0105] It should be noted that the perception data along the route can include perception data on the roads and perception data within the target transfer area. Specifically, the control system can acquire real-time perception data of the roads along the current planned path through sensors deployed on the roads between the production line area and the target transfer area, such as real-time traffic flow, real-time congestion levels, and real-time accident or construction data; it can also acquire real-time regional perception data (parking space status data) based on sensors deployed within the target transfer area.

[0106] Step S502: Obtain the real-time operation data of the vehicle to be transferred, and determine whether there are any abnormal situations based on the real-time operation data and the sensing data along the route. The abnormal situations include: route abnormalities, parking space abnormalities, and vehicle abnormalities.

[0107] It should be understood that the intelligent driving controller can also send real-time operating data such as the vehicle's real-time location, real-time speed, and fault codes to the control system during the driving process. The control system can then make anomaly judgments based on this real-time operating data and the aforementioned roadside perception data.

[0108] It should be noted that this anomaly detection logic can include route anomaly detection, parking space anomaly detection, and vehicle anomaly detection. If a vehicle meets the above anomaly detection logic, and the vehicle still travels along the original current planned route or the planned route within the target transfer area, it may result in the vehicle's travel time exceeding the planned time or failure to reach the target parking space.

[0109] For example, the logic for determining route anomalies can be as follows: if the real-time congestion coefficient of the road the vehicle is currently traveling on and the next road to be traveled on suddenly spikes (e.g., exceeds 0.8) based on the perception data along the route, then the vehicle cannot continue traveling according to the currently planned route.

[0110] The logic for judging abnormal parking spaces can be as follows: if the target parking space is determined to be occupied based on the parking space status data, the vehicle cannot travel along the planned route within the target transfer area.

[0111] The logic for judging vehicle abnormalities can be as follows: determine the failure of the vehicle's intelligent driving function based on real-time operating data.

[0112] Step S503: If so, generate an abnormal decision path based on the abnormal situation, and control the vehicle to be transferred to travel along the abnormal decision path.

[0113] It should be understood that if the control system determines, based on the above-mentioned anomaly judgment logic, that there is at least one of the following anomalies: route anomaly, parking space anomaly, and vehicle anomaly, it will generate the corresponding anomaly decision path according to the corresponding anomaly.

[0114] In the event of a route anomaly, the control system can recalculate a new route that bypasses the congested section and identify it as an abnormal decision route that replaces the current planned route. The vehicle can then continue to the area entrance based on this abnormal decision route and then travel along the planned route within the aforementioned target transfer area to the target parking space.

[0115] In case of parking space anomalies, the control system can quickly call the PAMI model to reassign a new parking space and generate a path from the vehicle's real-time location to the new parking space as an abnormal decision path that replaces the current planned path and the planned path within the target transfer area. The vehicle can then drive directly to the new parking space based on this abnormal decision path.

[0116] In case of vehicle malfunctions, the control system can determine the nearest emergency parking space based on the vehicle's real-time location and site perception data. It then uses shortest distance algorithms, such as A* or Dijkstra's algorithm, to generate the shortest and safest path to the nearest emergency parking space—the malfunction decision path. The vehicle can then proceed directly to the emergency parking space based on this path, activating its hazard lights.

[0117] In practice, when an abnormal situation is detected, the control system can generate a corresponding abnormal decision path based on the abnormal situation, and convert the abnormal decision path into an abnormal navigation command and send it to the intelligent driving controller. This causes the intelligent driving controller to interrupt the execution of the aforementioned navigation command and switch to controlling the vehicle to drive along the abnormal decision path.

[0118] This embodiment acquires real-time perception data and vehicle operation data along the route during vehicle operation, and dynamically diagnoses three types of anomalies: route, parking space, and vehicle. Based on the anomaly, it automatically generates and switches to an emergency decision-making path. This achieves a closed-loop handling mechanism from anomaly perception to decision execution, effectively transforming passive alarms into proactive solutions, and significantly improving the safety of the transfer process and the level of automation in responding to emergencies.

[0119] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle transfer control method after it is off the production line. Any simple modifications based on this technical concept are within the protection scope of this application.

[0120] This application also proposes a vehicle transfer control system after it rolls off the production line. This system includes a transfer control subsystem and the vehicle to be transferred. (See here for reference.) Figure 4 The communication interaction process between the transfer control subsystem and the vehicles to be transferred in the system is described. Figure 4 This is a schematic diagram of the communication interaction between the modules in the vehicle transfer control system after the vehicle rolls off the production line in this application.

[0121] Depend on Figure 4 It is understood that in the transfer control system after the vehicle rolls off the production line, the vehicle to be transferred can communicate and interact with the transfer control subsystem based on the intelligent driving controller. In addition, the transfer control subsystem can also communicate and interact with the production line system and environmental sensors (sensors in the target transfer area and sensors in the current area to be perceived on the map).

[0122] The transfer control subsystem may include: a data processing module, a dynamic scheduling module, and a vehicle control module.

[0123] The data processing module is used to acquire the vehicle's basic data and intelligent driving-specific data for the vehicle to be transferred.

[0124] Specifically, the data processing module can acquire basic vehicle data and intelligent driving-specific data from the intelligent driving controller based on the MQTT protocol, and perform standardized processing and caching of the aforementioned data for subsequent calculations. The basic vehicle data and intelligent driving-specific data can be collected by the vehicle's own onboard perception module and synchronized to the intelligent driving controller.

[0125] The dynamic scheduling module is used to acquire site perception data, generate several candidate paths based on the site perception data, and determine the current planned path from each of the candidate paths according to the intelligent driving-specific data.

[0126] Specifically, the dynamic scheduling module can obtain site perception data from sensors in the current area to be perceived based on the MQTT protocol, generate candidate paths by combining the location information of the target transfer area obtained from the production line system, and determine the current planned path by combining intelligent driving-specific data.

[0127] Among them, the site perception data and the location information of the target transfer area can be preprocessed and cached by the data processing module before being sent to the dynamic scheduling module.

[0128] The dynamic scheduling module is also used to determine the endpoint of the current planned path, and input the parking space status data, the endpoint of the path and the basic vehicle data into the preset parking space allocation model to obtain the target parking space.

[0129] Specifically, the dynamic scheduling module can also obtain parking space status data from sensors in the target transfer area based on the MQTT protocol, and then combine the route endpoint and vehicle basic data into the PAMI model to allocate parking spaces and determine the target parking space. The vehicle control module is used to update the current planned route according to the target parking space, and control the vehicle to be transferred to travel along the updated current planned route to the target parking space.

[0130] Specifically, the vehicle control module can generate navigation instructions based on the target parking space and the current planned route, and send the navigation instructions to the intelligent driving controller based on the WebSocket protocol, so as to control the vehicle to drive to the target parking space based on the updated current planned route.

[0131] It should also be noted that the transfer control subsystem may include a full-process monitoring module and an active emergency module.

[0132] The full-process monitoring module can acquire and store all data involved in the vehicle transfer process (vehicle basic data, intelligent driving specific data, location information of the target transfer area, site perception data, parking space status data, etc.), and generate vehicle driving trajectory based on the actual vehicle path for subsequent viewing.

[0133] The active emergency module can make real-time judgments on abnormal situations during vehicle operation and generate abnormal decision paths. The vehicle control module then converts the abnormal decision paths into abnormal navigation commands and sends the abnormal navigation commands to the intelligent driving controller based on the WebSocket protocol, so as to control the vehicle to drive according to the abnormal decision paths.

[0134] This embodiment's vehicle transfer control system can instantly acquire basic data and intelligent driving-specific data after a vehicle rolls off the production line. It combines this with site perception data to generate candidate routes online, then filters the current planned route based on intelligent driving capabilities, and collaboratively calculates the optimal parking space allocation based on the route's endpoint. This achieves decoupling and sequential optimization of route planning and parking space allocation, thereby controlling the vehicle to travel along the planned route to the target parking space. Therefore, it eliminates the need for manual driving or external transfer equipment, directly reusing the vehicle's own intelligent driving capabilities for post-production transfer, thus reducing transfer costs. Furthermore, unlike passive alarms, it can proactively resolve anomalies based on abnormal situation judgment logic, which helps ensure the safety of vehicle transfer after rollout.

[0135] This application also provides a vehicle off-line transfer control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the vehicle off-line transfer control method in the first embodiment described above.

[0136] The following is for reference. Figure 5 , Figure 5 This is a schematic diagram of the structure of the vehicle transfer control device after it rolls off the production line according to this application. The vehicle transfer control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants (PDAs), tablet computers (PADs), portable media players (PMPs), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The vehicle transfer control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0137] like Figure 5As shown, the vehicle off-line transfer control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the vehicle off-line transfer control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the vehicle off-line transfer control equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a vehicle off-line transfer control equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented or possessed alternatively.

[0138] The vehicle post-production transfer control device provided in this application, employing the vehicle post-production transfer control method described in the above embodiments, can solve the technical problems of the vehicle post-production transfer control method. Compared with the prior art, the beneficial effects of the vehicle post-production transfer control device provided in this application are the same as those of the vehicle post-production transfer control method provided in the above embodiments, and other technical features of the vehicle post-production transfer control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0139] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other elements in the process, method, article, or system that includes that element.

[0140] The sequence numbers of the above embodiments of the present invention are merely for description and do not represent the superiority or inferiority of the embodiments. They are only some embodiments of this application and are not intended to limit the scope of this application. All equivalent structural transformations made under the technical concept of this application and based on the content of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included within the protection scope of this application.

Claims

1. A method for controlling the transfer of vehicles after they have rolled off the production line, characterized in that, The method includes: Obtain basic vehicle data and intelligent driving-specific data of the vehicles to be transferred; Acquire site perception data, generate several candidate paths based on the site perception data, and determine the current planned path from each of the candidate paths according to the intelligent driving-specific data; Determine the endpoint of the current planned path, and input the parking space status data, the endpoint of the path, and the basic vehicle data into a preset parking space allocation model to obtain the target parking space; The current planned route is updated based on the target parking space, and the vehicle to be transferred is controlled to travel along the updated current planned route to the target parking space.

2. The method as described in claim 1, characterized in that, The steps for obtaining the basic vehicle data and intelligent driving-specific data of the vehicles to be transferred include: Upon receiving a communication request from a vehicle to be transferred, a communication connection is established with the vehicle based on a preset two-layer communication protocol, which includes a data transmission protocol and a command transmission protocol. Based on the communication connection, the vehicle's basic data and intelligent driving-specific data are obtained according to the data transmission protocol.

3. The method as described in claim 1, characterized in that, The basic vehicle data includes: vehicle off-line location information; the intelligent driving specific data includes: vehicle intelligent driving readiness. The steps of acquiring site perception data, generating several candidate paths based on the site perception data, and determining the current planned path from each of the candidate paths according to the intelligent driving-specific data include: Obtain the location information of the target transfer area, and determine the current map range to be perceived based on the vehicle off-line location information and the location information of the target transfer area; The site perception data corresponding to the current map area to be perceived is obtained by calling the electronic map interface. The site perception data includes: road planning information, traffic facility information and real-time traffic information. Based on a preset path planning algorithm, several candidate paths are generated according to the road planning information, the traffic facility information, and the real-time traffic information; The current planned path is determined from the candidate paths based on the vehicle's intelligent driving readiness.

4. The method as described in claim 3, characterized in that, The step of generating several candidate paths based on a preset path planning algorithm, according to the road planning information, the traffic facility information, and the real-time traffic information, includes: Based on the vehicle's off-line location information, the target transfer area's location information, and the road planning information, several initial paths are generated. The path congestion coefficient corresponding to each initial path is determined based on the traffic facility information and the real-time traffic information. Several initial paths with congestion coefficients higher than a preset congestion value are filtered out from the initial paths to obtain several candidate paths.

5. The method as described in claim 1, characterized in that, The step of inputting parking space status data, the path endpoint, and the vehicle basic data into a preset parking space allocation model to obtain the target parking space includes: The vacancy status of each candidate parking space is determined based on the parking space status data, and the distance between each candidate parking space and the end point of the path is determined based on the end point of the path. The matching degree between each candidate parking space and the vehicle to be transferred is determined based on the vehicle's basic data, and the intelligent driving status adaptability of the vehicle to be transferred is determined based on the intelligent driving specific data. The idle state, the parking space distance, the parking space vehicle matching degree, and the intelligent driving state adaptability are substituted into the preset parking space allocation model to obtain the matching score of each candidate parking space. The candidate parking space with the highest matching score is selected as the target parking space.

6. The method as described in claim 5, characterized in that, The preset parking space allocation model is represented as follows: In the formula, Let be the matching score for the k-th candidate parking space. In idle state For parking space vehicle matching degree, For parking space distance, For intelligent driving state adaptation, - All of these are pre-configured dynamic weighting coefficients.

7. The method as described in claim 1, characterized in that, The step of updating the current planned route according to the target parking space and controlling the vehicle to be transferred to travel along the updated current planned route to the target parking space includes: A planned route within the target transfer area is generated based on the destination of the current planned route and the target parking space; Control the vehicle to be transferred to travel along the currently planned path until the vehicle to be transferred reaches the target transfer area, then control the vehicle to be transferred to travel along the planned path within the target transfer area until it reaches the target parking space.

8. The method as described in claim 7, characterized in that, After the step of controlling the vehicle to be transferred to travel along the currently planned route, the method further includes: While the vehicle to be transferred is traveling along the current planned route, the perception data along the route corresponding to the current planned route is acquired. The system acquires real-time operating data of the vehicle to be transferred, and determines whether there are any abnormalities based on the real-time operating data and the sensing data along the route. The abnormalities include: route abnormalities, parking space abnormalities, and vehicle abnormalities. If so, an abnormal decision path is generated based on the abnormal situation, and the vehicle to be transferred is controlled to travel along the abnormal decision path.

9. A vehicle transfer control device after it rolls off the production line, characterized in that, The device includes: a memory, a processor, and a vehicle off-line transfer control program stored in the memory and executable on the processor, the vehicle off-line transfer control program being configured to implement the steps of the vehicle off-line transfer control method as described in any one of claims 1 to 8.

10. A vehicle transfer control system after it rolls off the production line, characterized in that, The system includes: a transfer control subsystem and vehicles to be transferred; the transfer control subsystem includes: The data processing module is used to acquire the vehicle's basic data and intelligent driving-specific data of the vehicle to be transferred; The dynamic scheduling module is used to acquire site perception data, generate several candidate paths based on the site perception data, and determine the current planned path from each of the candidate paths according to the intelligent driving special data. The dynamic scheduling module is also used to determine the endpoint of the current planned path, and input the parking space status data, the endpoint of the path and the basic vehicle data into the preset parking space allocation model to obtain the target parking space; The vehicle control module is used to update the current planned route according to the target parking space, and control the vehicle to be transferred to travel along the updated current planned route to the target parking space.

Images