Method for realizing path collaborative planning by using industrial vehicle ADAS system

Abstract

The invention relates to the technical field of path planning, in particular to a method for realizing path collaborative planning by using an industrial vehicle ADAS system. The method comprises the steps of obtaining driving information of an industrial vehicle and road distribution of a working area in a current time period, and constructing a connected graph based on the driving information and the road distribution, according to the emergency condition type of each fork node during each time of information acquisition, the number of connecting lines of each fork node in the connected graph and the number of fork nodes between each fork node and other fork nodes on each connecting line, obtaining a route passing index; the nodes in the connected graph are clustered, the information discontinuous influence degree is determined according to the node number of the cluster to which each fork node belongs and the distribution discrete situation of the route passing indexes between each fork node and the fork node directly associated with the fork node, and then the path of the industrial vehicle is planned in real time. According to the invention, the industrial vehicle path planning effect is ensured, and the operation efficiency and safety of the vehicle are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a method for realizing collaborative path planning by utilizing an industrial vehicle ADAS system. Background Art

[0002] The path planning in the ADAS system of industrial vehicles realizes environmental perception through multi-sensor integration and data fusion technology, combines laser radar, camera and GPS and other equipment to obtain information, and realizes dynamic collection, processing, fusion and analysis of multi-modal data through intelligent agents, uses large models for feature extraction, pattern recognition and anomaly detection, and realizes local path optimization, and uses V2V and V2I communication to realize information sharing and collaboration between vehicles. In a multi-vehicle collaborative working environment, PID or MPC control algorithms are used to accurately execute paths, combined with virtual simulation and field testing to ensure the effectiveness and safety of the system.

[0003] Existing path planning methods generally only plan the driving routes of industrial vehicles based on the distance of the route. However, in the actual industrial production process, in order to improve work efficiency, multiple industrial vehicles often work together to complete transportation work at the same time, and some sections may not be able to operate safely and efficiently. Therefore, when using existing path planning methods to plan the driving routes of industrial vehicles, there is a problem of poor planning effect. Summary of the invention

[0004] In order to solve the problem that the existing methods have poor planning effects when planning the driving routes of industrial vehicles, the purpose of the present invention is to provide a method for realizing path collaborative planning by using an industrial vehicle ADAS system. The technical solutions adopted are as follows: The present invention provides a method for realizing path collaborative planning by using an industrial vehicle ADAS system, the method comprising the following steps: Acquire the driving information of the industrial vehicle and the road distribution of the working area in the current time period, and construct a connected graph based on the driving information and the road distribution, wherein the nodes in the connected graph include the fork nodes of the road and the position nodes of the industrial vehicle; Obtaining the influence of each fork node at each information collection according to the emergency situation type of each fork node in the connected graph at each information collection and the number of links of each fork node in the connected graph; obtaining the route traffic index between each fork node and other fork nodes by combining the influence of each fork node at each information collection in the connected graph and the number of fork nodes between each fork node and other fork nodes on each link; Clustering the nodes in the connectivity graph, and determining the degree of information discontinuity impact of each fork node according to the number of nodes in the cluster to which each fork node belongs and the distribution discreteness of the route traffic index between each fork node and the fork nodes directly associated with it in the connectivity graph; Plan the paths of industrial vehicles in real time based on the impact of information discontinuities.

[0005] Preferably, obtaining the influence degree of each fork node at each information collection according to the emergency situation type of each fork node in the connectivity graph at each information collection and the number of connections of each fork node in the connectivity graph comprises: Based on the emergency situation type of the candidate fork node at each information collection in the current time period, determine the corresponding preset impact coefficient; According to the number of links of the candidate fork node in the connectivity graph and the preset influence coefficient, the influence degree of the candidate fork node at each information collection is obtained; The candidate fork node is any fork node in the connected graph.

[0006] Preferably, obtaining the influence degree of the candidate fork node at each information collection according to the number of links of the candidate fork node in the connectivity graph and the preset influence coefficient includes: The normalized result of the product of the number of links of the candidate fork node in the connectivity graph and the preset influence coefficient corresponding to each information collection of the candidate fork node in the current time period is determined as the influence degree of the candidate fork node at each information collection.

[0007] Preferably, the method combines the influence degree of each fork node in the connectivity graph at each information collection and the number of fork nodes between each fork node and other fork nodes on each link line to obtain the route traffic index between each fork node and other fork nodes, including: Calculate the first sum of the influence of the first fork node during all information collections in the current time period; count the total number of all fork nodes between the first fork node and the second fork node on all links in the connected graph; Obtaining a route traffic index between a first fork node and a second fork node according to the first sum value and the total number; The first fork node is any fork node in the connected graph, and the second fork node is any fork node in the connected graph except the first fork node and on the same line as the first fork node.

[0008] Preferably, obtaining the route traffic index between the first fork node and the second fork node according to the first sum value and the total number includes: A first product between the first sum and the total number is calculated, and a negative correlation normalization result of the first product is used as a route traffic index between the first fork node and the second fork node.

[0009] Preferably, a connected graph clustering algorithm is used to cluster all nodes in the connected graph.

[0010] Preferably, the information discontinuity influence degree of each fork node is determined according to the number of nodes in the cluster to which each fork node belongs and the distribution discreteness of the route traffic index between each fork node and the fork node directly associated with it in the connectivity graph, including: Calculate the degree of dispersion of the route traffic index between the candidate fork node and all fork nodes directly associated with it; According to the number of nodes in the cluster to which the candidate fork node belongs and the degree of discreteness, the degree of influence of information discontinuity of the candidate fork node is obtained. The number of nodes in the cluster to which the candidate fork node belongs is positively correlated with the degree of influence of information discontinuity, and the degree of discreteness is negatively correlated with the degree of influence of information discontinuity.

[0011] Preferably, the acquisition of the discrete degree includes: determining the standard deviation of the route traffic index between the candidate fork node and all the fork nodes directly associated with it as the discrete degree.

[0012] Preferably, the real-time planning of the path of the industrial vehicle based on the degree of impact of information discontinuity includes: The degree of influence of the information discontinuity is used as the weight of the path node, and all path planning priorities are divided into the first level, the second level and the third level according to the large model; When at the first level, the corresponding path is used as the preferred path, and the industrial vehicle performs mobile operations; When in the second level, the industrial vehicle decelerates on the corresponding path or selects an alternative path; When in the third level, braking measures are taken on the industrial vehicle.

[0013] Preferably, the constructing a connectivity graph based on the driving information and the road distribution includes: The positions of industrial vehicles at each time of information collection in the current time period and the forks in the working area roads passed by the industrial vehicles are taken as nodes in the connected graph. The corresponding nodes in the connected graph are connected according to the paths traveled by all industrial vehicles in the current time period to obtain a connected graph.

[0014] The present invention has at least the following beneficial effects: The present invention first constructs a connected graph corresponding to the current time period according to the driving information of industrial vehicles and the road distribution of the working area in the current time period, and then evaluates the influence of the fork node at each information collection according to the emergency type of each fork node in the connected graph and the number of links of each fork node in the connected graph. Combined with the influence of each fork node at each information collection and the number of fork nodes between each fork node and other fork nodes on each link, the passability between different road forks is evaluated to obtain a route passability index. The larger the route passability index, the higher the passability of the road between the corresponding two forks. The nodes in the connected graph are clustered. According to the number of nodes of the cluster to which each fork node belongs and the distribution discreteness of the route passability index between each fork node and the fork node directly associated with it in the connected graph, the influence degree of the information discontinuity of each fork node is obtained, and then the path of the industrial vehicle is planned. The multimodal data is comprehensively analyzed. The system can generate a more optimized path planning scheme, reduce path deviation, and improve the operation efficiency and safety of the vehicle. The present invention collects driving data of industrial vehicles in real time during driving, ensuring that the vehicles can quickly respond to environmental changes and status updates, thereby making more accurate and timely decisions in path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of a method for implementing collaborative path planning using an industrial vehicle ADAS system provided by an embodiment of the present invention; Figure 2 A structural block diagram of a system for implementing collaborative path planning using an industrial vehicle ADAS system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the method for realizing path collaborative planning by using the industrial vehicle ADAS system proposed by the present invention is described in detail below in combination with the accompanying drawings and preferred embodiments.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the method for implementing path collaborative planning using an industrial vehicle ADAS system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] An embodiment of a method for realizing collaborative path planning using an industrial vehicle ADAS system: The specific scenario targeted by this embodiment is: in industrial vehicle path planning, in order to ensure work efficiency, the driving path or driving speed of the industrial vehicle is adjusted in real time according to the actual situation of each path.

[0021] This embodiment proposes a method for realizing path collaborative planning using an industrial vehicle ADAS system, such as Figure 1 As shown, the method for implementing path collaborative planning using an industrial vehicle ADAS system in this embodiment includes the following steps: Step S1, obtaining the driving information of the industrial vehicle and the road distribution of the working area in the current time period, and constructing a connected graph based on the driving information and the road distribution, wherein the nodes in the connected graph include the fork nodes of the road and the position nodes of the industrial vehicle.

[0022] In the industrial environment of industrial vehicles, in order to improve the ADAS system's perception of complex driving environments, it is necessary to optimize sensor data fusion and strengthen multi-source data synchronization and real-time processing. By adopting time series analysis and prediction models, the system can more accurately detect and evaluate complex driving environment conditions. Combined with the lightweight deep learning model of edge computing, the system's adaptability and real-time performance are enhanced. Multi-level risk assessment and optimized decision planning can improve the system's collision risk prediction capabilities.

[0023] In industrial vehicle path planning, edge computing is first required. Appropriate edge computing devices, such as industrial-grade computers and embedded systems, are selected. These devices have sufficient computing power to process complex models and real-time data. Industrial vehicles are equipped with a variety of sensors to collect environmental information in real time. Cameras are used to capture images, perform visual recognition and object detection; LiDAR provides detailed three-dimensional spatial data to help identify the shape and precise location of objects. These sensor data are locally processed and initially fused through edge computing devices to reduce data transmission delays.

[0024] Using large-model intelligent agents, edge computing devices can analyze and fuse multiple sensor data to improve the accuracy of environmental perception and the reliability of decision-making. The processed information is fed back to the vehicle's control system in real time with low latency, supporting key operations such as path planning, obstacle avoidance, and speed adjustment, ensuring that the vehicle operates efficiently and safely in dynamic and complex environments.

[0025] The image data collected by the camera is obtained by combining with the camera installed at the key position of the industrial vehicle; the image data obtained is the complex driving environment information perceived by the current position of the laser radar; after obtaining the image, the obstacle is marked according to the outline of the obstacle scanned by the laser radar, and the image acquisition device integrated with the laser radar can also obtain the obstacle; and the impact coefficient of the abnormal environment type on the industrial vehicle operation is judged, and marked with a preset impact coefficient.

[0026] The route data of industrial vehicles is also processed. In the digital map, each route and fork is assigned a unique identifier, such as "R1" or "J1", to facilitate system identification and scheduling. Use paint or reflective stickers to mark route and fork numbers on the ground to facilitate identification by the on-board vision system of industrial vehicles. RFID tags are installed at routes and forks. Vehicles read these tags to update location information. QR codes or barcodes are installed at key locations, and vehicle cameras scan to obtain location labels. Computer vision technology is used to identify labels in images, such as reading sign text through OCR. Wireless sensor nodes are deployed at route nodes and forks to provide unique identification to support navigation.

[0027] This embodiment first obtains the distribution of roads in the work area, which are roads on which industrial vehicles can work. Then, the driving information of all industrial vehicles in the work area in the current time period is collected. The current time period is a collection of all historical moments whose time interval with the current moment is less than or equal to the preset time length. In this embodiment, the preset time length is 10 minutes. In specific applications, the implementer can set it according to specific circumstances. The driving information includes the location of all vehicles during the driving process at each collection moment. In this embodiment, the driving information is collected once every second. In specific applications, the implementer can set the collection frequency of driving information according to specific circumstances.

[0028] So far, this embodiment has collected the driving information of industrial vehicles and the road distribution information of the work area in the current time period. Since the working area of ​​industrial vehicles is usually laid out in a straight line or grid format, the routes that industrial vehicles can pass in the working area are usually fixed to ensure that industrial vehicles and other equipment run along the predetermined path, so the fork in each road is known. The position of the industrial vehicle at each information collection in the current time period and the fork in the road in the working area passed by the industrial vehicle are used as nodes in the connectivity graph, and the corresponding nodes in the connectivity graph are connected according to the paths traveled by all industrial vehicles in the current time period to obtain a connectivity graph, and the unique identifiers of the nodes and the lines, such as "R1" or "J1", remain unchanged, then each fork node has at least two lines connected to it, then for path collaborative planning, the effective planning of its path should be based on the industrial vehicle operating environment, and the possible range of passability impacts occurring at different locations are different. The method for constructing a connectivity graph is a prior art and will not be described in detail here.

[0029] Step S2, obtaining the influence of each fork node at each information collection according to the emergency situation type of each fork node in the connected graph at each information collection and the number of connections of each fork node in the connected graph; obtaining the route traffic index between each fork node and other fork nodes by combining the influence of each fork node in the connected graph at each information collection and the number of fork nodes between each fork node and other fork nodes on each connection line.

[0030] In the actual working environment of industrial vehicles, the extraction of environmental information relies on the collection of various sensors (such as LiDAR, cameras, RFID readers, etc.) carried by the moving industrial vehicles to keep the latest status of route and fork information, which has obvious intermittent information extraction characteristics. During its driving process, the industrial vehicle will obtain the identification information of the current location by scanning ground markers, QR codes or RFID tags. These location information and environmental data are uploaded to the central system or local computing unit in real time through wireless communication technology (such as Wi-Fi, Bluetooth). The central system will analyze and process the received data and update the route and fork information in the digital map. This includes identifying any possible changes, such as the occurrence of abnormal driving conditions, route changes or new path selection. In this way, the system can quickly correct any inaccurate or outdated map data. The updated information is fed back to the industrial vehicle in real time, enabling it to dynamically adjust the navigation path to improve driving efficiency and avoid potential dangers. Therefore, the accuracy of the path collaborative planning method for industrial vehicles is mainly affected by the accuracy of information update.

[0031] Since storage areas are usually laid out in a straight line or grid format, routes within work areas are usually fixed to ensure that industrial vehicles and other equipment run along predetermined paths. The navigation paths of industrial vehicles are relatively regular. The path selection in the path planning process of industrial vehicles depends more on the route forks and the related connectivity between paths, that is, its impact on the possible traffic conditions of multiple vehicles on the route. It should be analyzed more from the perspective of the structural impact changes of the grid distribution of the navigation path. In fact, it is to consider changes in the path similar to traffic flow. Path planning is actually mainly manifested in the specific consideration of the passability of the path and forks.

[0032] This embodiment will first evaluate the influence of each fork node in each information collection according to the emergency situation type of each fork node in the connectivity graph and the number of links of each fork node in the connectivity graph.

[0033] Specifically, this embodiment is described by taking a fork node in a connectivity graph as an example, and other fork nodes can be processed by the method provided in this embodiment.

[0034] Any fork node in the connectivity graph is recorded as a candidate fork node, and the preset impact coefficient of the corresponding emergency type is determined based on the emergency type of the candidate fork node during each information collection in the current time period; the preset impact coefficient is manually set by the staff according to the emergency type. The more urgent the emergency type, the greater the preset impact coefficient. The specific value is set according to the specific situation.

[0035] The normalized result of the product of the number of links of the candidate fork node in the connectivity graph and the preset influence coefficient corresponding to each information collection of the candidate fork node in the current time period is determined as the influence degree of the candidate fork node at each information collection.

[0036] In this embodiment, a specific calculation formula for the influence degree is given. The influence degree of the i-th fork node in the connectivity graph during the j-th information collection can be expressed as: in, It indicates the influence degree of the i-th fork node in the j-th information collection, represents the number of links of the i-th fork node in the connected graph, It represents the preset influence coefficient corresponding to the jth information collection of the i-th fork node in the current time period.

[0037] It represents the impact of the type of emergency situation occurring on the routes around the location of the i-th fork node. The larger the product, the greater the influence of the i-th fork node on the nearby route planning, that is, the greater the influence of the i-th fork node at the jth information collection.

[0038] Due to the regularity of the navigation path of industrial vehicles and the uniqueness of the connectivity between nodes, that is, industrial vehicles can only update information through the set regular path, the correlation between two nodes on the connectivity graph is the performance of the passability of the node connection. Therefore, the navigation path of industrial vehicles mainly depends on the connection characteristics between nodes, that is, the fewer the number of nodes between nodes, the stronger the passability of the path. Based on this, this embodiment then calculates the route passability index between each fork node and other fork nodes according to the influence of each fork node at each information collection and the number of fork nodes between each fork node and other fork nodes on each connection line. The route passability index is used to reflect the passability of the path.

[0039] Next, this embodiment is described by taking two fork nodes in a connectivity graph as an example.

[0040] Specifically, any fork node in the connected graph is recorded as the first fork node, and the second fork node is any fork node other than the first fork node and on the same line as the first fork node; the first sum of the influence of the first fork node during all information collections in the current time period is calculated; the total number of all fork nodes between the first fork node and the second fork node on all lines in the connected graph is counted. The first product between the first sum and the total number is calculated, and the negative correlation normalization result of the first product is used as the route traffic index between the first fork node and the second fork node.

[0041] In this embodiment, a specific calculation formula for the route traffic index is given, and the route traffic index between the i-th fork node and the k-th fork node can be expressed as: in, represents the route traffic index between the i-th fork node and the k-th fork node, represents the influence degree of the i-th fork node during the j-th information collection, and J represents the number of times the information of the i-th fork node is collected in the current time period, that is, the number of times the industrial vehicle passes through the i-th fork node in the current time period; It represents the total number of all fork nodes between the i-th fork node and the k-th fork node on all the links in the connected graph, and exp() represents an exponential function with a natural constant as the base.

[0042] represents the first sum value, Represents the first product, which represents the structural association between the i-th fork node and the k-th fork node, and is used for subsequent planning impact analysis. When the i-th fork node has a smaller impact in the current time period and the first product is smaller, the route between the i-th fork node and the k-th fork node is more suitable for passage, that is, the route passability index between the i-th fork node and the k-th fork node is larger.

[0043] By adopting the above method, the route traffic index between each fork node and other fork nodes can be obtained.

[0044] Step S3, clustering the nodes in the connectivity graph, and determining the degree of information discontinuity impact of each fork node according to the number of nodes in the cluster to which each fork node belongs and the distribution discreteness of the route traffic index between each fork node in the connectivity graph and the fork nodes directly associated with it.

[0045] When using the industrial vehicle ADAS system to implement collaborative path planning for industrial vehicles, the priority of the industrial vehicle driving path planning has a certain relationship with the position of other industrial vehicles, and it is necessary to reduce possible collisions from the region. However, since industrial vehicles obtain identification information of the current position by scanning ground markers, QR codes or RFID tags during their driving process to keep the latest status of route and fork information, they have obvious intermittent information extraction characteristics. The corresponding performance on the connectivity graph is the structural manifestation of the connectivity graph, that is, only when there are industrial vehicles on the fork and route at the time of data collection to obtain road condition information, the corresponding nodes on the connectivity graph have information data.

[0046] A connected graph clustering algorithm is used to cluster all nodes in the connected graph corresponding to the current time period to obtain multiple clusters. Each cluster is regarded as the regional influence range of the route traffic conditions in the local area. For each node, the more nodes in the cluster it belongs to within the collection period and the stronger the change characteristics, the greater the degree of influence of the node information discontinuity.

[0047] Still taking the candidate fork node as an example for explanation, specifically, the standard deviation of the route access index between the candidate fork node and all the fork nodes directly associated with it is used as the degree of dispersion of the route access index between the candidate fork node and all the fork nodes directly associated with it; the larger the standard deviation, the more discrete the distribution of the route access index, that is, the greater the degree of dispersion. According to the number of nodes in the cluster to which the candidate fork node belongs and the degree of dispersion, the degree of information discontinuity influence of the candidate fork node is obtained, and the number of nodes in the cluster to which the candidate fork node belongs is positively correlated with the degree of information discontinuity influence, and the degree of dispersion is negatively correlated with the degree of information discontinuity influence.

[0048] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by actual application; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtractive relationship, a division relationship, etc., which is determined by actual application.

[0049] In this embodiment, a specific calculation formula for the influence degree of information discontinuity is given. The influence degree of information discontinuity of the i-th fork node in the connectivity graph can be expressed as: in, Indicates the degree of influence of information discontinuity at the i-th fork node in the connectivity graph, Indicates the number of nodes in the cluster to which the i-th fork node belongs, represents the standard deviation of the route traffic index between the i-th fork node and all the fork nodes directly associated with it in the connectivity graph, that is, the degree of dispersion; norm() represents the normalization function, Indicates the preset first adjustment parameter.

[0050] It should be noted that: for any fork node, the fork node directly associated with it is on the same line as the fork node, and there is no other fork node between the two fork nodes.

[0051] The purpose of introducing the preset first adjustment parameter into the calculation formula of the information discontinuity impact degree is to prevent the denominator from being 0. In this embodiment, the preset first adjustment parameter is 0.01. In specific applications, the implementer can set it according to the specific situation. It is used to reflect the influence of node information under the influence of information discontinuity. The larger the value is, the greater the influence of information discontinuity on the i-th fork node in the connectivity graph.

[0052] By adopting the above method, the influence degree of information discontinuity of each fork node can be obtained.

[0053] Step S4, planning the path of the industrial vehicle in real time based on the degree of impact of information discontinuity.

[0054] In this embodiment, the degree of information discontinuity influence of each fork node in step S3 is used as the weight of the path node, and then all path planning priorities are divided according to the large model, divided into the first level, the second level and the third level, the first level is a low level, the second level is a medium level, and the third level is a high level. The specific division standard can be divided by setting a threshold value, which will not be repeated here; further, the planned path of the industrial vehicle is adjusted in real time according to the path planning priority. When it is at the first level, it means that there is no impact on the planned path, and the corresponding path can be used as the preferred path for the industrial vehicle to move; when it is at the second level, it means that there is a possible emergency in the local area on the path, and it is recommended to slow down or choose an alternative route; when it is at the third level, it is necessary to brake immediately to stop the industrial vehicle, and wait for the path to pass before replanning the driving route. The ultimate goal is to ensure that industrial vehicles can operate safely and efficiently in complex industrial environments, and effectively improve the accuracy and safety of path planning of industrial vehicle ADAS systems, so that the planned path obtained is safer and more efficient.

[0055] This embodiment first constructs a connectivity graph corresponding to the current time period according to the driving information of industrial vehicles and the road distribution of the working area in the current time period, and then evaluates the influence of the fork node at each information collection according to the emergency type of each fork node in the connectivity graph and the number of links of each fork node in the connectivity graph. Combined with the influence of each fork node at each information collection and the number of fork nodes between each fork node and other fork nodes on each link, the passability between different road forks is evaluated to obtain a route passability index. The larger the route passability index, the higher the passability of the road between the corresponding two forks. The nodes in the connectivity graph are clustered, and the information discontinuity influence degree of each fork node is obtained according to the number of nodes in the cluster to which each fork node belongs and the distribution discreteness of the route passability index between each fork node and the fork node directly associated with it in the connectivity graph, so as to plan the path of the industrial vehicle and perform a comprehensive analysis on the multimodal data. The system can generate a more optimized path planning scheme, reduce path deviation, and improve the operation efficiency and safety of the vehicle. This embodiment collects driving data of industrial vehicles in real time during driving, ensuring that the vehicles can quickly respond to environmental changes and status updates, thereby making more accurate and timely decisions in path planning. Through intelligent agents, dynamic collection, processing, fusion and analysis of multimodal data and dynamic data are realized, and large models are used for feature extraction, pattern recognition and anomaly detection. The trained large model is used to efficiently fuse multimodal data, analyze and predict data, and improve the accuracy of collaborative path planning for industrial vehicles.

[0056] System implementation for collaborative path planning using an industrial vehicle ADAS system: See also Figure 2 , which shows a structural block diagram of a system for implementing path collaborative planning using an industrial vehicle ADAS system provided by an embodiment of the present invention. The system may include a data acquisition module, a first calculation module, a second calculation module and a path planning module.

[0057] The data acquisition module is used to obtain the driving information of the industrial vehicle and the road distribution of the working area in the current time period, and to construct a connected graph based on the driving information and the road distribution. The nodes in the connected graph include the fork nodes of the road and the industrial vehicle position nodes. The first calculation module is used to obtain the influence degree of each fork node at each information collection according to the emergency situation type of each fork node in the connected graph at each information collection and the number of links of each fork node in the connected graph; and obtain the route traffic index between each fork node and other fork nodes by combining the influence degree of each fork node in the connected graph at each information collection and the number of fork nodes between each fork node and other fork nodes on each link; A second calculation module is used to cluster the nodes in the connectivity graph, and determine the degree of information discontinuity influence of each fork node according to the number of nodes in the cluster to which each fork node belongs and the distribution discreteness of the route traffic index between each fork node in the connectivity graph and the fork nodes directly associated with it; The path planning module is used to plan the path of industrial vehicles in real time based on the impact of information discontinuity.

[0058] It should be understood that Figure 2 The structural block diagram of a system for implementing path cooperative planning using an industrial vehicle ADAS system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above-mentioned methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as on a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0059] For more details about the above modules, please refer to other places in this manual and will not be repeated here.

[0060] In other embodiments, a device for implementing collaborative path planning using an industrial vehicle ADAS system is also provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the above-mentioned method for implementing collaborative path planning using an industrial vehicle ADAS system. The device can specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the method for implementing collaborative path planning using an industrial vehicle ADAS system provided in the above-mentioned embodiment.

[0061] In other embodiments, a computer program product is also provided. When the computer program product is run on a computer, the computer executes the above-mentioned related steps to implement the method for realizing path collaborative planning using an industrial vehicle ADAS system provided in the above embodiment.

[0062] In other embodiments, a computer-readable storage medium is provided, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement the method for collaborative path planning using an industrial vehicle ADAS system provided in the above embodiment.

[0063] Among them, the provided system, electronic device, computer program product, and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0064] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for realizing path collaborative planning using an industrial vehicle ADAS system, characterized in that: The method comprises the following steps: Acquire the driving information of the industrial vehicle and the road distribution of the working area in the current time period, and construct a connected graph based on the driving information and the road distribution, wherein the nodes in the connected graph include the fork nodes of the road and the position nodes of the industrial vehicle; Obtaining the influence of each fork node at each information collection according to the emergency situation type of each fork node in the connected graph at each information collection and the number of links of each fork node in the connected graph; obtaining the route traffic index between each fork node and other fork nodes by combining the influence of each fork node at each information collection in the connected graph and the number of fork nodes between each fork node and other fork nodes on each link; Clustering the nodes in the connectivity graph, and determining the degree of information discontinuity impact of each fork node according to the number of nodes in the cluster to which each fork node belongs and the distribution discreteness of the route traffic index between each fork node and the fork nodes directly associated with it in the connectivity graph; Plan the paths of industrial vehicles in real time based on the impact of information discontinuities.

2. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 1, characterized in that: The step of obtaining the influence degree of each fork node at each information collection according to the emergency situation type of each fork node in the connectivity graph at each information collection and the number of connections of each fork node in the connectivity graph comprises: Based on the emergency situation type of the candidate fork node at each information collection in the current time period, determine the corresponding preset impact coefficient; According to the number of links of the candidate fork node in the connectivity graph and the preset influence coefficient, the influence degree of the candidate fork node at each information collection is obtained; The candidate fork node is any fork node in the connected graph.

3. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 2, characterized in that: The step of obtaining the influence degree of the candidate fork node at each information collection according to the number of links of the candidate fork node in the connectivity graph and the preset influence coefficient includes: The normalized result of the product of the number of links of the candidate fork node in the connectivity graph and the preset influence coefficient corresponding to each information collection of the candidate fork node in the current time period is determined as the influence degree of the candidate fork node at each information collection.

4. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 1, characterized in that: The method combines the influence degree of each fork node in the connectivity graph at each information collection and the number of fork nodes between each fork node and other fork nodes on each connection line to obtain the route traffic index between each fork node and other fork nodes, including: Calculate the first sum of the influence of the first fork node during all information collections in the current time period; count the total number of all fork nodes between the first fork node and the second fork node on all links in the connected graph; Obtaining a route traffic index between a first fork node and a second fork node according to the first sum value and the total number; The first fork node is any fork node in the connected graph, and the second fork node is any fork node in the connected graph except the first fork node and on the same line as the first fork node.

5. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 4, characterized in that: Obtaining a route traffic index between a first fork node and a second fork node according to the first sum value and the total number, including: A first product between the first sum and the total number is calculated, and a negative correlation normalization result of the first product is used as a route traffic index between the first fork node and the second fork node.

6. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 1, characterized in that: A connected graph clustering algorithm is used to cluster all nodes in the connected graph.

7. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 2, characterized in that: The method of determining the degree of information discontinuity influence of each fork node according to the number of nodes in the cluster to which each fork node belongs and the distribution discreteness of the route traffic index between each fork node and the fork node directly associated with it in the connectivity graph comprises: Calculate the degree of dispersion of the route traffic index between the candidate fork node and all fork nodes directly associated with it; According to the number of nodes in the cluster to which the candidate fork node belongs and the degree of discreteness, the degree of influence of information discontinuity of the candidate fork node is obtained. The number of nodes in the cluster to which the candidate fork node belongs is positively correlated with the degree of influence of information discontinuity, and the degree of discreteness is negatively correlated with the degree of influence of information discontinuity.

8. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 7, characterized in that: The acquisition of the discrete degree includes: determining the standard deviation of the route traffic index between the candidate fork node and all the fork nodes directly associated with the candidate fork node as the discrete degree.

9. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 1, characterized in that: The real-time planning of the path of the industrial vehicle based on the degree of influence of information discontinuity includes: The degree of influence of the information discontinuity is used as the weight of the path node, and all path planning priorities are divided into the first level, the second level and the third level according to the large model; When at the first level, the corresponding path is used as the preferred path, and the industrial vehicle performs mobile operations; When in the second level, the industrial vehicle decelerates on the corresponding path or selects an alternative path; When in the third level, braking measures are taken on the industrial vehicle.

10. The method for realizing path collaborative planning using an industrial vehicle ADAS system according to claim 1, characterized in that: The constructing a connectivity graph based on the driving information and the road distribution includes: The positions of industrial vehicles at each time of information collection in the current time period and the forks in the working area roads passed by the industrial vehicles are taken as nodes in the connected graph. The corresponding nodes in the connected graph are connected according to the paths traveled by all industrial vehicles in the current time period to obtain a connected graph.

Images